Main applications of machine learning in sludge anaerobic digestion： from process optimization to intelligent decision-making

SONG Xin; CAO Yihang; ZHANG Chi; LUO Jingyang

doi:10.13205/j.hjgc.202607022

Volume 44 Issue 7

Jul. 2026

Turn off MathJax

Article Contents

Article Navigation > ENVIRONMENTAL ENGINEERING > 2026 > 44(7): 222-232

SONG Xin, CAO Yihang, ZHANG Chi, LUO Jingyang. Main applications of machine learning in sludge anaerobic digestion： from process optimization to intelligent decision-making[J]. ENVIRONMENTAL ENGINEERING , 2026, 44(7): 222-232. doi: 10.13205/j.hjgc.202607022

Citation:

SONG Xin, CAO Yihang, ZHANG Chi, LUO Jingyang. Main applications of machine learning in sludge anaerobic digestion： from process optimization to intelligent decision-making[J]. ENVIRONMENTAL ENGINEERING , 2026, 44(7): 222-232. doi: 10.13205/j.hjgc.202607022

Citation:

SONG Xin, CAO Yihang, ZHANG Chi, LUO Jingyang. Main applications of machine learning in sludge anaerobic digestion： from process optimization to intelligent decision-making[J]. ENVIRONMENTAL ENGINEERING , 2026, 44(7): 222-232. doi: 10.13205/j.hjgc.202607022

PDF( 710 KB)

Main applications of machine learning in sludge anaerobic digestion： from process optimization to intelligent decision-making

doi: 10.13205/j.hjgc.202607022

SONG Xin^1,2,
CAO Yihang^1,2,
ZHANG Chi^1,2,
LUO Jingyang^{1,2
,
,}

1. Key Laboratory of Integrated Regulation and Resource Development on Shallow Lakes of the Ministry of Education, Hohai University, Nanjing 210098, China;
2. College of Environment, Hohai University, Nanjing 210098, China

Received Date: 2026-03-31
Available Online: 2026-09-01

Abstract

Abstract

Anaerobic sludge digestion is the core process for achieving energy recovery and sludge reduction in wastewater treatment plants. However， its complex biological reaction mechanisms and multivariable coupling characteristics pose persistent challenges to process optimization and stable control. Although traditional mechanistic models have clear theoretical foundations， they have limitations such as the difficulty in parameter calibration and insufficient adaptability when addressing dynamic conditions and nonlinear relationships. In recent years， machine learning has attracted extensive attention in the field of sludge digestion due to its powerful data modeling capabilities. This paper systematically reviews the main applications of machine learning in the performance prediction， process monitoring and early warning， and process parameter optimization of sludge anaerobic digestion. For gas production prediction， hybrid models and deep learning methods have achieved high-precision methane prediction. For process monitoring， soft-sensing models using easy-to-measure parameters facilitate real-time estimation of key indicators such as volatile fatty acids and total ammonia nitrogen. At the level of process optimization， the integration of the surrogate models with optimization algorithms offers dynamic regulation strategies for co-digestion ratios and pretreatment conditions. In addition， the incorporation of interpretable methods provides a technical path for addressing the model "black-box" problem and enhances operators' acceptability of applying models in engineering. The deep integration of these methods with dynamic optimization of process parameters enables the construction of an intelligent decision-making framework， which has significant engineering value. However， the transformation of these research findings from laboratory to engineering application is still hindered by multiple constraints， including data quality， model generalization， and engineering implementation. This paper provides an analytical framework for the optimization and regulation of sludge treatment processes that combines predictive capability with engineering reliability.
- machine learning,
- anaerobic digestion,
- sludge treatment,
- process optimization,
- interpretable artificial intelligence

FullText(HTML)

References(49)

