Machine learning prediction of biocrude yields and higher heating values from hydrothermal liquefaction of wet biomass and wastes

Enhancing biomass conversion to bioenergy with machine learning: Gains and problems

The growing concerns about environmental sustainability and energy security, such as exhaustion of traditional fossil fuels and global carbon footprint growth have led to an increasing interest in alternative energy sources, especially bioenergy. Recently, numerous scenarios have been proposed regarding the use of bioenergy from different sources in the future energy systems. In this regard, one of the biggest challenges for scientists is managing, modeling, decision-making, and future forecasting of bioenergy systems. The development of machine learning (ML) techniques can provide new opportunities for modeling, optimizing and managing the production, consumption and environmental effects of bioenergy. However, researchers in bioenergy fields have not widely utilized the ML concepts and practices. Therefore, a comparative review of the current ML techniques used for bioenergy productions is presented in this paper. This review summarizes the common issues and difficulties existing in integrating ML with bioenergy studies, and discusses and proposes the possible solutions. Additionally, a detailed discussion of the appropriate ML application scenarios is also conducted in every sector of the entire bioenergy chain. This indicates the modernized conversion processes supported by ML techniques are imperative to accurately capture process-level subtleties, and thus improving techno-economic resilience and socio-ecological integrity of bioenergy production. All the efforts are believed to help in sustainable bioenergy production with ML technologies for the future.

Prediction of Individual Gas Yields of Supercritical Water Gasification of Lignocellulosic Biomass by Machine Learning Models

Supercritical water gasification (SCWG) of lignocellulosic biomass is a promising pathway for the production of hydrogen. However, SCWG is a complex thermochemical process, the modeling of which is challenging via conventional methodologies. Therefore, eight machine learning models (linear regression (LR), Gaussian process regression (GPR), artificial neural network (ANN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGB), and categorical boosting regressor (CatBoost)) with particle swarm optimization (PSO) and a genetic algorithm (GA) optimizer were developed and evaluated for prediction of H2, CO, CO2, and CH4 gas yields from SCWG of lignocellulosic biomass. A total of 12 input features of SCWG process conditions (temperature, time, concentration, pressure) and biomass properties (C, H, N, S, VM, moisture, ash, real feed) were utilized for the prediction of gas yields using 166 data points. Among machine learning models, boosting ensemble tree models such as XGB and CatBoost demonstrated the highest power for the prediction of gas yields. PSO-optimized XGB was the best performing model for H2 yield with a test R2 of 0.84 and PSO-optimized CatBoost was best for prediction of yields of CH4, CO, and CO2, with test R2 values of 0.83, 0.94, and 0.92, respectively. The effectiveness of the PSO optimizer in improving the prediction ability of the unoptimized machine learning model was higher compared to the GA optimizer for all gas yields. Feature analysis using Shapley additive explanation (SHAP) based on best performing models showed that (21.93%) temperature, (24.85%) C, (16.93%) ash, and (29.73%) C were the most dominant features for the prediction of H2, CH4, CO, and CO2 gas yields, respectively. Even though temperature was the most dominant feature, the cumulative feature importance of biomass characteristics variables (C, H, N, S, VM, moisture, ash, real feed) as a group was higher than that of the SCWG process condition variables (temperature, time, concentration, pressure) for the prediction of all gas yields. SHAP two-way analysis confirmed the strong interactive behavior of input features on the prediction of gas yields.

Microalgal biorefineries: Advancement in machine learning tools for sustainable biofuel production and value-added products recovery

The microalgae can be converted into biofuels, biochemicals, and bioactive compounds in a biorefinery. Recently, designing and executing more viable and sustainable biofuel production from microalgal biomass is one of the vital challenges in the development of biorefinery. Scalable cultivation of microalgae is mandatory for commercializing and industrializing the biorefinery. The intrinsic complication in cultivation of microalgae is the physiological and operational factors that renders challenging impact to enable a smooth and profitable operation. However, this aim can only be successful via a simulation prospect. Machine learning tools provides advanced approaches for evaluating, predicting, and controlling uncertainties in microalgal biorefinery for sustainable biofuel production. The present review provides a critical evaluation of the most progressing machine learning tools that validate a potential to be employed in microalgal biorefinery. These tools are highly potential for their extensive evaluation on microalgal screening and classification. However, the application of these tools for optimization of microalgal biomass cultivation in industries in order to increase the biomass production, is still in its initial stages. Integrated hybrid machine learning tools can aid the industries to function efficiently with least resources. Some of the challenges, and perspectives of machine learning tools are discussed. Besides, future prospects are also emphasized. Though, most of the research reports on machine learning tools are not appropriate to gather generalized information, standard protocols and strategies must be developed to design generalized machine learning tools. On a whole, this review offers a perspective information about digitalized microalgal exploitation in a microalgal biorefinery.

