Multi-objective location-routing optimization based on machine learning for green municipal waste management

Most of the existing municipal waste management (MWM) systems focus on the optimization of the waste disposal center locations and waste collection paths, which can be modeled based on the location-routing problem (LRP). This study models a green MWM system by a three-objective location-routing problem to achieve equilibrium among the total cost, carbon emission, and residential satisfaction. The amount of waste demand for each customer is considered as an independent discrete random variable following a normal distribution. The multi-objectives and non-deterministic characteristics make this problem more intractable than the traditional LRP. A multi-objective optimization algorithm based on decision tree classifier is proposed for solving this problem. The decision tree classifier learns from previous searching experience, and then guides the following evolution process to avoid blind searching. The experimental results show that the proposed algorithm has high competitiveness compared with other state-of-art methods. A case study is also conducted for a real waste collection problem in a certain area of Beijing. The proposed method adopts efficient location-routing strategies to balance the total cost, carbon emissions, and distance between residential areas and waste disposal centers.

Machine learning assisted combined systems of wastewater treatment plants with constructed wetlands optimal decision-making

This study proposed an efficient framework for optimizing the design and operation of combined systems of wastewater treatment plants (WWTP) and constructed wetlands (CW). The framework coupled a WWTP model with a CW model and used a multi-objective evolutionary algorithm to identify trade-offs between energy consumption, effluent quality, and construction cost. Compared to traditional design and management approaches, the framework achieved a 27 % reduction in WWTP energy consumption or a 44 % reduction in CW cost while meeting strict effluent discharge limits for Chinese WWTP. The framework also identified feasible decision variable ranges and demonstrated the impact of different optimization strategies on system performance. Furthermore, the contributions of WWTP and CW in pollutant degradation were analyzed. Overall, the proposed framework offers a highly efficient and cost-effective solution for optimizing the design and operation of a combined WWTP and CW system.

In-silico method development and optimization of on-line comprehensive two-dimensional liquid chromatography via a shortcut model

Comprehensive two-dimensional liquid chromatography (LCxLC) represents a valuable alternative to conventional single column, or one-dimensional, liquid chromatography (1D-LC) for resolving multiple components in a complex mixture in a short time. However, developing LCxLC methods with trial-and-error experiments is challenging and time-consuming, which is why the technique is not dominant despite its significant potential. This work presents a novel shortcut model to in-silico predicting retention time and peak width within an RPLCxRPLC separation system (i.e., LCxLC systems that use reversed-phase columns (RPLC) in both separation dimensions). Our computationally effective model uses the hydrophobic-subtraction model (HSM) to predict retention and considers limitations due to the sample volume, undersampling and the maximum pressure drop. The shortcut model is used in a two-step strategy for sample-dependent optimization of RPLCxRPLC separation systems. In the first step, the Kendall's correlation coefficient of all possible combinations of available columns is evaluated, and the best column pair is selected accordingly. In the second step, the optimal values of design variables, flow rate, pH and sample loop volume, are obtained via multi-objective stochastic optimization. The strategy is applied to method development for the separation of 8, 12 and 16 component mixtures. It is shown that the proposed strategy provides an easy way to accelerate method development for full-comprehensive 2D-LC systems as it does not require any experimental campaign and an entire optimization run can take less than two minutes.

A protein-protein interaction network aligner study in the multi-objective domain

BACKGROUND AND OBJECTIVE

The protein-protein interaction (PPI) network alignment has proven to be an efficient technique in the diagnosis and prevention of certain diseases. However, the difficulty in maximizing, at the same time, the two qualities that measure the goodness of alignments (topological and biological quality) has led aligners to produce very different alignments. Thus making a comparative study among alignments of such different qualities a big challenge. Multi-objective optimization is a computer method, which is very powerful in this kind of contexts because both conflicting qualities are considered together. Analysing the alignments of each PPI network aligner with multi-objective methodologies allows you to visualize a bigger picture of the alignments and their qualities, obtaining very interesting conclusions. This paper proposes a comprehensive PPI network aligner study in the multi-objective domain.

METHODS

Alignments from each aligner and all aligners together were studied and compared to each other via Pareto dominance methodologies. The best alignments produced by each aligner and all aligners together for five different alignment scenarios were displayed in Pareto front graphs. Later, the aligners were ranked according to the topological, biological, and combined quality of their alignments. Finally, the aligners were also ranked based on their average runtimes.

RESULTS

Regarding aligners constructing the best overall alignments, we found that SAlign, BEAMS, SANA, and HubAlign are the best options. Additionally, the alignments of best topological quality are produced by: SANA, SAlign, and HubAlign aligners. On the contrary, the aligners returning the alignments of best biological quality are: BEAMS, TAME, and WAVE. However, if there are time constraints, it is recommended to select SAlign to obtain high topological quality alignments and PISwap or SAlign aligners for high biological quality alignments.

CONCLUSIONS

The use of the SANA aligner is recommended for obtaining the best alignments of topological quality, BEAMS for alignments of the best biological quality, and SAlign for alignments of the best combined topological and biological quality. Simultaneously, SANA and BEAMS have above-average runtimes. Therefore, it is suggested, if necessary due to time restrictions, to choose other, faster aligners like SAlign or PISwap whose alignments are also of high quality.

Optimizing hydropower scheduling through accurate power load prediction: A practical case study

Hydropower stations that are part of the grid system frequently encounter challenges related to the uneven distribution of power generation and associated benefits, primarily stemming from delays in obtaining timely load data. This research addresses this issue by developing a scheduling model that combines power load prediction and dual-objective optimization. The practical application of this model is demonstrated in a real-case scenario, focusing on the Shatuo Hydropower Station in China. In contrast to current models, the suggested model can achieve optimal dispatch for grid-connected hydropower stations even when power load data is unavailable. Initially, the model assesses various prediction models for estimating power load and subsequently incorporates the predictions into the GA-NSGA-II algorithm, specifically an enhanced elite non-dominated sorting genetic algorithm. This integration is performed while considering the proposed objective functions to optimize the discharge flow of the hydropower station. The outcomes reveal that the CNN-GRU model, denoting Convolutional Neural Network-Gated Recursive Unit, exhibits the highest prediction accuracy, achieving R-squared and RMSE (i.e., Root Mean Square Error) values of 0.991 and 0.026, respectively. The variance between scheduling based on predicted load values and actual load values is minimal, staying within 5 (m 3 / s ), showcasing practical effectiveness. The optimized scheduling outcomes in the real case study yield dual advantages, meeting both the demands of ship navigation and hydropower generation, thus achieving a harmonious balance between the two requirements. This approach addresses the real-world challenges associated with delayed load data collection and insufficient scheduling, offering an efficient solution for managing hydropower station scheduling to meet both power generation and navigation needs.

Real-time task parameter selection method of accounting system based on multi-objective optimization and genetic algorithm

The progress of the digital economy has promoted the enterprise accounting system. To accelerate the update and evolution of accounting systems, we propose a parameter selection method based on multi-objective optimization and genetic algorithm. Firstly, this article proposes an accounting feature extraction method based on multimodal information embedding. The dual-branch structure and feature pyramid network are used to realize the feature extraction of the information involved in accounting. Then, this article proposes a multi-objective parameter selection method based on a parallel genetic algorithm. By embedding a genetic algorithm in the process of dual-branch model training, the model's ability to sense accounting information is improved. Finally, using the above two methods, an accounting system evaluation method upon recurrent Transformer is proposed to improve the financial situation of enterprises. Our experiments have proven that our approach attains a remarkable performance with an 87.6% F-value, 83.5% mAP value, and 83.4% accuracy. These results position our method at an advanced level globally, showcasing its capability to enhance accounting systems.

Towards an optimal design of a functionally graded porous uncemented acetabular component using genetic algorithm

Generation of polyethylene wear debris and peri‑prosthetic bone resorption have been identified as potential causes of acetabular component loosening in Total Hip Arthroplasty. This study was aimed at optimization of a functionally graded porous acetabular component to minimize peri‑prosthetic bone resorption and polyethylene liner wear. Porosity levels (porosity values at acetabular rim, and dome) and functional gradation exponents (radial and polar) were considered as the design parameters. The relationship between porosity and elastic properties were obtained from numerical homogenization. The multi-objective optimization was carried out using a non-dominated sorting genetic algorithm integrated with finite element analysis of the hemipelvises subject to various loading conditions of common daily activities. The optimal functionally graded porous designs (OFGPs -1, -2, -3, -4, -5) exhibited less strain-shielding in cancellous bone compared to solid metal-backing. Maximum bone-implant interfacial micromotions (63-68 μm) for OFGPs were found to be close to that of solid metal-backing (66 μm), which might facilitate bone ingrowth. However, OFGPs exhibited an increase in volumetric wear (3-10 %) compared to solid metal-backing. The objective functions were found to be more sensitive to changes in polar gradation exponent than radial gradation exponent, based on the Sobol' method. Considering the common failure mechanisms, OFGP-1, having highly porous acetabular rim and less porous dome, appears to be a better alternative to the solid metal-backing.