References

[1]	ZHANG C，DUAN N N，ZHAO S Q，et al. Selection and development trend of urban multi-source sludge treatment and disposal technologies under the Dual Carbon Goal[J]. Environmental Engineering，2025，43（7）：1-9. 张辰，段妮娜，赵水钎，等. 双碳目标下城市多源污泥处理处置技术选择与发展趋势[J]. 环境工程，2025，43（7）：1-9.
[2]	RAZAVIARANI V，ALKOUR M，THOMAS A M. Sustainable sludge management through circular economy solutions for resource recovery and carbon footprint reduction[J]. Journal of the Air& Waste Management Association，2025，76（3）：213-228.
[3]	ZHANG D，DONG Y，HUANG Y，et al. Research and application status of sludge treatment and disposal technologies at home and abroad[J]. Environmental Engineering，2015，33（S1）：600-604. 张冬，董岳，黄瑛，等. 国内外污泥处理处置技术研究与应用现状[J]. 环境工程，2015，33（增刊1）：600-604.
[4]	王雪雪，陈长夫，罗庆明，等. 我国市政污泥环境管理政策及行业发展趋势[J/OL]. 环境工程学报，1-16.[ 2026-06-30]. htps：/ink.cnkinelurid/11.5591.X. 20260324.1457. 004. WANG X X，CHEN C F，LUO Q M，et al. Environmental management policies and industry development trends of municipal sludge in China[J/OL]. Chinese Journal of Environmental Engineering，2025：1-16.[ 2026-06-30]. htps：/ink.cnkinelurid/11.5591.X. 20260324.1457. 004.
[5]	CAO X Q，CHEN A N，GAN Y P，et al. Research and progress of sludge anaerobic digestion technology[J]. Environmental Engineering，2008，26（S1）：215-219. 曹秀芹，陈爱宁，甘一萍，等. 污泥厌氧消化技术的研究与进展[J]. 环境工程，2008，26（增刊1）：215-219.
[6]	BATSTONE D，KELLER J，ANGELIDAKI I，et al. The IWA anaerobic digestion model No 1（ADM1）[J]. Water Science and Technology，2002，45（10）：65-73.
[7]	LIU Y，JIANG Y，NASAR N，et al. Improving ADM1 predictions via Bayesian analysis for continuous anaerobic digestion[J]. Journal of Environmental Management，2026，398：119125.
[8]	JORDAN M，MITCHELL T. Machine learning：Trends，perspectives，and prospects[J]. Science，2015，349（6245）：255-260.
[9]	GAN E，CHAN Y，WAN Y，et al. Examining the synergistic effects through machine learning prediction and optimisation in the anaerobic co-digestion（ACoD）of palm oil mill effluent（POME）and decanter cake（DC）with economic analysis[J]. Journal of Cleaner Production，2024，437：139726.
[10]	WANG L，LONG F，LIAO W，et al. Prediction of anaerobic digestion performance and identification of critical operational parameters using machine learning algorithms[J]. Bioresource Technology，2020，298：122481.
[11]	KARAMI A，JASHNI A K，NIKOO M R，et al. Simulation of anaerobic digestion process under variable feeding sludge using a hybrid machine learning model[J]. Chemosphere，2025，387：144672.
[12]	PENG J T，TANG Z H，WU T W，et al. Research progress of anaerobic digestion of organic solid waste empowered by artificial intelligence[J]. Energy and Environmental Protection，2026，40（2）：89-101. 彭江涛，汤振华，吴泰武，等. AI 赋能有机固废厌氧消化研究进展[J]. 能源环境保护，2026，40（2）：89-101.
[13]	DE CLERCQ D，WEN Z，FEI F，et al. Interpretable machine learning for predicting biomethane production in industrial-scale anaerobic co-digestion[J]. Science of the Total Environment，2020，712：136457.
[14]	SIMEONOV I，HUBENOV V. Application of artificial intelligence for prediction，monitoring，optimization and control of anaerobic digestion processes：a review[J]. Processes，2025，13（12）：3812.
[15]	MARYCZ M，TUROWSKA I，GLAZIK S，et al. Artificial intelligence in anaerobic digestion：a review of sensors，modeling approaches，and optimization strategies[J]. Sensors，2025，25（22）：6961.
[16]	HENRI H，ALEXIS A，ANMOL K，et al. Integrating data-driven models and process expertise in soft-sensor design for a wastewater treatment digital twin application[J]. Water Science and Technology，2025，92（9）：1308-1327.