Data-driven intelligent modeling, optimization, and global sensitivity analysis of a xanthan gum biosynthesis process

In this study, the focus was to produce xanthan gum from pineapple waste using Xanthomonas campestris. Six machine learning models were employed to optimize fermentation time and key metabolic stimulants (KH2PO4 and NH4NO3). The production of xanthan gum was optimized using two evolutionary optimization algorithms, particle swarm optimization, and genetic algorithm while the importance of input features was ranked using global sensitivity analysis. KH2PO4 was the most important input and was found to be beneficial for xanthan gum production, while a limited amount of nitrogen was needed. The extreme learning machine model was the most adequate for modeling xanthan gum production, predicting a maximum xanthan yield of 10.34 g/l (an 11.9 % increase over the control) at a fermentation time of 3 days, KH2PO4 of 15 g/l, and NH4NO3 of 2 g/l. This study has provided important insights into the intelligent modeling of a biostimulated process for valorizing pineapple waste.

Role of modeling and artificial intelligence in process parameter optimization of biochar: A review

Enhancement of crop yield, conservation and quality upgradation of soil, and efficient water management are the main objectives of sustainable agriculture and mitigating climate change's impact on agriculture. In recent days, biochar, obtained via thermochemical alteration of biomass is becoming a powerful agent for soil and water quality improvement, carbon sequestration, greenhouse gas emission reduction, and heavy metal adsorption. The present study predominantly focuses on various process parameters related to biochar preparation through pyrolysis, their impact on biochar production as well as physicochemical characteristics, and the optimization of such process parameters. Different designs of the experiment (DOE) and optimization techniques including traditional and non-traditional optimizations are discussed in the current review, along with their applicability and shortcomings. Since the biochar preparation process is tedious and energy-consuming, the present review will help to understand the importance of optimization in preparing biochar, thereby leading to a better way to prepare biochar.

Prediction of Higher Heating Values in Bio-Oil from Solvothermal Biomass Conversion and Bio-Oil Upgrading Given Discontinuous Experimental Conditions

Both the conversion of lignocellulosic biomass to bio-oil (BO) and the upgrading of BO have been the targets of many studies. Due to the large diversity and discontinuity seen in terms of reaction conditions, catalysts, solvents, and feedstock properties that have been used, a comparison across different publications is difficult. In this study, machine learning modeling is used for the prediction of final higher heating value (HHV) and ΔHHV for the conversion of lignocellulosic feedstocks to BO, and BO upgrading. The models achieved coefficient of determination (R2) scores ranging from 0.77 to 0.86, and the SHapley Additive exPlanations (SHAP) values were used to obtain model explainability, revealing that only a few experimental parameters are largely responsible for the outcome of the experiments. In particular, process temperature and reaction time were overwhelmingly responsible for the majority of the predictions, for both final HHV and ΔHHV. Elemental composition of the starting feedstock or BO dictated the upper possible HHV value obtained after the experiment, which is in line with what is known from previous methodologies for calculating HHV for fuels. Solvent used, initial moisture concentration in BO, and catalyst active phase showed low predicting power, within the context of the data set used. The results of this study highlight experimental conditions and variables that could be candidates for the creation of minimum reporting guidelines for future studies in such a way that machine learning can be fully harnessed.