Transformation scenarios towards multifunctional landscapes: A multi-criteria land-use allocation model applied to Jambi Province, Indonesia

In tropical regions, shifting from forests and traditional agroforestry to intensive plantations generates conflicts between human welfare (farmers' demands and societal needs) and environmental protection. Achieving sustainability in this transformation will inevitably involve trade-offs between multiple ecological and socioeconomic functions. To address these trade-offs, our study used a new methodological approach allowing the identification of transformation scenarios, including theoretical landscape compositions that satisfy multiple ecological functions (i.e., structural complexity, microclimatic conditions, organic carbon in plant biomass, soil organic carbon and nutrient leaching losses), and farmers needs (i.e., labor and input requirements, total income to land, and return to land and labor) while accounting for the uncertain provision of these functions and having an actual potential for adoption by farmers. We combined a robust, multi-objective optimization approach with an iterative search algorithm allowing the identification of ecological and socioeconomic functions that best explain current land-use decisions. The model then optimized the theoretical land-use composition that satisfied multiple ecological and socioeconomic functions. Between these ends, we simulated transformation scenarios reflecting the transition from current land-use composition towards a normative multifunctional optimum. These transformation scenarios involve increasing the number of optimized socioeconomic or ecological functions, leading to higher functional richness (i.e., number of functions). We applied this method to smallholder farms in the Jambi Province, Indonesia, where traditional rubber agroforestry, rubber plantations, and oil palm plantations are the main land-use systems. Given the currently practiced land-use systems, our study revealed short-term returns to land as the principal factor in explaining current land-use decisions. Fostering an alternative composition that satisfies additional socioeconomic functions would require minor changes ("low-hanging fruits"). However, satisfying even a single ecological indicator (e.g., reduction of nutrient leaching losses) would demand substantial changes in the current land-use composition ("moonshot"). This would inevitably lead to a profit decline, underscoring the need for incentives if the societal goal is to establish multifunctional agricultural landscapes. With many oil palm plantations nearing the end of their production cycles in the Jambi province, there is a unique window of opportunity to transform agricultural landscapes.

A fuzzy interval dynamic optimization model for surface and groundwater resources allocation under water shortage conditions, the case of West Azerbaijan Province, Iran

The allocation of water in areas which face shortage of water especially during hot dry seasons is of utmost importance. This is normally affected by various factors, the management of which takes a lot of time and energy with efforts falling infertile in many cases. In recent years, scholars have been trying to investigate the applicability of fuzzy interval optimization models in attempts to address the problem. However, a review of literature indicates that in applicating such models, the dynamic nature of the problem has mostly been overlooked. Therefore, the aim of the present study is to provide a fuzzy interval dynamic optimization model for the allocation of surface and groundwater resources under water shortage conditions in West Azerbaijan Province, Iran. In so doing, an optimization model for the allocation of water resources was designed and then was validated by removing surface and groundwater resources and analyzing its performance once these resources were removed. The model was then applied in the case study of ten regions in West Azerbaijan Province and the optimal allocation values and water supply percentages were determined for each region over 12 periods. The results showed that the increase in total demand has the greatest effect while the increase in groundwater industrial demand has the least effect on the supply reduction rate. The increase of uncertainty up to 50% in the fuzzy interval programming would lead to subsequent increases in groundwater extraction by up to 19% and decreases in water supply by up to 10%. The increase of uncertainty in the fuzzy interval dynamic model would cause an increase in groundwater extraction to slightly more than 10% and a decrease in water supply to 0.05%. Therefore, implementing the fuzzy interval dynamic programming model would result in better gains and would reduce uncertainty effects. This would imply that using a mathematical model can result in better gains and can provide better footings for more informed decisions by authorities for managing water resources.

Solar photovoltaic panel production in Mexico: A novel machine learning approach

This study examines the potential for widespread solar photovoltaic panel production in Mexico and emphasizes the country's unique qualities that position it as a strong manufacturing candidate in this field. An advanced model based on artificial neural networks has been developed to predict solar photovoltaic panel plant metrics. This model integrates a state-of-the-art non-linear programming framework using Pyomo as well as an innovative optimization and machine learning toolkit library. This approach creates surrogate models for individual photovoltaic plants including production timelines. While this research, conducted through extensive simulations and meticulous computations, unveiled that Latin America has been significantly underrepresented in the production of silicon, wafers, cells, and modules within the global market; it also demonstrates the substantial potential of scaling up photovoltaic panel production in Mexico, leading to significant economic, social, and environmental benefits. By hyperparameter optimization, an outstanding and competitive artificial neural network model has been developed with a coefficient of determination values above 0.99 for all output variables. It has been found that water and energy consumption during PV panel production is remarkable. However, water consumption (33.16 × 10-4 m3/kWh) and the emissions generated (1.12 × 10-6 TonCO2/kWh) during energy production are significantly lower than those of conventional power plants. Notably, the results highlight a positive economic trend, with module production plants generating the highest profits (35.7%) among all production stages, while polycrystalline silicon production plants yield comparatively lower earnings (13.0%). Furthermore, this study underscores a critical factor in the photovoltaic panel production process which is that cell production plants contribute the most to energy consumption (39.7%) due to their intricate multi-stage processes. The blending of Machine Learning and optimization models heralds a new era in resource allocation for a more sustainable renewable energy sector, offering a brighter, greener future.

Comparative life-cycle sustainability assessment of centralized and decentralized remediation strategies at the city level

Remediation of contaminated soil at industrial sites has become a challenge and an opportunity for sustainable urban land use, considering the substantial secondary impacts resulting from remediation activities. The design of soil remediation strategies for multi-site remediation from a regional perspective is of great significance for cities with a large number of brownfields. Centralized and decentralized facilities have been studied in different environmental fields, yet limited research has focused on centralized soil remediation, specifically the treatment of contaminated soil from different sites through the construction of shared soil treatment facilities. This study proposes a framework for comparing centralized and decentralized strategies for contaminated soil remediation based on the integration of life-cycle sustainability assessment and multi-objective optimization. With Zhuzhou, an industrial city in China, serving as an example, results show that after optimization, the centralized scenario can reduce total environmental impacts by 25 %-41 %. In addition, the centralized scenario can reduce economic costs by 27 %-39 %, saving up to 176 million USD. The advantages of the centralized soil remediation strategy include: (1) increased use of soil washing, (2) reduced use of off-site disposal, and (3) reduced construction and efficient utilization of soil treatment facilities. In conclusion, the centralized strategy is relatively suitable for cities or areas with a large number of medium or small-sized contaminated sites. The built framework can quantitatively evaluate multiple sites soil remediation at both the city and individual site level, allowing for a straightforward and objective comparison with the optimal remediation design.

Maximizing efficiency in sunflower breeding through historical data optimization

Genomic selection (GS) has become an increasingly popular tool in plant breeding programs, propelled by declining genotyping costs, an increase in computational power, and rediscovery of the best linear unbiased prediction methodology over the past two decades. This development has led to an accumulation of extensive historical datasets with genotypic and phenotypic information, triggering the question of how to best utilize these datasets. Here, we investigate whether all available data or a subset should be used to calibrate GS models for across-year predictions in a 7-year dataset of a commercial hybrid sunflower breeding program. We employed a multi-objective optimization approach to determine the ideal years to include in the training set (TRS). Next, for a given combination of TRS years, we further optimized the TRS size and its genetic composition. We developed the Min_GRM size optimization method which consistently found the optimal TRS size, reducing dimensionality by 20% with an approximately 1% loss in predictive ability. Additionally, the Tails_GEGVs algorithm displayed potential, outperforming the use of all data by using just 60% of it for grain yield, a high-complexity, low-heritability trait. Moreover, maximizing the genetic diversity of the TRS resulted in a consistent predictive ability across the entire range of genotypic values in the test set. Interestingly, the Tails_GEGVs algorithm, due to its ability to leverage heterogeneity, enhanced predictive performance for key hybrids with extreme genotypic values. Our study provides new insights into the optimal utilization of historical data in plant breeding programs, resulting in improved GS model predictive ability.