[17]	GANESHAN P，BOSE A，LEE J，et al. Machine learning for high solid anaerobic digestion：performance prediction and optimization[J]. Bioresource Technology，2024，400：130996.
[18]	LING J Y X，CHAN Y J，CHEN J W，et al. Machine learning methods for the modelling and optimisation of biogas production from anaerobic digestion：a review[J]. Environmental Science and Pollution Research，2024，31（13）：19085-19104.
[19]	RADOČAJ D，JURIŠIĆ M. Comparative evaluation of ensemble machine learning models for methane production from anaerobic digestion[J]. Fermentation，2025，11（3）：130.
[20]	FARD M G，KOUPAIE E H. Anaerobic co-digestion of wastewater sludge and food waste：a machine learning approach to process modeling and optimization[J]. Journal of Environmental Management，2025，393：126985.
[21]	MUKASINE A，SIBOMANA L，JAYAVEL K，et al. Maximizing biogas yield using an optimized stacking ensemble machine learning approach[J]. Energies，2024，17（2）：921.
[22]	ZHUANG Z，LIU X，JIN J，et al. Prediction，uncertainty quantification，and ANN-assisted operation of anaerobic digestion guided by entropy using machine learning[J]. Entropy，2025，27（12）：1233.
[23]	YOUSSEF B，AMINE C，MOHAMED S，et al. Optimizing TAN monitoring in various anaerobic digestion systems：a machine learning approach with XGBoost and AdaBoost[C]// 2025 IEEE 16th Control and System Graduate Research Colloquium（ICSGRC）. Piscataway，2025：1-6.
[24]	CHEN L，HE P，ZOU J，et al. Scalable and interpretable automated machine learning framework for biogas prediction，optimization，and stability monitoring in industrial-scale dry anaerobic digestion[J]. Chemical Engineering Journal，2025，519：165482.
[25]	KHAN M，SURENDRA K，BANIYA S，et al. Biochar-augmented anaerobic digestion system：insights from an interpretable stacking ensemble deep learning[J]. Environmental Science& Technology，2025，59（29）：15236-15250.
[26]	RU J，YOUNGCHAE S，DONGMEI P，et al. Exploration of deep learning models for real-time monitoring of state and performance of anaerobic digestion with online sensors[J]. Bioresource Technology，2022，363：127908.
[27]	KONG D，CHU L，YANG P，et al. Plant-scale biogas production based on integrating of CEEMDAN decomposition with PSO optimized multilayer perceptron neural network[J]. Fermentation，2024，10（12）：660.
[28]	CHENG X，XU R，WU Y，et al. Predicting and evaluating different pretreatment methods on methane production from sludge anaerobic digestion via automated machine learning with ensembled semisupervised learning[J]. ACS ES&T Engineering，2024，4（3）：525-539.
[29]	RAO K，SAIKRISHNA G，SUPRIYA K. Data preprocessing techniques：emergence and selection towards machine learning models-a practical review using HPA dataset[J]. Multimedia Tools and Applications，2023，82（24）：36789-36812.
[30]	FARZIN F，MOGHADDAM S S，EHTESHAMI M. Auto-tuning data-driven model for biogas yield prediction from anaerobic digestion of sewage sludge at the south-tehran wastewater treatment plant：feature selection and hyperparameter population-based optimization[J]. Renewable Energy，2024，227：120346.
[31]	MEOLA A，WOLF K，WEINRICH S. Meta-tuning and fast optimization of machine learning models for dynamic methane prediction in anaerobic digestion[J]. Bioresource Technology，2025，432：132654.
[32]	ATAOLLAH S，HIMAN S，KAMAL N，et al. Towards robust smart data-driven soil erodibility index prediction under different scenarios[J]. Geocarto International，2022，37（26）：13176-13209.
