Identifying the maturity of co-compost of olive mill waste and natural mineral materials: Modelling via ANN and multi-objective optimization

Simulation and optimization of cheese whey additive for value-added compost production: Hyperparameter tuning approach and genetic algorithm

Cheese whey is a difficult and costly wastewater to treat due to its high organic matter and mineral content. Although many management strategies are conducted for whey removal, its use in composting is limited. In this study, the effect of cheese whey in the composting of sewage sludge and poultry waste on compost quality and process efficiency was investigated. Also, valid and consistent simulations were developed with Gaussian Process Regression (GPR), Support Vector Regression (SVR), and Neural Network Regression (NNR) Machine Learning (ML) algorithms. The results of all physicochemical parameters determined that 3% of cheese whey addition for both feedstocks improved the composting process's efficiency and the final product's quality. The best results obtained through hyperparameter tuning showed that Gaussian Process Regression (GPR) was the most effective modeling tool providing realistic simulations. The reliability of these simulations was verified by running the GPR process 50 times. MdAPE demonstrated the validity and consistency of the created process simulations. Moreover, a genetic algorithm was used to optimize these dependent simulations and achieved almost 100% desirability. Optimization studies showed that the effective cheese whey ratios were 3.2724% and 3.1543% for sewage sludge and poultry waste, respectively. Optimization results were compatible with the results of experimental studies. This study provides a new strategy for the recovery of cheese whey as well as a new perspective on the effect of cheese whey on both physicochemical parameters and composting phases and the modeling and optimization processes of the results.

Response surface methodology for process optimization in livestock wastewater treatment: A review

With increasing demand for meat and dairy products, the volume of wastewater generated from the livestock industry has become a significant environmental concern. The treatment of livestock wastewater (LWW) is a challenging process that involves removing nutrients, organic matter, pathogens, and other pollutants from livestock manure and urine. In response to this challenge, researchers have developed and investigated different biological, physical, and chemical treatment technologies that perform better upon optimization. Optimization of LWW handling processes can help improve the efficacy and sustainability of treatment systems as well as minimize environmental impacts and associated costs. Response surface methodology (RSM) as an optimization approach can effectively optimize operational parameters that affect process performance. This review article summarizes the main steps of RSM, recent applications of RSM in LWW treatment, highlights the advantages and limitations of this technique, and provides recommendations for future research and practice, including its cost-effectiveness, accuracy, and ability to improve treatment efficiency.

Application of Multivariate Regression and Artificial Neural Network Modelling for Prediction of Physicochemical Properties of Grape-Skin Compost

The reusability of by-products in the food industry is consistent with sustainable and greener production; therefore, the aim of this paper was to evaluate the applicability of multiple linear regression (MLR), piecewise linear regression (PLR) and artificial neural network models (ANN) to the prediction of grape-skin compost's physicochemical properties (moisture, dry matter, organic matter, ash content, carbon content, nitrogen content, C/N ratio, total colour change of compost samples, pH, conductivity, total dissolved solids and total colour change of compost extract samples) during in-vessel composting based on the initial composting conditions (air-flow rate, moisture content and day of sampling). Based on the coefficient of determination for prediction, the adjusted coefficient of determination for calibration, the root-mean-square error of prediction (RMSEP), the standard error of prediction (SEP), the ratio of prediction to deviation (RPD) and the ratio of the error range (RER), it can be concluded that all developed MLR and PLR models are acceptable for process screening. Furthermore, the ANN model developed for predicting moisture and dry-matter content can be used for quality control (RER >11). The obtained results show the great potential of multivariate modelling for analysis of the physicochemical properties of compost during composting, confirming the high applicability of modelling in greener production processes.

Composting municipal solid waste and animal manure in response to the current fertilizer crisis - a recent review

The dynamic price increases of fertilizers and the generation of organic waste are currently global issues. The growth of the population has led to increased production of solid municipal waste and a higher demand for food. Food production is inherently related to agriculture and, to achieve higher yields, it is necessary to replenish the soil with essential minerals. A synergistic approach that addresses both problems is the implementation of the composting process, which aligns with the principles of a circular economy. Food waste, green waste, paper waste, cardboard waste, and animal manure are promising feedstock materials for the extraction of valuable compounds. This review discusses key factors that influence the composting process and compares them with the input materials' parameters. It also considers methods for optimizing the process, such as the use of biochar and inoculation, which result in the production of the final product in a significantly shorter time and at lower financial costs. The applications of composts produced from various materials are described along with associated risks. In addition, innovative composting technologies are presented.