Indicator based multi-criteria decision support systems for wastewater treatment plants

Wastewater treatment plant decision makers face stricter regulations regarding human health protection, environmental preservation, and emissions reduction, meaning they must improve process sustainability and circularity, whilst maintaining economic performance. This creates complex multi-objective problems when operating and selecting technologies to meet these demands, resulting in the development of many decision support systems for the water sector. European Commission publications highlight their ambition for greater levels of sustainability, circularity, and environmental and human health protection, which decision support system implementation should align with to be successful in this region. Following the review of 57 wastewater treatment plant decision support systems, the main function of multi-criteria decision-making tools are technology selection and the optimisation of process operation. A large contrast regarding their aims is found, as process optimisation tools clearly define their goals and indicators used, whilst technology selection procedures often use vague language making it difficult for decision makers to connect selected indicators and resultant outcomes. Several recommendations are made to improve decision support system usage, such as more rigorous indicator selection protocols including participatory selection approaches and expansion of indicators sets, as well as more structured investigation of results including the use of sensitivity or uncertainty analysis, and error quantification.

Keeping your best options open with AI-based treatment planning in prostate and cervix brachytherapy

PURPOSE

Without a clear definition of an optimal treatment plan, no optimization model can be perfect. Therefore, instead of automatically finding a single "optimal" plan, finding multiple, yet different near-optimal plans, can be an insightful approach to support radiation oncologists in finding the plan they are looking for.

METHODS AND MATERIALS

BRIGHT is a flexible AI-based optimization method for brachytherapy treatment planning that has already been shown capable of finding high-quality plans that trade-off target volume coverage and healthy tissue sparing. We leverage the flexibility of BRIGHT to find plans with similar dose-volume criteria, yet different dose distributions. We further describe extensions that facilitate fast plan adaptation should planning aims need to be adjusted, and straightforwardly allow incorporating hospital-specific aims besides standard protocols.

RESULTS

Results are obtained for prostate (n = 12) and cervix brachytherapy (n = 36). We demonstrate the possible differences in dose distribution for optimized plans with equal dose-volume criteria. We furthermore demonstrate that adding hospital-specific aims enables adhering to hospital-specific practice while still being able to automatically create cervix plans that more often satisfy the EMBRACE-II protocol than clinical practice. Finally, we illustrate the feasibility of fast plan adaptation.

CONCLUSIONS

Methods such as BRIGHT enable new ways to construct high-quality treatment plans for brachytherapy while offering new insights by making explicit the options one has. In particular, it becomes possible to present to radiation oncologists a manageable set of alternative plans that, from an optimization perspective are equally good, yet differ in terms of coverage-sparing trade-offs and shape of the dose distribution.

GrMoNAS: A granularity-based multi-objective NAS framework for efficient medical diagnosis

Neural Architecture Search (NAS) has been widely applied to automate medical image diagnostics. However, traditional NAS methods require significant computational resources and time for performance evaluation. To address this, we introduce the GrMoNAS framework, designed to balance diagnostic accuracy and efficiency using proxy datasets for granularity transformation and multi-objective optimization algorithms. The approach initiates with a coarse granularity phase, wherein diverse candidate neural architectures undergo evaluation utilizing a reduced proxy dataset. This initial phase facilitates the swift and effective identification of architectures exhibiting promise. Subsequently, in the fine granularity phase, a comprehensive validation and optimization process is undertaken for these identified architectures. Concurrently, employing multi-objective optimization and Pareto frontier sorting aims to enhance both accuracy and computational efficiency simultaneously. Importantly, the GrMoNAS framework is particularly suitable for hospitals with limited computational resources. We evaluated GrMoNAS in a range of medical scenarios, such as COVID-19, Skin cancer, Lung, Colon, and Acute Lymphoblastic Leukemia diseases, comparing it against traditional models like VGG16, VGG19, and recent NAS approaches including GA-CNN, EBNAS, NEXception, and CovNAS. The results show that GrMoNAS achieves comparable or superior diagnostic precision, significantly enhancing diagnostic efficiency. Moreover, GrMoNAS effectively avoids local optima, indicating its significant potential for precision medical diagnosis.

Hospital food management: a multi-objective approach to reduce waste and costs

Food waste contributes significantly to greenhouse emissions and represents a substantial portion of overall waste within hospital facilities. Furthermore, uneaten food leads to a diminished nutritional intake for patients, that typically are vulnerable and ill. Therefore, this study developed mathematical models for constructing patient meals in a 1000-bed hospital located in Florida. The objective is to minimize food waste and meal-building costs while ensuring that the prepared meals meet the required nutrients and caloric content for patients. To accomplish these objectives, four mixed-integer programming models were employed, incorporating binary and continuous variables. The first model establishes a baseline for how the system currently works. This model generates the meals without minimizing waste or cost. The second model minimizes food waste, reducing waste up to 22.53 % compared to the baseline. The third model focuses on minimizing meal-building costs and achieves a substantial reduction of 37 %. Finally, a multi-objective optimization model was employed to simultaneously reduce both food waste and cost, resulting in reductions of 19.70 % in food waste and 32.66 % in meal-building costs. The results demonstrate the effectiveness of multi-objective optimization in reducing waste and costs within large-scale food service operations.

Efficient implicit constraint handling approaches for constrained optimization problems

Many real-world optimization problems, particularly engineering ones, involve constraints that make finding a feasible solution challenging. Numerous researchers have investigated this challenge for constrained single- and multi-objective optimization problems. In particular, this work extends the boundary update (BU) method proposed by Gandomi and Deb (Comput. Methods Appl. Mech. Eng. 363:112917, 2020) for the constrained optimization problem. BU is an implicit constraint handling technique that aims to cut the infeasible search space over iterations to find the feasible region faster. In doing so, the search space is twisted, which can make the optimization problem more challenging. In response, two switching mechanisms are implemented that transform the landscape along with the variables to the original problem when the feasible region is found. To achieve this objective, two thresholds, representing distinct switching methods, are taken into account. In the first approach, the optimization process transitions to a state without utilizing the BU approach when constraint violations reach zero. In the second method, the optimization process shifts to a BU method-free optimization phase when there is no further change observed in the objective space. To validate, benchmarks and engineering problems are considered to be solved with well-known evolutionary single- and multi-objective optimization algorithms. Herein, the proposed method is benchmarked using with and without BU approaches over the whole search process. The results show that the proposed method can significantly boost the solutions in both convergence speed and finding better solutions for constrained optimization problems.

NSCSO: a novel multi-objective non-dominated sorting chicken swarm optimization algorithm

Addressing the challenge of efficiently solving multi-objective optimization problems (MOP) and attaining satisfactory optimal solutions has always posed a formidable task. In this paper, based on the chicken swarm optimization algorithm, proposes the non-dominated sorting chicken swarm optimization (NSCSO) algorithm. The proposed approach involves assigning ranks to individuals in the chicken swarm through fast non-dominance sorting and utilizing the crowding distance strategy to sort particles within the same rank. The MOP is tackled based on these two strategies, with the integration of an elite opposition-based learning strategy to facilitate the exploration of optimal solution directions by individual roosters. NSCSO and 6 other excellent algorithms were tested in 15 different benchmark functions for experiments. By comprehensive comparison of the test function results and Friedman test results, the results obtained by using the NSCSO algorithm to solve the MOP problem have better performance. Compares the NSCSO algorithm with other multi-objective optimization algorithms in six different engineering design problems. The results show that NSCSO not only performs well in multi-objective function tests, but also obtains realistic solutions in multi-objective engineering example problems.

