首页 > 分享 > 机器学习在有机固体废物资源化的应用进展

机器学习在有机固体废物资源化的应用进展

花匠小妙招
2024-12-16 15:52

摘要:

机器学习（ML）方法，以其卓越的数据解析和模式识别能力，已在有机固体废物（OSW）处理领域展现出显著的应用潜力. 随着对OSW处理需求的日益增长及技术革新的推进，ML在该领域的应用正迅速普及. 聚焦ML技术在OSW资源化处理中的应用，首先界定了OSW的范畴，针对OSW处理中存在的异质性和复杂性问题，指出了传统处理技术在进行OSW产量预测和条件优化时的局限性. 通过对2018—2023年相关学术成果进行系统梳理和分析，揭示了ML在OSW处理中的研究趋势和潜力. 特别是发现以人工神经网络（ANN）、支持向量机（SVM）、决策树（DT）、随机森林（RF）和极端梯度提升（XGBoost）为代表的常用模型结合遗传（GA）优化算法，成为提高OSW处理效率和资源回收率的研究热点. 分析了这些模型在源头产生与分类、热化学转化处理、厌氧生物处理和好氧堆肥等具体应用中的现状及应用频率，同时评估了它们的优缺点及适用性. 研究发现，ML技术能够有效提高OSW处理的预测精度和工艺优化能力，尤其是在废物特性预测和生物处理过程模拟方面展现出显著优势. 然而，数据质量、模型的泛化能力以及算法选择仍然是ML技术应用中的关键挑战. 为此，提出开发综合模型、加强跨学科技术融合等一系列解决策略，以期为OSW资源化提供科学指导和技术支持.

Abstract:

Machine learning (ML) techniques, with their advanced data analysis and pattern recognition capabilities, are highly effective for addressing the complexities of organic solid waste (OSW) treatment and resource recovery. As global waste generation continues to increase, the need for efficient and sustainable OSW management solutions is growing. Traditional waste treatment technologies often face challenges in managing the heterogeneous and complex nature of OSW, which varies widely in composition. In contrast, ML can optimize treatment processes, improve resource recovery rates, and enhance decision-making. This study explores a range of commonly used ML models, including artificial neural network (ANN), support vector machine (SVM), decision tree, random forest, and extreme gradient boosting (XGBoost). These models have been used to predict waste characteristics, classify diverse types of OSW, and optimize treatment parameters across various processes, such as thermochemical conversion, anaerobic digestion, and aerobic composting. A key focus of this work is the combination of ML models with optimization algorithms like Genetic Algorithm, which improves the performance of ML models by optimizing hyperparameters and enhancing prediction accuracy. This approach is particularly useful in complex processes such as biological treatment and resource recovery, where ML models can predict waste characteristics and optimize treatment conditions. This work also presents a comprehensive analysis of the application frequency of these ML models in various stages of OSW treatment, including source generation, classification, and treatment processes like pyrolysis, gasification, and composting. This analysis identifies the strengths and weaknesses of each model, highlighting the importance of selecting the most appropriate ML approach based on the specific characteristics of the OSW treatment task. ANN, for example, is particularly useful for complex, nonlinear relationships within biological treatment processes, while SVM is effective for small datasets and high-dimensional data. Despite the promise of ML in OSW management, there are key challenges that remain unresolved. These include issues related to data quality, such as missing or incomplete datasets, and the generalization ability of ML models across different treatment scenarios. Furthermore, selecting the right ML model for a specific task requires careful consideration of the data structure, the complexity of the problem, and the desired outcomes. The full potential of ML in OSW treatment may not be realized without addressing these challenges. This work proposes strategies for overcoming these challenges and improving the effectiveness of ML in OSW treatment. One strategy involves developing integrated models that combine multiple ML techniques to leverage their respective strengths. For example, the ensemble learning method, which integrates the outputs of multiple models, has been demonstrated to improve prediction accuracy and robustness. Another strategy is the use of reinforcement learning and transfer learning, which effectively address dynamic environments and small datasets, respectively. Finally, this work highlights the need for future research to focus on the integration of ML models with real-time process monitoring and control systems. By linking ML with data-driven control strategies, such as model predictive control, it may be possible to develop fully automated, intelligent OSW treatment systems that optimize resource recovery and minimize environmental impact. The work concludes by recommending that researchers continue exploring the combinations of ML with advanced control techniques to push the achievement boundaries in sustainable waste management.