Modeling and optimization study on degradation of organic contaminants using nZVI activated persulfate based on response surface methodology and artificial neural network: a case study of benzene as the model pollutant

Due to the complicated transport and reactive behavior of organic contamination in groundwater, the development of mathematical models to aid field remediation planning and implementation attracts increasing attentions. In this study, the approach coupling response surface methodology (RSM), artificial neural networks (ANN), and kinetic models was implemented to model the degradation effects of nano-zero-valent iron (nZVI) activated persulfate (PS) systems on benzene, a common organic pollutant in groundwater. The proposed model was applied to optimize the process parameters in order to help predict the effects of multiple factors on benzene degradation rate. Meanwhile, the chemical oxidation kinetics was developed based on batch experiments under the optimized reaction conditions to predict the temporal degradation of benzene. The results indicated that benzene (0.25 mmol) would be theoretically completely oxidized in 1.45 mM PS with the PS/nZVI molar ratio of 4:1 at pH 3.9°C and 21.9 C. The RSM model predicted well the effects of the four factors on benzene degradation rate (R2 = 0.948), and the ANN with a hidden layer structure of [8-8] performed better compared to the RSM (R2 = 0.980). In addition, the involved benzene degradation systems fit well with the Type-2 and Type-3 pseudo-second order (PSO) kinetic models with R2 > 0.999. It suggested that the proposed statistical and kinetic-based modeling approach is promising support for predicting the chemical oxidation performance of organic contaminants in groundwater under the influence of multiple factors.

Optimization of olive oil extraction wastes co composting procedure based on bioprocessing parameters

Organic waste generation has increased massively around the world during the last decades, especially the waste produced by the olive-growing industry. In order to manage the waste accumulation, composting process is an appropriate biotechnological solution which allows the waste organic matter biotransformation into a useful product the "compost", used as an amendment for agricultural soils. The classical composting process presents several disadvantages; the major difficulty is to find the best feedstocks proportion to be used, leading to a final C/N ratio ranged between 12 and 15, a neutral pH, a humidity between 40% and 60% and organic matter (OM) content of 20-60%, at ambient temperature. Consequently, an accurate optimization of the composting process is needed for predicting the process parameters progress. To optimize these parameters and the waste rates initially mixed, the multiple regression method was used to determine the compost final parameters values, referring to the initial mixture of the different waste types. The best model filling the required standardized values included 49% of olive mill wastewater, 19.5% of exhausted olive mill cake, 15.5% of poultry manure, and 16% of green waste. This combination provides a pH of 7.5, a C/N ratio of 12.5 and an OM content of 44%. Such modelization would enshorten the composting required time.

Role of different natural materials in reducing nitrogen loss during industrial sludge composting: Modelling and optimization

In this study, the effects of pumice, expanded perlite, and expanded vermiculite on nitrogen loss were examined for industrial sludge composting using the Box-Behnken experimental design. The independent factors and their levels were selected as amendment type, amendment ratio, and aeration rate, and codded as x₁, x₂, and x₃ at 3 levels (low, center, and high). The statistical significance of independent variables and their interactions were determined at 95% confidence limits by Analysis of Variance. The quadratic polynomial regression equation produced to predict the responses was solved and the optimum values of the variables were predicted by analyzing the three-dimensional response surfaces plots. The optimum conditions for minimum nitrogen loss by the regression model were as pumice of amendment type, 40% of amendment ratio, and 6 L/min of aeration rate. In this study, it was observed that time-consuming and laborious laboratory work can be minimized with the Box-Behnken experimental design.

Evaluation of the influence of rice husk amendment on compost quality in the composting of sewage sludge

This study aimed to evaluate the influence of rice husk addition on compost quality and maturity in sewage sludge composting using a pilot scale aerated in-vessel reactor. During the composting process, changes in compost quality and physicochemical factors including pH, temperature, moisture content, electrical conductivity, total organic carbon (TOC), total nitrogen (TN), and carbon to nitrogen ratio (C/N) were monitored. In the pile containing 25% rice husk, the lowest losses occurred with 52.49% for TOC and 23.24% for TN, while C/N ratio in the final compost was 18.82, achieving mature and quality compost. The moisture contents of the final composts were found as 50.72% in the control group while it was 31.73% and 28.18% in the reactors containing 10% and 25% rice husk, respectively. These results suggested that rice husk addition was beneficial for reducing moisture content and balancing the C/N ratio in sewage sludge composting.

Artificial intelligence and machine learning approaches in composting process: A review

Studies on developing strategies to predict the stability and performance of the composting process have increased in recent years. Machine learning (ML) has focused on process optimization, prediction of missing data, detection of non-conformities, and managing complex variables. This review investigates the perspectives and challenges of ML and its important algorithms such as Artificial Neural Networks (ANNs), Random Forest (RF), Adaptive-network-based fuzzy inference systems (ANFIS), Support Vector Machines (SVMs), and Deep Neural Networks (DNNs) used in the composting process. In addition, the individual shortcomings and inadequacies of the metrics, which were used as error or performance criteria in the studies, were emphasized. Except for a few studies, it was concluded that Artificial Intelligence (AI) algorithms such as Genetic algorithm (GA), Differential Evaluation Algorithm (DEA), and Particle Swarm Optimization (PSO) were not used in the optimization of the model parameters, but in the optimization of the parameters of the ML algorithms.