Multi-objective optimization of saline water irrigation in arid oasis regions: Integrating water-saving, salinity control, yield enhancement, and CO2 emission reduction for sustainable cotton production

Brackish water stands as a promising alternative to mitigate freshwater scarcity in arid regions. However, its application poses potential threats to agricultural sustainability. There is a need to establish a clear understanding of the economic and ecological benefits. We conducted a two-year (2021-2022) field experiment to investigate the effects of four different irrigation water salinity levels on soil electrical conductivity, cotton yield, water use efficiency, CO2 emissions, and carbon sequestration. The salinity levels were designated as CK (0.85 g L-1), S1 (3 g L-1), S2 (5 g L-1), and S3 (8 g L-1). Results indicated that using irrigation water with high salinity (≥5 g L-1) led to the accumulation of salt in the soil, and a decrease in plant biomass and seed cotton yield. Compared to CK, the S3 treatment decreased by 18.72 % and 20.10 % in the respective two years. Interestingly, using brackish water (3 L-1 and 5 g L-1) decreased the rate and cumulative CO2 emissions, and increased the carbon emission efficiency and carbon sequestration by 0.098-0.094 kg kg-1 and 871-1859 kg ha-1 in 2021, 0.098-0.094 kg kg-1 and 617-1995 kg ha-1 in 2022, respectively. To comprehensively evaluate the tradeoff between economic and ecological benefits, we employed the TOPSIS method, and S1 was identified as the optimal irrigation salinity. Through fitting analysis, the most suitable irrigation salinity levels for 2021 and 2022 were determined as 3.52 g L-1 and 3.31 g L-1, respectively. From the perspective of water conservation, salinity management, yield improvement, and reduction of CO2 emissions, it is feasible to utilize brackish water for irrigation purposes, as long as the salinity does not exceed 3.52 g L-1 (first year) and 3.31 g L-1 (second year).

Modifying national industrial structure for reducing heavy metals in China: A nexus-based multi-objective optimization approach

Heavy metals (HMs) exhibit significant toxicity and can lead to a range of health issues. Certain HMs share common emission sources, necessitating an exploration of the nexus among various HMs for achieving collaborative reductions. Considering the efficacy and feasibility of industrial modification to environmental pressures, this paper proposes a novel nexus-based optimization approach based on nexus analysis, multi-region input-output (MRIO) table, and multi-objective optimization to mitigate atmospheric HMs. The atmospheric HM emission inventory in 2017 is first compiled. Subsequently, the Integrated Nexus Strength of HMs Risk (HMR-INS) is proposed and employed to determine the range of sectoral output variations. Finally, a multi-objective optimization approach is employed based on the MRIO table in 2017. Compared with the traditional optimization method, the proposed approach performs better regarding HM-related risks and total output, leading to a 1.9 million tons increase in reduction on HM-related risks and a 1.37 trillion yuan increment in total output. Some further analyses are also given to provide feasible solutions for industrial modification, which considers both the economic efficiency and the stability of the industrial structure.

Multi-objective optimization of the hybrid photovoltaic-battery-diesel-desalination system based on multi-type of desalination unit

Meeting the energy and water demands of remote areas has created significant challenges globally. To address this issue, the utilization of hybrid energy-water systems, integrated with renewable energies, has been highlighted as a viable solution. This work has been focused on the multi-objective optimization of a hybrid energy system, encompassing photovoltaic panels, batteries, diesel generators, and desalination units. The design goals to achieve the optimal configuration include minimizing system costs, reducing carbon dioxide emissions, enhancing the renewable factor, and improving reliability. Also, for the mentioned design goals, the performance of three desalination methods including reverse osmosis (RO), multi-stage flash (MSF), and multiple-effect distillation (MED) was evaluated by Hybrid Optimization of Multiple Energy Resources (HOMER) software. Our findings reveal that the RO desalination method, when combined with renewable energy, outperforms other methods both economically and environmentally. Notably, the RO method reduces net present cost (NPC) by 6.18% and 8.25% and carbon dioxide emissions by 38% and 46%, respectively, compared to MED and MSF methods. Additionally, sensitivity analysis, considering factors such as interest rate, photovoltaic panel cost, battery cost, and fuel cost, was conducted on NPC. The results showed that with a 2% decrease in the interest rate, the amount of NPC increases by about 2.4% due to the increase in the share of renewable energy. Therefore, reducing the interest rate helps to design a system with less carbon dioxide emissions. This work, by highlighting the economic and environmental implications of different desalination methods, as well as key cost factors, contributes to the optimal design of combined energy-water schemes for remote areas.

A low-carbon economic dispatch method for regional integrated energy system based on multi-objective chaotic artificial hummingbird algorithm

This paper investigates Regional Integrated Energy Systems (RIES), emphasizing the connection of diverse energy supply subsystems to address varied user needs and enhance operational efficiency. A novel low-carbon economic dispatch method, utilizing the multi-objective chaotic artificial hummingbird algorithm, is introduced. The method not only optimizes economic and environmental benefits but also aligns with "carbon peak and carbon neutrality" objectives. The study begins by presenting a comprehensive low-carbon economic dispatch model, followed by the proposal of the multi-objective chaotic artificial hummingbird algorithm, crucial for deriving the Pareto frontier of the low-carbon economic dispatch model. Additionally, we introduce a TOPSIS approach based on combined subjective and objective weights, this approach harnesses the objective data from the Pareto solution set deftly, curbs the subjective biases of dispatchers effectively and facilitates the selection of an optimal system operation plan from the Pareto frontier. Finally, the simulation results highlight the outstanding performance of our method in terms of optimization outcomes, convergence efficiency, and solution diversity. Noteworthy among these results is an 8.8% decrease in system operational economic costs and a 14.2% reduction in carbon emissions.

Multi-objective genetic algorithm calibration of colored self-compacting concrete using DEM: an integrated parallel approach

A detailed numerical simulation of Colored Self-Compacting Concrete (CSCC) was conducted in this research. Emphasis was placed on an innovative calibration methodology tailored for ten unique CSCC mix designs. Through the incorporation of multi-objective optimization, MATLAB's Genetic Algorithm (GA) was seamlessly integrated with PFC3D, a prominent Discrete Element Modeling (DEM) software package. This integration facilitates the exchange of micro-parameter values, where MATLAB's GA optimizes these parameters, which are then input into PFC3D to simulate the behavior of CSCC mix designs. The calibration process is fully automated through a MATLAB script, complemented by a fish script in PFC, allowing for an efficient and precise calibration mechanism that automatically terminates based on predefined criteria. Central to this approach is the Uniaxial Compressive Strength (UCS) test, which forms the foundation of the calibration process. A distinguishing aspect of this study was the incorporation of pigment effects, reflecting the cohesive behavior of cementitious components, into the micro-parameters influencing the cohesion coefficient within DEM. This innovative approach ensured significant alignment between simulations and observed macro properties, as evidenced by fitness values consistently exceeding 0.94. This investigation not only expanded the understanding of CSCC dynamics but also contributed significantly to the discourse on advanced concrete simulation methodologies, underscoring the importance of multi-objective optimization in such studies.

Insitu synthesis of Al- MgAl2O4 composites and parametric optimization of tribological characteristics

In this research, multiobjective optimization of tribological characteristics of Al-4Mg/in-situ MgAl2O4 composites fabricated via ultrasonic cavitation treatment assisted stir casting technique was carried out. Al-4Mg alloy dispersed with 0.5, 1 and 2 wt% in-situ MgAl2O4 was prepared and the microstructural and mechanical characterisation of the same has been carried out. Reinforcement addition, load and sliding velocity at 3 different levels was considered to attain the responses wear rate and friction coefficient. To identify optimised process condition for the developed composites to attain reduced friction coefficient and wear rate condition, grey analysis is tried out. Experimental results analysed via Grey relation and analysis of variance (ANOVA) proved wt.% of MgAl2O4 particles as significant parameter trailed by load and speed. Based on grey relational grade, minimal wear loss at lowest frictional coefficient can be attained for the composite dispersed with 2 wt% of in-situ MgAl2O4 at 20 N load and 2 m/s sliding velocity. Mechanisms behind the wear loss was analysed from worn out surface micrographs.

A historical review and analysis on MOORA and its fuzzy extensions for different applications

Multi-criteria decision-making (MCDM) methods have been widely used among researchers to provide a trade-off solution between best and worst, considering conflicting criteria and sets of preferences. An efficient and systematic literature review of these methods is needed to maintain their application in distinctive domains. To this end, this paper presents a comprehensive and systematic literature survey on "multi-objective optimization by ratio analysis" (MOORA) method and its fuzzy extensions developed and discussed in recent years. This review includes articles categorized based on the publication name, publishing year, journal name, type of applications, and type of fuzzy extensions. In addition, this review will enhance the understanding of practitioners and decision-makers on the MOORA method, its development, fuzzy hybridization, different application areas, and future work. The study revealed that the MOORA technique was predominantly used with the TOPSIS approach, followed by the AHP and COPRAS methods. Furthermore, 76.28 % use single and hybridization approaches among all MOORA studies, while 23.72 % use MOORA in a fuzzy environment.