A Critical Review of Data Science Applications in Resource Recovery and Carbon Capture from Organic Waste

Municipal and agricultural organic waste can be treated to recover energy, nutrients, and carbon through resource recovery and carbon capture (RRCC) technologies such as anaerobic digestion, struvite precipitation, and pyrolysis. Data science could benefit such technologies by improving their efficiency through data-driven process modeling along with reducing environmental and economic burdens via life cycle assessment (LCA) and techno-economic analysis (TEA), respectively. We critically reviewed 616 peer-reviewed articles on the use of data science in RRCC published during 2002-2022. Although applications of machine learning (ML) methods have drastically increased over time for modeling RRCC technologies, the reviewed studies exhibited significant knowledge gaps at various model development stages. In terms of sustainability, an increasing number of studies included LCA with TEA to quantify both environmental and economic impacts of RRCC. Integration of ML methods with LCA and TEA has the potential to cost-effectively investigate the trade-off between efficiency and sustainability of RRCC, although the literature lacked such integration of techniques. Therefore, we propose an integrated data science framework to inform efficient and sustainable RRCC from organic waste based on the review. Overall, the findings from this review can inform practitioners about the effective utilization of various data science methods for real-world implementation of RRCC technologies.

Machine Learning Model Insights into Base-Catalyzed Hydrothermal Lignin Depolymerization

Lignin, an abundant component of plant matter, can be depolymerized into renewable aromatic chemicals and biofuels but remains underutilized. Homogeneously catalyzed depolymerization in water has gained attention due to its economic feasibility and performance but suffers from inconsistently reported yields of bio-oil and solid residues. In this study, machine learning methods were used to develop predictive models for bio-oil and solid residue yields by using a few reaction variables and were subsequently validated by doing experimental work and comparing the predictions to the results. The models achieved a coefficient of determination (R2) score of 0.83 and 0.76, respectively, for bio-oil yield and solid residue. Variable importance for each model was calculated by two different methodologies and was tied to existing studies to explain the model predictive behavior. Based on the outcome of the study, the creation of concrete guidelines for reporting in lignin depolymerization studies was recommended. Shapley additive explanation value analysis reveals that temperature and reaction time are generally the strongest predictors of experimental outcomes compared to the rest.

Application of heavy metal immobilization in soil by biochar using machine learning

Biochar application is a promising strategy for the immobilization of heavy metal (HM)-contaminated soil, while it is always time-consuming and labor-intensive to clarify key influenced factors of soil HM immobilization by biochar. In this study, four machine learning algorithms, namely random forest (RF), support vector machine (SVR), Gradient boosting decision trees (GBDT), and Linear regression (LR) are employed to predict the HMimmobilization ratio. The RF was the best-performance ML model (Training R2 = 0.90, Testing R2 = 0.85, RMSE = 4.4, MAE = 2.18). The experiment verification based on the optimal RF model showed that the experiment verification was successful, as the results were comparable to the RF modeling results with a prediction error<20%. Shapley additive explanation and partial least squares path model method were used to identify the critical factors and direct and indirect effects of these features on the immobilization ratio. Furthermore, independent models of four HM (Cd, Cu, Pb, and Zn) also achieved better model prediction performance. Feature importance and interactions relationship of influenced factors for individual HM immobilization ratio was clarified. This work can provide a new insight for HM immobilization in soils.

Application of life cycle assessment and machine learning for the production and environmental sustainability assessment of hydrothermal bio-oil

The hydrothermal bio-oil (HBO) production from biomass conversion can achieve sustainable and low-carbon development. It is always time-consuming and labor-intensive to quantitative relationship between influential variables and bio-oil yield and environmental sustainability impact in the hydrothermal conditions. Machine learning was used to predict bio-oil yield. Life cycle assessment (LCA) is further conducted to assess its environmental sustainability effect. The results demonstrated that gradient boosting decision tree regression (GBDT) have the most optimal prediction performance for the HBO yield (Training R² = 0.97, Testing R² = 0.92, RMSE = 0.05, MAE = 0.03). Lipid content is the most significant influential factor for HBO yield. LCA result further suggested that 1 kg of bio-oil production can cause 0.02 kg ep of SO₂, 2.05 kg ep of CO₂, and 0.01 kg ep of NO_x emission, and environmental sustainability assessment of HBO is exhibited. This study provides meaningful insights to ML model prediction performance improvement and carbon footprint of HBO.

