Exploring Insights in Biomass and Waste Gasification via Ensemble Machine Learning Models and Interpretability Techniques DOI Creative Commons
Ocident Bongomin, Charles Nzila, Josphat Igadwa Mwasiagi

и другие.

International Journal of Energy Research, Год журнала: 2024, Номер 2024(1)

Опубликована: Янв. 1, 2024

This comprehensive review delves into the intersection of ensemble machine learning models and interpretability techniques for biomass waste gasification, a field crucial sustainable energy solutions. It tackles challenges like feedstock variability temperature control, highlighting need deeper understanding to optimize gasification processes. The study focuses on advanced modeling random forests gradient boosting, alongside methods Shapley additive explanations partial dependence plots, emphasizing their importance transparency informed decision‐making. Analyzing diverse case studies, explores successful applications while acknowledging overfitting computational complexity, proposing strategies practical robust models. Notably, finds consistently achieve high prediction accuracy (often exceeding R 2 scores 0.9) gas composition, yield, heating value. These (34% reviewed papers) are most applied method, followed by artificial neural networks (26%). Heating value (12%) was studied performance metric. However, is often neglected during model development due complexity permutation Gini importance. paper calls dedicated research utilizing interpreting models, especially co‐gasification scenarios, unlock new insights process synergy. Overall, this serves as valuable resource researchers, practitioners, policymakers, offering guidance enhancing efficiency sustainability gasification.

Язык: Английский

Carbon Sequestration Strategies in Soil Using Biochar: Advances, Challenges, and Opportunities DOI
Lei Luo,

Jiaxiao Wang,

Jitao Lv

и другие.

Environmental Science & Technology, Год журнала: 2023, Номер 57(31), С. 11357 - 11372

Опубликована: Июль 26, 2023

Biochar, a carbon (C)-rich material obtained from the thermochemical conversion of biomass under oxygen-limited environments, has been proposed as one most promising materials for C sequestration and climate mitigation in soil. The contribution biochar hinges not only on its fused aromatic structure but also abiotic biotic reactions with soil components across entire life cycle environment. For instance, minerals microorganisms can deeply participate mineralization or complexation labile (soluble easily decomposable) even recalcitrant fractions biochar, thereby profoundly affecting cycling Here we identify five key issues closely related to application review outstanding advances. Specifically, terms use pyrochar, hydrochar, stability soil, effect flux speciation changes emission nitrogen-containing greenhouse gases induced by production application, barriers are expounded. By elaborating these critical issues, discuss challenges knowledge gaps that hinder our understanding provide outlooks future research directions. We suggest combining mechanistic biochar-to-soil interactions long-term field studies, while considering influence multiple factors processes, is essential bridge gaps. Further, standards should be widely implemented, threshold values urgently developed. Also needed comprehensive prospective assessments restricted account contributions contamination remediation, quality improvement, vegetation accurately reflect total benefits

Язык: Английский

Процитировано

99
From biomass to biocrude: Innovations in hydrothermal liquefaction and upgrading DOI Creative Commons
Muhammad Usman, Shuo Cheng, Sasipa Boonyubol

и другие.

Energy Conversion and Management, Год журнала: 2024, Номер 302, С. 118093 - 118093

Опубликована: Фев. 1, 2024

It is crucial to find sustainable and renewable fuel sources because traditional fossil fuels are running out pollution levels rising. In this context, biocrude derived from biomass emerges as a promising alternative, with hydrothermal liquefaction (HTL) playing pivotal role in transformation. HTL's versatility converting wide range of or waste materials into especially notable. Therefore, comprehensive review focused on the latest advancements HTL technology, including its potential process various materials, resulting high yields (up 60–86% different types). The study explored such effects catalysts processes, scalability for commercializing continuous aqueous phase recycling. also integration machine learning optimization, offering insights how these advanced computational techniques can enhance efficiency output quality. subsequent hydrotreatment emerge key technologies utilizing source. This not only highlights current state refining upgrading but stresses need ongoing development domains. presented transformative solution energy sector, alternative while tackling impurities heteroatoms management challenges. concluded by underscoring practical implications advancements, suggesting roadmap future research field.

Язык: Английский

Процитировано

43
Feature engineering for improved machine-learning-aided studying heavy metal adsorption on biochar DOI

Tian Shen,

Haoyi Peng,

Xingzhong Yuan

и другие.