Optimization of land use planning under multi-objective demand-the case of Changchun City, China

Modeling and scenario analysis are the core elements of land use change research, and in the face of the increasingly serious ecological and environmental problems in urbanization, it is important to carry out land use simulation studies under different protection constraints for scientific planning and policy formulation. Taking Changchun City, the capital of Jilin Province, a pilot national eco-province, as an example, a CLUE-S model with coupled landscape ecological security patterns was constructed to predict and simulate the land use structure and layout under multi-objective optimization scenarios in the planning target year (2030), and the results were analyzed based on landscape index evaluation. The study found the following: (i) the proportion of ecological land area under low, medium, and high security levels in the study area was 8.7%, 64.8%, and 26.5%, respectively; (ii) under the current development trend scenario, the trend of increasing fragmentation of cultivated land patches in Changchun in 2030 will remain unchanged, with construction land spreading along the periphery in a compact and continuous pattern, while ecological land will be seriously encroached upon; and (iii) in the 2030 multi-objective optimization scenario, land use patches of all types will begin to show a tendency to cluster, with less landscape fragmentation and more connectivity, while cultivated land and construction land will also begin to converge and do not deteriorate as a result of spatial conflicts over ecological land.

Determination of the optimal feed recipe of anaerobic digesters using a mathematical model and a genetic algorithm

Recently, numerous experimental studies have been undertaken to understand the interactions between different feedstocks in anaerobic digestion. They have unveiled the potential of blending substrates in the process. Nevertheless, these experiments are time-intensive, prompting the exploration of various optimization approaches. Notably, genetic algorithms have gained interest due to their population-based structures allowing them to efficiently yield multiple Pareto-optimal solutions in a single run. This study uses a simplified static anaerobic co-digestion model as the fitness function for a multi-objective optimization. The optimization aims to achieve a methane production set-point while reducing the output ammonia nitrogen and increasing the recipe' profitability. Thus, the study employs genetic algorithms to identify Pareto fronts and constraints confined the solution space within feasible boundaries. It also underscores the influence of economic considerations on the viable solution space. Ultimately, the optimal feed recipe not only ensures stable operations within the digester but also enhances associated profits.

Research and optimization of hydrogen addition and EGR on the combustion, performance, and emission of the biodiesel-hydrogen dual-fuel engine with different loads based on the RSM

Pollutants produced by engines are a significant source of environmental pollution, so the study of engine emissions is very important. In this study, with CONVERGE software, a diesel engine model of the engine was produced. To better obtain the characteristic results of the engine, this was coupled with an improved chemical kinetics mechanism. Then, the results of this model were verified experimentally. Additionally, the effects of four different EGR rates on the combustion, performance, and emissions of a dual-fuel diesel engine were investigated by the verified model under different (50 %, 75 %, and 100 %) load conditions. Lastly, the brake specific fuel consumption, NOx emission, and HC emission were optimized by the response surface methodology (RSM). The results show that the pressure, temperature, and NOx emission in the engine's cylinder can all be reduced by raising the EGR at three different loads. Besides, the optimization results show that the engine achieves the best operating conditions at 100 % load, hydrogen fraction of 6.92 %, and EGR rate of 7.68 %.

Search-based Automatic Repair for Fairness and Accuracy in Decision-making Software

Decision-making software mainly based on Machine Learning (ML) may contain fairness issues (e.g., providing favourable treatment to certain people rather than others based on sensitive attributes such as gender or race). Various mitigation methods have been proposed to automatically repair fairness issues to achieve fairer ML software and help software engineers to create responsible software. However, existing bias mitigation methods trade accuracy for fairness (i.e., trade a reduction in accuracy for better fairness). In this paper, we present a novel search-based method for repairing ML-based decision making software to simultaneously increase both its fairness and accuracy. As far as we know, this is the first bias mitigation approach based on multi-objective search that aims to repair fairness issues without trading accuracy for binary classification methods. We apply our approach to two widely studied ML models in the software fairness literature (i.e., Logistic Regression and Decision Trees), and compare it with seven publicly available state-of-the-art bias mitigation methods by using three different fairness measurements. The results show that our approach successfully increases both accuracy and fairness for 61% of the cases studied, while the state-of-the-art always decrease accuracy when attempting to reduce bias. With our proposed approach, software engineers that previously were concerned with accuracy losses when considering fairness, are now enabled to improve the fairness of binary classification models without sacrificing accuracy.

A framework for controllable Pareto front learning with completed scalarization functions and its applications

Pareto Front Learning (PFL) was recently introduced as an efficient method for approximating the entire Pareto front, the set of all optimal solutions to a Multi-Objective Optimization (MOO) problem. In the previous work, the mapping between a preference vector and a Pareto optimal solution is still ambiguous, rendering its results. This study demonstrates the convergence and completion aspects of solving MOO with pseudoconvex scalarization functions and combines them into Hypernetwork in order to offer a comprehensive framework for PFL, called Controllable Pareto Front Learning. Extensive experiments demonstrate that our approach is highly accurate and significantly less computationally expensive than prior methods in term of inference time.

Development of an assessment-based planting structure optimization model for mitigating agricultural greenhouse gas emissions

Optimization of crop structure is an efficient way to reduce greenhouse gas (GHGs) from agriculture production. However, carbon footprint have rarely been incorporated into previous planting structure optimization models due to the challenges of assessing the spatial and temporal distribution of agricultural carbon footprint for multiple crops in irrigated districts. In addition, previous planting structure models suffered from strong subjectivity in objective function determination, and the obtained non-dominated solution set offered difficulties to decision-makers in selecting specific implementation options. To fill such gaps, an integrated accounting-assessment-optimization-decision making (AAODM) approach was proposed, which remedies the shortcomings of previous crop planting structure optimization models in carbon footprint mitigation, and overcomes the subjectivity of objective function determination and the difficulty in selecting specific implementation options. Firstly, life cycle assessment (LCA) method was used to account for the multi-year agricultural carbon footprints of multiple crops in the irrigation district. The optimization objective functions of planting structure optimization models can then be determined based on the assessment method of carbon footprint influencing factors. Next, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) was used to generate a non-dominated solution set of the optimization model. The optimal planting structure can be finally obtained based on decision making methods by determining the maximum harmonic mean (HM) and knee points (KPs) of the non-dominated solution set. The developed AAODM approach was then applied to a case study of agricultural crop management in Bayan Nur City, China. The results showed that the level of economic development was a key factor influencing the increase in carbon footprint in Bayan Nur City over the past 20 years. The regulation of the level of economic development would significantly influence the agricultural carbon footprint in Bayan Nur City. Moreover, two optimal crop cultivation patterns were provided for decision-makers by selecting solutions from the Pareto front with decision making methods. The comparison results with other methods showed that the solutions obtained by NSGA-II were superior to MOPSO in terms of carbon reduction. The developed AAODM approach for agricultural GHG mitigation could help agricultural production systems in achieving low carbon emissions and high efficiency.

A multi-objective optimization approach for the production of polyhydroxybutyrate via Chlorogloea fritschii under diurnal light with single-stage cultivation

The present study aims to optimize the nutrients for maximization of cyanobacterial biomass with high content of polyhydroxybutyrate (PHB), a bioplastic, and recovery of biomass by auto-sedimentation under diurnal light mimic to sunlight. The multi-objective optimization with desirability approach was used to improve dry cell weight (DCW), PHB content (% w/w), and auto-sedimentation concentration factor (SCF) of biomass. Initially, NaNO3, K2HPO4, TRACE (micronutrient solution), Na2EDTA, and MgSO4.7H2O were screened as important media compositions. Screening was followed by the application of response surface methodology for the development of a model used in multi-objective optimization. The optimized media selected from many optimal solutions, a set of Pareto solutions generated by multi-objective optimization was validated in a flat panel photobioreactor. Using a single-stage cultivation strategy under diurnal light, Chlorogloea fritschii TISTR 8527 has shown capability to produce DCW of 1.23 g/l with PHB content of 31.78 % and SCF of 93.63 with optimal media. This leads to the enhancement of both PHB content (2.72 fold) and SCF (1.64 fold) were observed when compared to the non-optimal medium. This is the first multi-objective optimization study for media optimization using cyanobacteria reported till now under diurnal light mimic to sunlight for bioplastic production.