Unlocking the potential of transesterification catalysts for biodiesel production through machine learning approach

The growing demand for fossil fuels has motivated the search for a renewable energy source, and biodiesel has emerged as a promising and environmentally friendly alternative. In this study, machine learning techniques were employed to predict the biodiesel yield from transesterification processes using three different catalysts: homogeneous, heterogeneous, and enzyme. Extreme gradient boosting algorithms showed the highest accuracy in predictions, with a coefficient of determination accuracy of nearly 0.98, as determined through a 10-fold cross-validation of the input data. The results indicated that linoleic acid, behenic acid, and reaction time were the most crucial factors affecting biodiesel yield predictions for homogeneous, heterogeneous, and enzyme catalysts, respectively. This research provides insights into the individual and combined effects of key factors on transesterification catalysts, contributing to a deeper understanding of the system.

Machine learning algorithms for high-resolution prediction of spatiotemporal distribution of air pollution from meteorological and soil parameters

This study uses machine learning (ML) models for a high-resolution prediction (0.1°×0.1°) of air fine particular matter (PM_2.5) concentration, the most harmful to human health, from meteorological and soil data. Iraq was considered the study area to implement the method. Different lags and the changing patterns of four European Reanalysis (ERA5) meteorological variables, rainfall, mean temperature, wind speed and relative humidity, and one soil parameter, the soil moisture, were used to select the suitable set of predictors using a non-greedy algorithm known as simulated annealing (SA). The selected predictors were used to simulate the temporal and spatial variability of air PM_2.5 concentration over Iraq during the early summer (May-July), the most polluted months, using three advanced ML models, extremely randomized trees (ERT), stochastic gradient descent backpropagation (SGD-BP) and long short-term memory (LSTM) integrated with Bayesian optimizer. The spatial distribution of the annual average PM_2.5 revealed the population of the whole of Iraq is exposed to a pollution level above the standard limit. The changes in temperature and soil moisture and the mean wind speed and humidity of the month before the early summer can predict the temporal and spatial variability of PM_2.5 over Iraq during May-July. Results revealed the higher performance of LSTM with normalized root-mean-square error and Kling-Gupta efficiency of 13.4% and 0.89, compared to 16.02% and 0.81 for SDG-BP and 17.9% and 0.74 for ERT. The LSTM could also reconstruct the observed spatial distribution of PM_2.5 with MapCurve and Cramer's V values of 0.95 and 0.91, compared to 0.9 and 0.86 for SGD-BP and 0.83 and 0.76 for ERT. The study provided a methodology for forecasting spatial variability of PM_2.5 concentration at high resolution during the peak pollution months from freely available data, which can be replicated in other regions for generating high-resolution PM_2.5 forecasting maps.

A review of biowaste remediation and valorization for environmental sustainability: Artificial intelligence approach

Biowaste remediation and valorization for environmental sustainability focuses on prevention rather than cleanup of waste generation by applying the fundamental recovery concept through biowaste-to-bioenergy conversion systems - an appropriate approach in a circular bioeconomy. Biomass waste (biowaste) is discarded organic materials made of biomass (e.g., agriculture waste and algal residue). Biowaste is widely studied as one of the potential feedstocks in the biowaste valorization process due to its being abundantly available. In terms of practical implementations, feedstock variability from biowaste, conversion costs and supply chain stability prevent the widespread usage of bioenergy products. Biowaste remediation and valorization have used artificial intelligence (AI), a newly developed idea, to overcome these difficulties. This report analyzed 118 works that applied various AI algorithms to biowaste remediation and valorization-related research published between 2007 and 2022. Four common AI types are utilized in biowaste remediation and valorization: neural networks, Bayesian networks, decision tree, and multivariate regression. The neural network is the most frequent AI for prediction models, the Bayesian network is utilized for probabilistic graphical models, and the decision tree is trusted for providing tools to assist decision-making. Meanwhile, multivariate regression is employed to identify the relationship between experimental variables. AI is a remarkably effective tool in predicting data, which is reportedly better than the conventional approach owing to its characteristics of time-saving and high accuracy. The challenge and future work in biowaste remediation and valorization are briefly discussed to maximize the model's performance.

Biomass carbon mining to develop nature-inspired materials for a circular economy

A transition from a linear to a circular economy is the only alternative to reduce current pressures in natural resources. Our society must redefine our material sources, rethink our supply chains, improve our waste management, and redesign materials and products. Valorizing extensively available biomass wastes, as new carbon mines, and developing biobased materials that mimic nature's efficiency and wasteless procedures are the most promising avenues to achieve technical solutions for the global challenges ahead. Advances in materials processing, and characterization, as well as the rise of artificial intelligence, and machine learning, are supporting this transition to a new materials' mining. Location, cultural, and social aspects are also factors to consider. This perspective discusses new alternatives for carbon mining in biomass wastes, the valorization of biomass using available processing techniques, and the implementation of computational modeling, artificial intelligence, and machine learning to accelerate material's development and process engineering.