Modelling and optimization of sewage sludge composting using biomass ash via deep neural network and genetic algorithm

In this study, the use of Deep Cascade Forward Neural Network (DCFNN) was investigated to model both linear and non-linear chaotic relationships in co-composting of dewatered sewage sludge and biomass fly ash (BFA). Model results were evaluated in comparison with RSM, Feed Forward Neural Network (FFNN) and Feed Back Neural Network (FBNN), and Cascade Forward Neural Network (CFNN). DCFNN produced predictive results with MAPE values less than 1% for all datasets in all experimental designs except one with 1.99%. Furthermore, the decision variables were optimized by Genetic Algorithm (GA). The desirability level obtained from the optimization results was found to be 100% in a few designs and above 95% in all other designs. The results showed that DCFNN is a reliable and consistent tool for modeling composting process parameters, also GA is a satisfactory tool for determining which outputs the input parameters will produce in an experimental setup.

Machine learning framework for intelligent prediction of compost maturity towards automation of food waste composting system

Reactive composting is a promising technology for recovering valuable resources from food waste, while its manual regulation is laborious and time-consuming. In this study, machine learning (ML) technologies are adopted to enable automated composting by predicting compost maturity and providing process regulation. Four machine learning algorithms, namely random forest (RF), extreme gradient boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and Multilayer Perceptron (MLP) are employed to predict the seed germination index (GI) and C/N ratio. Based on the best fusion model with the highest R² of 0.977 and 0.986 for the multi-task prediction of GI and C/N ratio, the critical factors and their interactions with maturity are identified. Moreover, the ML model is validated on a composting reactor and the ML-based prediction application can provide regulation to ensure food waste decompose within the required time. In conclusion, this compost maturity prediction system automates the reactive composting, thus reducing labor costs.

Modeling and optimization of process parameters in co-composting of tea waste and food waste: Radial basis function neural networks and genetic algorithm

In this study, the effects of co-composting of food waste (FW) and tea waste (TW) on the losses of total nitrogen (TN), total organic carbon (TOC), and moisture content (MC) were investigated. TW and FW were composted separately and compared with the co-composting of FW and TW at different ratios. While the MC losses were close to each other in all processes, the lowest TN and TOC losses were found in the composting process containing 25% TW as 26.80% and 40.11%, respectively. Moreover, Radial Basis Function Neural Networks (RBFNNs) were used to predict the losses of TN, TOC, and MC. The outputs of RBFNN were compared with Response Surface Methodology (RSM), Support Vector Regression (SVR), and Feed Forward Neural Network (FF-NN). In addition, the optimal parameter values were determined by Genetic algorithm (GA). As a result, it will be possible to simulate and improve different co-composting processes with obtained data.

Variation in community structure and network characteristics of spent mushroom substrate (SMS) compost microbiota driven by time and environmental conditions

Global mushroom production is growing rapidly, raising concerns about polluting effects of spent mushroom substrate (SMS) and interest in uses in composts. In this study, SMS composting trials and high-throughput sequencing were carried out to investigate to better understand how the structure, co-occurrence patterns, and functioning of bacterial and fungal communities vary through compost time and across environmental conditions. The results suggested that both bacterial and fungal microbiota displayed significant variation in community composition across different composting stages. Enzyme activity levels showed both directional and fluctuating changes during composting, and the activity dynamics of carboxymethyl cellulase, polyphenol oxidase, laccase, and catalase correlated significantly with the succession of microbial community composition. The co-occurrence networks are "small-world" and modularized and the topological properties of each subnetwork were significantly influenced by the environmental factors. Finally, seed germination and seedling experiments were performed to verify the biosafety and effectiveness of the final composting products.

A Review of Performance Prediction Based on Machine Learning in Materials Science

With increasing demand in many areas, materials are constantly evolving. However, they still have numerous practical constraints. The rational design and discovery of new materials can create a huge technological and social impact. However, such rational design and discovery require a holistic, multi-stage design process, including the design of the material composition, material structure, material properties as well as process design and engineering. Such a complex exploration using traditional scientific methods is not only blind but also a huge waste of time and resources. Machine learning (ML), which is used across data to find correlations in material properties and understand the chemical properties of materials, is being considered a new way to explore the materials field. This paper reviews some of the major recent advances and applications of ML in the field of properties prediction of materials and discusses the key challenges and opportunities in this cross-cutting area.

Application of Optimization and Modeling for the Enhancement of Composting Processes

Composting is a more environmentally friendly and cost-effective alternative to digesting organic waste and turning it into organic fertilizer. It is a biological process in which polymeric waste materials contained in organic waste are biodegraded by fungi and bacteria. Temperature, pH, moisture content, C/N ratio, particle size, nutrient content and oxygen supply all have an impact on the efficiency of the composting process. To achieve optimal composting efficiency, all of these variables and their interactions must be considered. To this end, statistical optimization techniques and mathematical modeling approaches have been developed over the years. In this paper, an overview of optimization and mathematical modeling approaches in the field of composting processes is presented. The advantages and limitations of optimization and mathematical modeling for improving composting processes are also addressed.