A dual-population multi-objective evolutionary algorithm driven by generative adversarial networks for benchmarking and protein-peptide docking

Multi-objective optimization problems (MOPs) are characterized as optimization problems in which multiple conflicting objective functions are optimized simultaneously. To solve MOPs, some algorithms used machine learning models to drive the evolutionary algorithms, leading to the design of a variety of model-based evolutionary algorithms. However, model collapse occurs during the generation of candidate solutions, which results in local optima and poor diversity in model-based evolutionary algorithms. To address this problem, we propose a dual-population multi-objective evolutionary algorithm driven by Wasserstein generative adversarial network with gradient penalty (DGMOEA), where the dual-populations coordinate and cooperate to generate high-quality solutions, thus improving the performance of the evolutionary algorithm. We compare the proposed algorithm with the 7 state-of-the-art algorithms on 20 multi-objective benchmark functions. Experimental results indicate that DGMOEA achieves significant results in solving MOPs, where the metrics IGD and HV outperform the other comparative algorithms on 15 and 18 out of 20 benchmarks, respectively. Our algorithm is evaluated on the LEADS-PEP dataset containing 53 protein-peptide complexes, and the experimental results on solving the protein-peptide docking problem indicated that DGMOEA can effectively reduce the RMSD between the generated and the original peptide's 3D poses and achieve more competitive results.

Exergetic analysis and optimization of process variables in xylitol production: Maximizing efficiency and sustainability in biotechnological processes

This study presents an exergetic analysis of xylitol fermentative production from hemicellulose hydrolysate, aiming to optimize operational conditions in a fluidized bed bioreactor. The aerobic fermentation conditions evaluated in this study (gas flow rate - x1, hydrolysate concentration factor - x2, and recirculation flow rate - x3) were optimized using various exergetic parameters and xylitol yield as objective functions. Four objective functions were defined for the mono-objective optimization process: rational exergetic efficiency, normalized destroyed exergy, thermodynamic sustainability index, and xylitol yield factor. The results reveal that the optimization problem involves conflicting objectives when considering both yield-based and exergy-based approaches. Thus, the bioreactor's performance was formulated as a multi-objective problem, where the yield factor and thermodynamic sustainability index were simultaneously maximized. For the multi-objective optimization, the ideal operational variable ranges were found to be: 594 ≤x1≤ 619 mL/min, x2= 7 e 37 ≤x3≤ 57 L/h.

Enhancing multifunctionality in European boreal forests: The potential role of Triad landscape functional zoning

Land-use policies aim at enhancing the sustainable use of natural resources. The Triad approach has been suggested to balance the social, ecological, and economic demands of forested landscapes. The core idea is to enhance multifunctionality at the landscape level by allocating landscape zones with specific management priorities, i.e., production (intensive management), multiple use (extensive management), and conservation (forest reserves). We tested the efficiency of the Triad approach and identified the respective proportion of above-mentioned zones needed to enhance multifunctionality in Finnish forest landscapes. Through a simulation and optimization framework, we explored a range of scenarios of the three zones and evaluated how changing their relative proportion (each ranging from 0 to 100%) impacted landscape multifunctionality, measured by various biodiversity and ecosystem service indicators. The results show that maximizing multifunctionality required around 20% forest area managed intensively, 50% extensively, and 30% allocated to forest reserves. In our case studies, such landscape zoning represented a good compromise between the studied multifunctionality components and maintained 61% of the maximum achievable net present value (i.e., total timber economic value). Allocating specific proportion of the landscape to a management zone had distinctive effects on the optimized economic or multifunctionality values. Net present value was only moderately impacted by shifting from intensive to extensive management, while multifunctionality benefited from less intensive and more diverse management regimes. This is the first study to apply Triad in a European boreal forest landscape, highlighting the usefulness of this approach. Our results show the potential of the Triad approach in promoting forest multifunctionality, as well as a strong trade-off between net present value and multifunctionality. We conclude that simply applying the Triad approach does not implicitly contribute to an overall increase in forest multifunctionality, as careful forest management planning still requires clear landscape objectives.

Multi-dimensional management framework on fresh groundwater lens of Kish Island in the Persian Gulf, Iran

Groundwater in arid and semi-arid coastal aquifers is vulnerable to seawater intrusion and quality deterioration despite being one of the most reliable sources of water supply due to the increasing number of development plans and competition between water consumers. A multi-dimensional groundwater management framework is developed to trade-off between groundwater abstraction, allocation equity, groundwater quality, and energy considerations in the reverse osmosis (RO) filtration process in the fresh groundwater lens of Kish Island, Iran. An arid island confined in the Persian Gulf is modeled using 3D simulation and three well-occupied multi-objective evolutionary optimization algorithms. Four objectives include: maximizing the groundwater abstraction, minimizing the Gini coefficient (allocation inequity), minimizing the total energy required to pass saline water through the RO membrane to reach the standard total dissolved solids (TDS), and minimizing the average TDS concentration of water abstraction positions from 11 management zones have been considered over a 50-year management horizon. Solutions obtained in the simulation-based constrained multi-objective optimization framework allow managers to choose from 587 Pareto optimal solutions. They provide an abstraction scheme with a range of 1.44 to 4.53 MCM/yr, a Gini coefficient of 0 to 0.98, filtration energy of 988,562 to 1,935,760 kWh/yr, and an average TDS of 19,663 to 21,351 mg/L. The Pareto optimal solutions can help decision-makers decide on the multi-dimensional problems of sustainable coastal groundwater management and show patterns among different objectives.

Rheological and mechanical performance analysis and proportion optimization of cemented gangue backfill materials based on response surface methodology

Cemented backfill mining is a green mining method that enhances the coal mining rate and the safety of mined-out regions. To transport the cemented gangue backfill material (CGBM) into the mined-out regions, it is essential to ensure high flowability and adequate compressive strength after hardening. Based on the response surface methodology (RSM), 29 experiments were conducted in this paper to test the yield stress and plastic viscosity of CGBM slurry. Cubic specimens with dimensions of 100 mm were prepared and underwent uniaxial compression tests to obtain the compressive strength at a curing age of 28 days. Quadratic polynomial regression models were established for yield stress, plastic viscosity, and compressive strength to explore the effects of fly ash content, water-cement ratio, mass concentration, and superplasticizer dosage on the properties of CGBM. Multi-objective optimization was conducted to determine the optimal material proportion of CGBM. The research results indicate that (1) the mass concentration most profoundly affected the yield stress and plastic viscosity of CGBM, and it increased with an increase in mass concentration. Fly ash content had an inverse relationship with compressive strength. Superplasticizer was found to improve the flowability and strength of CGBM. (2) The established response surface model could reflect the relationship between CGBM's material proportion and rheological and mechanical properties, and predict relevant parameters. (3) Multi-objective optimization determined the optimal proportion of CGBM to be 80% fly ash content, 54% water-cement ratio, 79% mass concentration, and 3% superplasticizer dosage. The research findings offer valuable guidance to mining backfill engineering.

Optimal allocation of agricultural water and land resources integrated with virtual water trade: A perspective on spatial virtual water coordination

Agricultural production consumes the majority of global freshwater resources. The worsening water scarcity has imposed significant stress on agricultural production when regions seek food self-sufficiency. To seek optimal allocation of spatial agricultural water and land resources in each water function zone of the objective region, a multi-objective optimization model was developed to tackle the trade-offs between the water-saving objective and the economic benefit objective considering virtual water trade (VWT). The cultivated area of each crop in each water function zone was taken into account as the decision variable, while a set of strong constraints were used to restrict land resources and water availability. Then, a decomposition-simplex method aggregation algorithm (DSMA) was proposed to solve this nonlinear, bounding-constrained, and multi-objective optimization model. Based on the quantitative analysis of the spatial blue and green virtual water in each agricultural product, the proposed methodology was applied to a real-world, provincial-scale region in China (i.e., Jiangsu Province). The optimized results provided 18 Pareto solutions to reallocate the land resources in the 21 IV-level water function zones of Jiangsu Province, considering four major rainy-season crops and two dry-season crops. Compared to the actual scenario, the superior scheme increased by 7.95% (5.6 × 109 RMB) for economic trade and decreased by 1.77% (2.0 × 109 m3) for agricultural water consumption. It was mainly because the potential of spatial blue and green virtual water in Jiangsu was fully exploited by improving spatial land resource allocation. The food security of Jiangsu could be guaranteed by achieving self-sufficiency in the superior scheme, and the total VWT in the optimal scheme was 2.2 times more than the actual scenario. The results provided a systematic decision-support methodology from the perspective of spatial virtual water coordination, yet, the methodology is widely applicable.