[33]	DAVIDE C，MATTHIJS J W，GIUSEPPE J. The coefficient of determination R-squared is more informative than SMAPE，MAE，MAPE，MSE and RMSE in regression analysis evaluation[J]. PeerJ Computer Science，2021（7）：e623.
[34]	ROHIT G，LE Z，JIAYI H，et al. Review of explainable machine learning for anaerobic digestion[J]. Bioresource Technology，2022，369：128468.
[35]	LIAO Y，PAN C，LU F，et al. Boosting biogas prediction：an interpretable SVM-RVM-stacking model for small-sample anaerobic digestion[J]. Journal of Environmental Chemical Engineering，2025，13（5）：118829.
[36]	AMANGELDY B，BAIGARAYEVA Z，TASMURZAYEV N，et al. Benchmarking tabular foundation models for total volatile fatty acid prediction in anaerobic digestion[J]. Algorithms，2026，19（2）：127.
[37]	ABUBAKAR U A，LEMAR G S，BELLO A A D，et al. Evaluation of traditional and machine learning approaches for modeling volatile fatty acid concentrations in anaerobic digestion of sludge：potential and challenges[J]. Environmental Science and Pollution Research，2024，32（49）：1-14.
[38]	NEUBAUER L，KRÜMPEL J，KHAN M T，et al. Predicting anaerobic digestion stability in load-flexible operation using gas phase indicators and classification algorithms[J]. Bioresource Technology，2025，429：132508.
[39]	LIU Z，FOONG S Y，ZHANG Y，et al. Proactive detection，prediction，and control of instabilities in anaerobic digestion systems[J]. Renewable and Sustainable Energy Reviews，2025，224：116101.
[40]	CHEN Y，HUANG Z，MA C，et al. A newly early warning model for anaerobic digestion systems：based on an improved sparrow search algorithm combined with least square support vector machine[J]. Chemical Engineering Journal，2024，490：151743.
[41]	JIA R，SONG Y C，AN Z，et al. Unraveling anaerobic digestion instability：a simple index based on the kinetic balance of biochemical reactions[J]. Processes，2023，11（10）：2987.
[42]	MUZAMMIL K，WACHIRANON C，C S K，et al. Applications of artificial intelligence in anaerobic co-digestion：recent advances and prospects[J]. Bioresource Technology，2022，370：128501.
[43]	J A R，D N J，J B. Using multi-objective optimisation with ADM1 and measured data to improve the performance of an existing anaerobic digestion system[J]. Chemosphere，2022，301：134523.
[44]	GE Y，LI Z，YUAN Z，et al. The prediction and optimization of biomass compatibility ratios by machine learning for enhancing methane production in anaerobic co-digestion[J]. Bioresource Technology，2025，437：133071.
[45]	CHEN P，WEI Q，LI W，et al. Dynamic control of thermal hydrolysis to maximize net energy recovery from sewage sludge based on machine learning[J]. Bioresource Technology，2025，438：133263.
[46]	RUTLAND H，YOU J，LIU H，et al. A systematic review of machine-learning solutions in anaerobic digestion[J]. Bioengineering，2023，10（12）：721.
[47]	AMINA A，MOHAMMED B. Peeking inside the black-box：a survey on explainable artificial intelligence（XAI）[J]. IEEE Access，2018（6）：52138-52160.
[48]	WEISHUAI L，JINGANG H，ZHUOER S，et al. Machine learning enabled prediction and process optimization of VFA production from riboflavin-mediated sludge fermentation[J]. Frontiers of Environmental Science& Engineering，2023，17（11）：135.
[49]	FLORES S J R，LIZA R，NAVEDA R N，et al. Machine learning and hybrid approaches in the energy valorization of contaminated sludge：global trends and perspectives[J]. Processes，2026，14（2）：363.