Machine learning approaches to predict the apparent rate constants for aqueous organic compounds by ferrate

The apparent second-order rate constant with hexavalent ferrate (Fe(VI)) (k_Fe(VI)) is a key indicator to evaluate the removal efficiency of a molecule by Fe(VI) oxidation. k_Fe(VI) is often determined by experiment, but such measurements can hardly catch up with the rapid growth of organic compounds (OCs). To address this issue, in this study, a total of 437 experimental second-order k_Fe(VI) rate constants at a range of conditions (pH and temperature) were used to train four machine learning (ML) algorithms (lasso regression (LR), ridge regression (RR), extreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM)). Using the Morgan fingerprint (MF)) of a range of organic compounds (OCs) as the input, the performance of the four algorithms was comprehensively compared with respect to the coefficient of determination (R²) and root-mean-square error (RMSE). It is shown that the RR, XGBoost, and LightGBM models displayed generally acceptable performance k_Fe(VI) (R²_test > 0.7). In addition, the shapely additive explanation (SHAP) and feature importance methods were employed to interpret the XGBoost/LightGBM and RR models, respectively. The results showed that the XGBoost/LightGBM and RR models suggestd pH as the most important predictor and the tree-based models elucidate how electron-donating and electron-withdrawing groups influence the reactivity of the Fe(VI) species. In addition, the RR model share eight common features, including pH, with the two tree-based models. This work provides a fast and acceptable method for predicting k_Fe(VI) values and can help researchers better understand the degradation behavior of OCs by Fe(VI) oxidation from the perspective of molecular structure.

Exposing and understanding synergistic effects in co-pyrolysis of biomass and plastic waste via machine learning

During co-pyrolysis of biomass with plastic waste, bio-oil yields (BOY) could be either induced or reduced significantly via synergistic effects (SE). However, investigating/ interpreting the SE and BOY in multidimensional domains is complicated and limited. This work applied XGBoost machine-learning and Shapley additive explanation (SHAP) to develop interpretable/ explainable models for predicting BOY and SE from co-pyrolysis of biomass and plastic waste using 26 input features. Imbalanced training datasets were improved by synthetic minority over-sampling technique. The prediction accuracy of XGBoost models was nearly 0.90 R² for BOY while greater than 0.85 R² for SE. By SHAP, individual impact and interaction of input features on the XGBoost models can be achieved. Although reaction temperature and biomass-to-plastic ratio were the top two important features, overall contributions of feedstock characteristics were more than 60 % in the system of co-pyrolysis. The finding provides a better understanding of co-pyrolysis and a way of further improvements.

Machine learning for hydrothermal treatment of biomass: A review

Hydrothermal treatment (HTT) (i.e., hydrothermal carbonization, liquefaction, and gasification) is a promising technology for biomass valorization. However, diverse variables, including biomass compositions and hydrothermal processes parameters, have impeded in-depth mechanistic understanding on the reaction and engineering in HTT. Recently, machine learning (ML) has been widely employed to predict and optimize the production of biofuels, chemicals, and materials from HTT by feeding experimental data. This review comprehensively analyzed the application of ML for HTT of biomass and systematically illustrated basic ML procedure and descriptors for inputs and outputs of ML models (e.g., biomass compositions, operation conditions, yield and physicochemical properties of derived products) that could be applied in HTT. Moreover, this review summarized ML-aided HTT prediction of yield, compositions, and physicochemical properties of HTT hydrochar or biochar, bio-oil, syngas, and aqueous phase. Ultimately, future prospects were proposed to enhance predictive performance, mechanistic interpretation, process optimization, data sharing, and model application during ML-aided HTT.