High-security automatic path planning of radiofrequency ablation for liver tumors

BACKGROUND AND OBJECTIVE

Radiofrequency ablation (RFA) is an effective method for the treatment of liver tumors. Preoperative path planning, which plays a crucial role in RFA treatment, requires doctors to have significant experience and ability. Specifically, correct and highly active preoperative path planning should ensure the safety of the whole puncturing process, complete ablation of tumors and minimal damage to healthy tissues.

METHODS

In this paper, a high-security automatic multiple puncture path planning method for liver tumors is proposed, in which the optimization of the ablation number, puncture number, target positions and puncture point positions subject to comprehensive clinical constraints are studied. In particular, both the safety of the puncture path and the distribution of ablation ellipsoids are taken into consideration. The influence of each constraint on the safety of the whole puncturing process is discussed in detail. On this basis, the efficiency of the planning method is obviously improved by simplifying the computational data and optimized variables. In addition, the performance and adaptability of the proposed method to large and small tumors are compared and summarized.

RESULTS

The proposed method is evaluated on 10 liver tumors of various geometric characteristics from 7 cases. The test results show that the average path planning time and average ablation efficiency are 41.4 s and 60.19%, respectively. For tumors of different sizes, the planning results obtained from the proposed method have similar healthy tissue coverage. Through the clinical evaluation of doctors, the planning results meet the needs of RFA for liver tumors.

CONCLUSIONS

The proposed method can provide reasonable puncture paths in RFA planning, which is beneficial to ensure the safety and efficiency of liver tumor ablation.

Electrochemical mechanism of synchronous ammonia and nitrate removal based on multi-objective optimization by coupling random forest with genetic algorithm

In this work, an electrochemical system was constructed for the simultaneous elimination of ammonia and nitrate using the prepared Ti foam/SnO2-Sb anode and a Cu foam cathode. The hybrid RF-GA method is proposed as a tool for the analysis and optimization of the simultaneous removal of ammonia and nitrate. The influence of independent variables including NaCl concentration, time, and current densities was studied. Results showed that the random forest (RF) model could successfully predict the behavior of electrochemical systems (R2 = 0.9751, RMSE = 0.4567 for the ammonia prediction model; R2 = 0.9772, RMSE = 0.0436 for the nitrate prediction model). The variable importance measures (VIM) analysis reveals that time has the maximum influence on the degradation rate of ammonia and nitrate. The RF model is used as an objective function for the genetic algorithm (GA) to determine the optimum conditions in combination with the calculated specific energy consumption. Based on the optimization results, the removal rates of ammonia and nitrate reach 94.4 % and 74.7 %, respectively, with a minimum specific energy consumption of 0.181 kwh·g-1. The electrochemical reaction mechanism of the composite pollutants in the Ti foam/SnO2-Sb and Cu foam electrode system is further elucidated. The results indicate that nitrate is reduced to nitrite, ammonia, or nitrogen gas at the cathode, accompanied by the mutual transformation of Cu(0), Cu(I), and Cu(II) on the Cu electrode. Ammonia is oxidized to nitrogen gas or nitrate at the anode. Ultimately, the nitrogen-containing composite pollutant is decomposed and discharged as nitrogen gas by cyclic redox reactions.

Optimizing classroom modularity and combinations to enhance daylighting performance and outdoor platform through ANN acceleration in the post-epidemic era

The global COVID-19 pandemic has increased attention to the relationship between the built environment and health, particularly in educational settings where students spend a significant amount of their time. Traditional side daylighting used in schools, while cost-effective and easy to construct, can result in uneven indoor daylighting. To address this issue, this paper proposes a terraced teaching building design model for primary and secondary schools in Guangzhou based on the design experience of an "open-air school movement" during a historical respiratory epidemic in the early 20th century. The proposed design relies on skylight for lighting, and each classroom has an outdoor platform. An optimization algorithm based on Spatial Daylight Autonomy (sDA), Uniformity of Daylighting (UOD), Annual Sunlight Exposure (ASE), Outdoor Platform Area (OPA), Gable Wall Length (GWL), and Space Utilization (SU) is used to obtain the optimal concrete form of the building. To speed up the simulation process, a set of Artificial Neural Network (ANN) based rapid prediction network models for complex forms is proposed. This group prediction method improves the simulation speed by 357 times and grossly speed up the optimization process based on six indexes in the early design stage, resulting in four terraced teaching buildings that meet the above criteria. Overall, the proposed design provides a novel architectural form that ensures overall visual comfort while promoting students' learning and physical health.

Identifying robust adaptive irrigation operating policies to balance deeply uncertain economic food production and groundwater sustainability trade-offs

Increasing irrigation demand has heavily relied on groundwater use, especially in places with highly variable water supplies that are vulnerable to drought. Groundwater management in agriculture is becoming increasingly challenging given the growing effects from overdraft and groundwater depletion worldwide. However, multiple challenges emerge when seeking to develop sustainable groundwater management in irrigated systems, such as trade-offs between the economic revenues from food production and groundwater resources, as well as the broad array of uncertainties in food-water systems. In this study we explore the applicability of Evolutionary Multi-Objective Direct Policy Search (EMODPS) to identify adaptive irrigation policies that water agencies and farmers can implement including operational decisions related to land use and groundwater use controls as well as groundwater pumping fees. The EMODPS framework yields state-aware, adaptive policies that respond dynamically as system state conditions change, for example with variable surface water (e.g., shifting management strategies across wet versus dry years). For this study, we focus on the Semitropic Water Storage district located in the San Joaquin Valley, California to provide broader insights relevant to ongoing efforts to improve groundwater sustainability in the state. Our findings demonstrate that adaptive irrigation policies can achieve sufficiently flexible groundwater management to acceptably balance revenue and sustainability goals across a wide range of uncertain future scenarios. Among the evaluated policy decisions, pumping restrictions and reductions in inflexible irrigation demands from tree crops are actions that can support dry-year pumping while maximizing groundwater storage recovery during wet years. Policies suggest that an adaptive pumping fee is the most flexible decision to control groundwater pumping and land use.

MAGNETO: Cell type marker panel generator from single-cell transcriptomic data

Single-cell RNA sequencing experiments produce data useful to identify different cell types, including uncharacterized and rare ones. This enables us to study the specific functional roles of these cells in different microenvironments and contexts. After identifying a (novel) cell type of interest, it is essential to build succinct marker panels, composed of a few genes referring to cell surface proteins and clusters of differentiation molecules, able to discriminate the desired cells from the other cell populations. In this work, we propose a fully-automatic framework called MAGNETO, which can help construct optimal marker panels starting from a single-cell gene expression matrix and a cell type identity for each cell. MAGNETO builds effective marker panels solving a tailored bi-objective optimization problem, where the first objective regards the identification of the genes able to isolate a specific cell type, while the second conflicting objective concerns the minimization of the total number of genes included in the panel. Our results on three public datasets show that MAGNETO can identify marker panels that identify the cell populations of interest better than state-of-the-art approaches. Finally, by fine-tuning MAGNETO, our results demonstrate that it is possible to obtain marker panels with different specificity levels.

Exploring a multi-objective optimization operation model of water projects for boosting synergies and water quality improvement in big river systems

Due to excessive nutrient enrichment and rapidly increasing water demand, the occurrence of riverine environment deterioration events such as algal blooms in rivers of China has become more frequent and severe since the 1990s, which has imposed harmful consequences on riverine ecosystems. However, tackling river algal blooms as an important issue of restoring riverine environment is very challenging because the complex interaction mechanisms between the causes are impacted by multiple factors. The contributions of our study consist of: (1) optimizing joint operation of water projects for boosting synergies of water quality and quantity, and hydroelectricity; and (2) preventing algal bloom from perspectives of hydrological and water-quality conditions by regulating water releases of water projects. This study proposed a multi-objective optimization methodology grounded on the Non-dominated Sorting Genetic Algorithm to simultaneously minimize the excess values of algal bloom indicators (water quality, O1), minimize the used reservoir capacity for water supply (water quantity, O2), and maximize the hydropower generation (hydroelectricity, O3). The proposed methodology was applied to several catastrophic algal bloom events that took place between 2017 and 2021 and thirteen water projects in the Hanjiang River of China. The results indicated that the proposed methodology largely stimulated the synergistic benefits of the three objectives by reaching a 36.7% reduction in total nitrogen and phosphorus concentrations, a 33.1% improvement in the remaining reservoir capacity, and a 41.0% improvement in hydropower output, as compared with those of the standard operation policy (SOP). In addition, the optimal water release schemes of water projects would increase the minimum streamflow velocity of downstream algal bloom control stations by 8.6%-9.4%. This study provides a new perspective on water project operation in the environmental improvement in big river systems while boosting multi-objectives synergies to support environmentalists and decision-makers with scientific guidance on sustainable water resources management.