Journal of Hazardous Materials, Год журнала: 2024, Номер 466, С. 133442 - 133442

Опубликована: Янв. 6, 2024

Язык: Английский

Процитировано

29
Machine-learning-aided prediction and engineering of nitrogen-containing functional groups of biochar derived from biomass pyrolysis DOI
Lijian Leng,

Xinni Lei,

Naif Abdullah Al‐Dhabi

и другие.

Chemical Engineering Journal, Год журнала: 2024, Номер 485, С. 149862 - 149862

Опубликована: Фев. 20, 2024

Язык: Английский

Процитировано

24
Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy DOI
Van Giao Nguyen, Prabhakar Sharma, Ümit Ağbulut

и другие.

Biofuels Bioproducts and Biorefining, Год журнала: 2024, Номер 18(2), С. 567 - 593

Опубликована: Фев. 5, 2024

Abstract Biochar is emerging as a potential solution for biomass conversion to meet the ever increasing demand sustainable energy. Efficient management systems are needed in order exploit fully of biochar. Modern machine learning (ML) techniques, and particular ensemble approaches explainable AI methods, valuable forecasting properties efficiency biochar properly. Machine‐learning‐based forecasts, optimization, feature selection critical improving techniques. In this research, we explore influences these techniques on accurate yield range sources. We emphasize importance interpretability model, improves human comprehension trust ML predictions. Sensitivity analysis shown be an effective technique finding crucial characteristics that influence synthesis Precision prognostics have far‐reaching ramifications, influencing industries such logistics, technologies, successful use renewable These advances can make substantial contribution greener future encourage development circular biobased economy. This work emphasizes using sophisticated data‐driven methodologies synthesis, usher ecologically friendly energy solutions. breakthroughs hold key more environmentally future.

Язык: Английский

Процитировано

23
Machine learning-based optimization of catalytic hydrodeoxygenation of biomass pyrolysis oil DOI

Xiangmeng Chen,

Alireza Shafizadeh, Hossein Shahbeik

и другие.

Journal of Cleaner Production, Год журнала: 2024, Номер 437, С. 140738 - 140738

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

18
Machine learning applications for biochar studies: A mini-review DOI
Wei Wang, Jo‐Shu Chang, Duu‐Jong Lee

и другие.

Bioresource Technology, Год журнала: 2024, Номер 394, С. 130291 - 130291

Опубликована: Янв. 4, 2024

Язык: Английский

Процитировано

16
Artificial intelligence and machine learning for smart bioprocesses DOI
Samir Kumar Khanal, Ayon Tarafdar, Siming You

и другие.

Bioresource Technology, Год журнала: 2023, Номер 375, С. 128826 - 128826

Опубликована: Март 5, 2023

Язык: Английский

Процитировано

41
Machine learning-aided prediction of nitrogen heterocycles in bio-oil from the pyrolysis of biomass DOI
Lijian Leng, Tanghao Li, Hao Zhan

и другие.

Energy, Год журнала: 2023, Номер 278, С. 127967 - 127967

Опубликована: Май 29, 2023

Язык: Английский

Процитировано

34
Precise Prediction of Biochar Yield and Proximate Analysis by Modern Machine Learning and SHapley Additive exPlanations DOI
Lê Anh Tuấn, Ashok Pandey,

Ranjan Sirohi

и другие.

Energy & Fuels, Год журнала: 2023, Номер 37(22), С. 17310 - 17327

Опубликована: Окт. 28, 2023

Biochar is found to possess a large number of applications in energy and environmental areas. However, biochar could be produced from variety sources, showing that yield proximate analysis outcomes change over wide range. Thus, developing high-accuracy machine learning-based tool very necessary predict characteristics. In this study, hybrid technique was developed by blending modern learning (ML) algorithms with cooperative game theory-based Shapley Additive exPlanations (SHAP). SHAP employed help improve interpretability while offering insights into the decision-making process. ML models, linear regression as baseline method, more advanced methodologies like AdaBoost boosted tree (BRT) were employed. The prediction models evaluated on battery statistical metrics, all observed robust enough. Among three BRT-based model delivered best performance R2 range 0.982 0.999 during training phase 0.968 0.988 test. value mean squared error also quite low (0.89 9.168) for models. quantified each input element expected results provided in-depth understanding underlying dynamics. helped reveal temperature main factor affecting response predictions. proposed here provides substantial manufacturing process, allowing improved control properties increasing use sustainable flexible material numerous applications.

Язык: Английский

Процитировано

31