Bioresource Upgrade for Sustainable Energy, Environment, and Biomedicine

We conceptualize bioresource upgrade for sustainable energy, environment, and biomedicine with a focus on circular economy, sustainability, and carbon neutrality using high availability and low utilization biomass (HALUB). We acme energy-efficient technologies for sustainable energy and material recovery and applications. The technologies of thermochemical conversion (TC), biochemical conversion (BC), electrochemical conversion (EC), and photochemical conversion (PTC) are summarized for HALUB. Microalgal biomass could contribute to a biofuel HHV of 35.72 MJ Kg-1 and total benefit of 749 $/ton biomass via TC. Specific surface area of biochar reached 3000 m2 g-1 via pyrolytic carbonization of waste bean dregs. Lignocellulosic biomass can be effectively converted into bio-stimulants and biofertilizers via BC with a high conversion efficiency of more than 90%. Besides, lignocellulosic biomass can contribute to a current density of 672 mA m-2 via EC. Bioresource can be 100% selectively synthesized via electrocatalysis through EC and PTC. Machine learning, techno-economic analysis, and life cycle analysis are essential to various upgrading approaches of HALUB. Sustainable biomaterials, sustainable living materials and technologies for biomedical and multifunctional applications like nano-catalysis, microfluidic and micro/nanomotors beyond are also highlighted. New techniques and systems for the complete conversion and utilization of HALUB for new energy and materials are further discussed.

Bio-oil production from biogenic wastes, the hydrothermal conversion step

Background: Food wastes are an abundant resource that can be effectively valorised by hydrothermal liquefaction to produce bio-fuels. The objective of the European project WASTE2ROAD is to demonstrate the complete value chain from waste collection to engine tests. The principle of hydrothermal liquefaction is well known but there are still many factors that make the science very empirical. Most experiments in the literature are performed on batch reactors. Comparison of results from batch reactors with experiments with continuous reactors are rare in the literature. Methods: Various food wastes were transformed by hydrothermal liquefaction. The resources used and the products from the experiments have been extensively analysed. Two different experimental reactors have been used, a batch reactor and a continuous reactor. This paper presents a dataset of fully documented experiments performed in this project, on food wastes with different compositions, conditions and solvents. The data set is extended with data from the literature. The data was analysed using machine learning analysis and regression techniques. Results: This paper presents experimental results on various food wastes as well as modelling and analysis with machine learning algorithms. The experimental results were used to attempt to establish a link between batch and continuous experiments. The molecular weight of bio-oil from continuous experiments appear higher than that of batch experiments. This may be due to the configuration of our reactor. Conclusions: This paper shows how the use of regression models help with understanding the results, and the importance of process variables and resource composition.  A novel data analysis technique gives an insight on the accuracy that can be obtained from these models.

Comparative study of machine learning methods integrated with genetic algorithm and particle swarm optimization for bio-char yield prediction

In this study, Machine learning (ML) models integrated with genetic algorithm (GA) and particle swarm optimization (PSO) have been developed to predict, evaluate, and analyze biochar yield using biomass properties and process operating conditions. Comparative study of different ML algorithms integrated with GA and PSO were performed to improve the ML models architecture and parameters selection. The results proposed that Ensembled Learning Tree (ELT-PSO) model outperformed all other models and is favored for biochar yield prediction (R² = 0.99, RMSE = 2.33). The partial dependence plots (PDPs) analysis shows the potential effects of each influencing parameter impact on the biochar yield and as well as shows that how these factors will interact during the pyrolysis process. A user-friendly software was developed based on the ELT-PSO model to avoid extensive and expensive experimentations without requiring considerable ML understanding. Difference recorded by GUI was less than 2% with experimental yield.

Machine learning prediction of nitrogen heterocycles in bio-oil produced from hydrothermal liquefaction of biomass

Hydrothermal liquefaction (HTL) of high-moisture biomass or biowaste to produce bio-oil is a promising technology. However, nitrogen-heterocycles (NH) presence in bio-oil is a bottleneck to the upgrading and utilization of bio-oil. The present study applied the machine learning (ML) method (random forest) to predict and help control the bio-oil NH, bio-oil yield, and N content of bio-oil (N_oil). The results indicated that the predictive performance of the yield and N_oil were better than previous studies, achieving test R² of 0.92 and 0.95, respectively. Acceptable predictive performance (test R² of 0.82 and RMSE of 7.60) for the prediction of NH was also achieved. The feature importance analysis, partial dependence, and Shapely value were used to interpret the prediction models and study the NH formation mechanisms and behavior. Then, forward optimization of NH was implemented based on optimal predictive models, indicating the high potential of ML-aided bio-oil production and engineering.