Multi-objective Allocation Optimization of Soil Conservation Measures Under Data Uncertainty

Many regions worldwide face soil loss rates that endanger future food supply. Constructing soil and water conservation measures reduces soil loss but comes with high labor costs. Multi-objective optimization allows considering both soil loss rates and labor costs, however, required spatial data contain uncertainties. Spatial data uncertainty has not been considered for allocating soil and water conservation measures. We propose a multi-objective genetic algorithm with stochastic objective functions considering uncertain soil and precipitation variables to overcome this gap. We conducted the study in three rural areas in Ethiopia. Uncertain precipitation and soil properties propagate to uncertain soil loss rates with values that range up to 14%. Uncertain soil properties complicate the classification into stable or unstable soil, which affects estimating labor requirements. The obtained labor requirement estimates range up to 15 labor days per hectare. Upon further analysis of common patterns in optimal solutions, we conclude that the results can help determine optimal final and intermediate construction stages and that the modeling and the consideration of spatial data uncertainty play a crucial role in identifying optimal solutions.

Techno-economic optimization and Nox emission reduction through steam injection in gas turbine combustion chamber for waste heat recovery and water production

Considering the persistent human need for electricity and fresh water, cogeneration systems based on the production of these two products have attracted the attention of researchers. This study investigates a cogeneration system of electricity and fresh water based on gas turbine (GT) as the prime mover. The wasted energy of the GT exhaust gases is absorbed by a heat recovery steam generator (HRSG) and supplies the superheat steam required by the steam turbine (ST). In order to produce fresh water, a multi-effect desalination (MED) system is applied. The motive steam required is provided by extracting steam from the ST. In order to reduce the environmental pollution of this cogeneration system, the steam injection method is proposed in the GT's combustion chamber (CC). This system is optimized by a multi-objective optimization tool based on the Genetic Algorithm (GA). The design variables include pressure ratio of compressor (CPR), inlet temperature of gas turbine (TIT), steam injection mass flow rate in the CC, HRSG operating pressure, HRSG evaporator pinch point temperature difference (PPTD), steam pressure of the MED ejector, ejector motive steam flow rate, number of MED effects, and return effect. The goals are to minimize the total cost rate (TCR), which includes the cost of initial investment and maintenance of the system, the cost of consumed fuel, and the cost of disposing of CO and NO pollutants, as well as maximizing the exergy efficiency. In the end, it is observed that the steam injection in the CC leads to the reduction of the mentioned pollutant index, and it is proposed as a suitable solution to reduce the pollution of the proposed cogeneration system.

Applicability of photovoltaic panel rainwater harvesting system in improving water-energy-food nexus performance in semi-arid areas

Growing food demand challenges the expansion of agriculture, while water and energy shortages have seriously jeopardized agricultural sustainability. Therefore, the water-energy-food (WEF) nexus must be integrated into sustainable agriculture management. However, despite the increasing sophistication of models for WEF optimization, more studies have considered only how to reduce resource consumption and less on how to increase resource supply. This paper outlines an agricultural WEF optimization model based on photovoltaic panel rainwater harvesting (PVRH). The model innovatively incorporates the PVRH system into the agricultural WEF nexus, providing a decision-making framework that exploits and conserves resources in parallel, while contributing to economic benefits. The model was applied in a rural case study in a semi-arid region of China. The results highlight the significant potential of the PVRH system to exploit water and energy, and the increased resources are allocated to irrigated alfalfa and vegetables, which would significantly increase revenue. However, the model does not recommend large-scale vegetable cultivation, which would increase water and energy consumption and reduce the WEF indicator values indicating agricultural sustainability. The final scheme will build a 98.92MWp PV power station, develop 1.31 × 108 kW·h of electricity and 1.97 × 107 m3 of rainwater into agricultural production. And through cropping restructuring, it will increase 23.61 % of economic revenue and save 57.74 % of water and 3.24 % of energy. In general, the model framework is transferable and applicable to similar agricultural areas under semi-arid climatic conditions.

Multi-objective test selection of smart contract and blockchain applications

The ability to create decentralized applications without the authority of a single entity has attracted numerous developers to build applications using blockchain technology. However, ensuring the correctness of such applications poses significant challenges, as it can result in financial losses or, even worse, a loss of user trust. Testing smart contracts introduces a unique set of challenges due to the additional restrictions and costs imposed by blockchain platforms during test case execution. Therefore, it remains uncertain whether testing techniques developed for traditional software can effectively be adapted to smart contracts. In this study, we propose a multi-objective test selection technique for smart contracts that aims to balance three objectives: time, coverage, and gas usage. We evaluated our approach using a comprehensive selection of real-world smart contracts and compared the results with various test selection methods employed in traditional software systems. Statistical analysis of our experiments, which utilized benchmark Solidity smart contract case studies, demonstrates that our approach significantly reduces the testing cost while still maintaining acceptable fault detection capabilities. This is in comparison to random search, mono-objective search, and the traditional re-testing method that does not employ heuristic search.

Multi-objective optimization via evolutionary algorithm (MOVEA) for high-definition transcranial electrical stimulation of the human brain

Designing a transcranial electrical stimulation (tES) strategy requires considering multiple objectives, such as intensity in the target area, focality, stimulation depth, and avoidance zone. These objectives are often mutually exclusive. In this paper, we propose a general framework, called multi-objective optimization via evolutionary algorithm (MOVEA), which solves the non-convex optimization problem in designing tES strategies without a predefined direction. MOVEA enables simultaneous optimization of multiple targets through Pareto optimization, generating a Pareto front after a single run without manual weight adjustment and allowing easy expansion to more targets. This Pareto front consists of optimal solutions that meet various requirements while respecting trade-off relationships between conflicting objectives such as intensity and focality. MOVEA is versatile and suitable for both transcranial alternating current stimulation (tACS) and transcranial temporal interference stimulation (tTIS) based on high definition (HD) and two-pair systems. We comprehensively compared tACS and tTIS in terms of intensity, focality, and steerability for targets at different depths. Our findings reveal that tTIS enhances focality by reducing activated volume outside the target by 60%. HD-tTIS and HD-tDCS can achieve equivalent maximum intensities, surpassing those of two-pair tTIS, such as 0.51 V/m under HD-tACS/HD-tTIS and 0.42 V/m under two-pair tTIS for the motor area as a target. Analysis of variance in eight subjects highlights individual differences in both optimal stimulation policies and outcomes for tACS and tTIS, emphasizing the need for personalized stimulation protocols. These findings provide guidance for designing appropriate stimulation strategies for tACS and tTIS. MOVEA facilitates the optimization of tES based on specific objectives and constraints, advancing tTIS and tACS-based neuromodulation in understanding the causal relationship between brain regions and cognitive functions and treating diseases. The code for MOVEA is available at https://github.com/ncclabsustech/MOVEA.

AB-Gen: Antibody Library Design with Generative Pre-trained Transformer and Deep Reinforcement Learning

Antibody leads must fulfill multiple desirable properties to be clinical candidates. Primarily due to the low throughput in the experimental procedure, the need for such multi-property optimization causes the bottleneck in preclinical antibody discovery and development, because addressing one issue usually causes another. We developed a reinforcement learning (RL) method, named AB-Gen, for antibody library design using a generative pre-trained transformer (GPT) as the policy network of the RL agent. We showed that this model can learn the antibody space of heavy chain complementarity determining region 3 (CDRH3) and generate sequences with similar property distributions. Besides, when using human epidermal growth factor receptor-2 (HER2) as the target, the agent model of AB-Gen was able to generate novel CDRH3 sequences that fulfill multi-property constraints. Totally, 509 generated sequences were able to pass all property filters, and three highly conserved residues were identified. The importance of these residues was further demonstrated by molecular dynamics simulations, consolidating that the agent model was capable of grasping important information in this complex optimization task. Overall, the AB-Gen method is able to design novel antibody sequences with an improved success rate than the traditional propose-then-filter approach. It has the potential to be used in practical antibody design, thus empowering the antibody discovery and development process. The source code of AB-Gen is freely available at Zenodo (https://doi.org/10.5281/zenodo.7657016) and BioCode (https://ngdc.cncb.ac.cn/biocode/tools/BT007341).