Prediction of carbon dioxide production from green waste composting and identification of critical factors using machine learning algorithms

Controlling carbon dioxide produced from green waste composting is a vital issue in response to carbon neutralization. However, there are few computational methods for accurately predicting carbon dioxide production from green waste composting. Based on the data collected, this study developed novel machine learning methods to predict carbon dioxide production from green waste composting and made a comparison among six methods. After eliminating the extreme outliers from the dataset, the Random Forest algorithm achieved the highest prediction accuracy of 88% in the classification task and showed the top performance in the regression task (root mean square error = 23.3). As the most critical factor, total organic carbon, with the Gini index accounting for about 59%, can provide guidance for reducing carbon emissions from green waste composting. These results show that there is great potential for using machine learning algorithms to predict carbon dioxide output from green waste composting.

Prediction of arabica coffee production using artificial neural network and multiple linear regression techniques

Crop yield and its prediction are crucial in agricultural production planning. This study investigates and predicts arabica coffee yield in order to match the market demand, using artificial neural networks (ANN) and multiple linear regression (MLR). Data of six variables, including areas, productivity zones, rainfalls, relative humidity, and minimum and maximum temperature, were collected for the recent 180 months between 2004 and 2018. The predicted yield of the cherry coffee crop continuously increases each year. From the dataset, it was found that the prediction accuracy of the R² and RMSE from ANN was 0.9524 and 0.0784 tons, respectively. The ANN model showed potential in determining the cherry coffee yields.

RETRACTED: Chemistry-Informed Neural Networks modelling of lignocellulosic biomass pyrolysis

This article has been retracted: please see Elsevier Policy on Article Withdrawal (http://www.elsevier.com/locate/withdrawalpolicy). This article has been retracted at the request of the authors and the Editor-in-Chief. The article has reused text from the papers published by other authors in Combustion and Flame 240 (2022) 111992 https://doi.org/10.1016/j.combustflame.2022.111992 and the Journal of Physical Chemistry A 125 (2021) 1082–1092 https://doi.org/10.1021/acs.jpca.0c09316 without proper citation and discussion of the two articles. One of the conditions of submission of a paper for publication is that authors declare explicitly that their work is original and has not appeared in a publication elsewhere. As such this article represents a misuse of the scientific publishing system. The scientific community takes a strong view on this matter and apologies are offered to readers of the journal that this was not detected during the submission process.

Effects of hydration parameters on chemical properties of biocrudes based on machine learning and experiments

To investigate the effects of temperature and biomass concentration of Hydrothermal liquefaction (HTL) on chemical properties of biocrudes, machine learning (ML) was used to predict the weight of hydration parameters on the properties of biocrudes. The elemental compositions, molecular weights, functional groups, thermal degradation, molecular structure of biocrudes were studied. The optimum yield of biocrudes was 65% and the highest heat value reached up to 34.28 kJ/g, showing comparable fuel properties. It was found that the hydration temperature significantly affects the elemental components, functional groups and molecular weight and structures of biocrudes. In addition, biomass concentration also affect the functional groups and structures of biocrudes. ML results indicated that Support Vector Machine Linear Kernel method is suitable for heat value prediction.

Machine learning prediction of lignin content in poplar with Raman spectroscopy

Based on features extracted from Raman spectra, regularization algorithms, SVR, DT, RF, LightGBM, CatBoost, and XGBoost were used to develop prediction models for lignin content in poplar. Firstly, Raman features extracted from FT-Raman spectra after data processing were used as input of models and determined lignin contents were output. Secondly, grid-search combined with cross-validation was used to adjust the hyper-parameters of models. Finally, the predictive models were built by aforementioned algorithms. The results indicated regularization algorithms, SVR, DT held test R² were >0.80 which means the predictive values from model still deviate from measured ones. Meanwhile, RF, LightGBM, CatBoost, and XGBoost were better than above algorithms, and their test R² were >0.91 which suggesting the predictive values was nearly close to measured ones. Therefore, fast and accurate methods for predicting lignin content were obtained and will be useful for screening suitable lignocellulosic resource with expected lignin content.