图 1 ML在OSW中的模型构建与应用过程

Figure 1. Machine learning modeling and applications in the organic solid waste field

图 2 相关文章的分布与趋势统计. (a) OSW处理; (b)热处理技术

Figure 2. Distribution and trend statistics of related articles in organic solid waste (OSW) treatment: (a) OSW treatment; (b) heat treatment technology

图 3 应用于OSW资源化的各种ML模型的频率统计

Figure 3. Frequency of various machine learning algorithms(including SVM, ANN,RF/DT and others) applied to the OSW field

图 4 ANN、SVM、DT/RF模型在OSW各领域的应用频率热图

Figure 4. Heatmap of the application frequencies of ANN, SVM, and DT/RF models in various OSW treatment methods

图 5 2018—2023年OSW处理领域机器学习模型应用频率趋势

Figure 5. Usage trends of machine learning models in OSW treatment (2018—2023)

表 1 ANN、SVM、RF/DT、XGBoost的优点、局限性及相应的适用领域

Table 1 Advantages, limitations, and corresponding application fields of ANN、SVM、RF/DT、GA in OSW

ML model Advantages Limitations Suitable application fields ANN(1) Deep learning capability
(2) Adaptability to various data types
(3) Automatic feature extraction
(4) Efficient graphics processing unit (GPU) training(1) Requires large datasets
(2) Complex tuning and architecture
(3) Computationally intensive(1) Predictive maintenance of waste-to-energy plants
(2) Real-time waste monitoring
(3) Dynamic waste routingSVM(1) Effective in high-dimensional spaces
(2) Versatile, with various kernels
(3) Regularization controls overfitting
(4) Global optimization(1) Memory intensive with large datasets
(2) Sensitive to parameter tuning
(3) Primarily for binary classification(1) Landfill gas prediction
(2) Odor-control optimization
(3) Resource-recovery planningDT(1) Fast learning
(2) Minimal data preprocessing(1) Prone to overfitting
(2) Limited nonlinear capabilities(1) Composting optimization
(2) Waste generation and classification
(3) Landfill diversion strategies
(4) Pyrolysis performance estimation
(5) Bioprocess optimizationRF(1) Robust ensemble method
(2) Addresses nonlinearity
(3) Less prone to overfitting than DT(1) Slower training than DT
(2) Complexity in interpretation
(3) Not ideal for high dimensionsXGBoost(1) High efficiency and fast training on large datasets
(2) Addresses missing data well
(3) Regularization controls overfitting
(4) Scalable for high dimensions(1) Computationally intensive
(2) Complex interpretation
(3) Requires careful parameter tuning(1) Resource-recovery efficiency prediction
(2) Real-time process optimization
(3) Multivariable process optimization
(4) Pyrolysis and gasification modeling [1]

Arun C, Sivashanmugam P. Study on optimization of process parameters for enhancing the multi-hydrolytic enzyme activity in garbage enzyme produced from preconsumer organic waste. Bioresour Technol, 2017, 226: 200 doi: 10.1016/j.biortech.2016.12.029

[2]

Laurent A, Bakas I, Clavreul J, et al. Review of LCA studies of solid waste management systems: Part I: Lessons learned and perspectives. Waste Manag, 2014, 34(3): 573 doi: 10.1016/j.wasman.2013.10.045

[3]

Kumar A, Samadder S R. Performance evaluation of anaerobic digestion technology for energy recovery from organic fraction of municipal solid waste: A review. Energy, 2020, 197: 117253 doi: 10.1016/j.energy.2020.117253

[4]

Salman C A, Schwede S, Thorin E, et al. Predictive modelling and simulation of integrated pyrolysis and anaerobic digestion process. Energy Procedia, 2017, 105: 850 doi: 10.1016/j.egypro.2017.03.400

[5]

Wang H X, Xu J L, Yu H X, et al. Study of the application and methods for the comprehensive treatment of municipal solid waste in Northeastern China. Renew Sustain Energy Rev, 2015, 52: 1881 doi: 10.1016/j.rser.2015.08.038

[6]

Nikku M, Deb A, Sermyagina E, et al. Reactivity characterization of municipal solid waste and biomass. Fuel, 2019, 254: 115690 doi: 10.1016/j.fuel.2019.115690

[7]

Patra A K, Lalhriatpuii M. Development of statistical models for prediction of enteric methane emission from goats using nutrient composition and intake variables. Agric Ecosyst Environ, 2016, 215: 89 doi: 10.1016/j.agee.2015.09.018

[8]

Andrade Cruz I, Chuenchart W, Long F, et al. Application of machine learning in anaerobic digestion: Perspectives and challenges. Bioresour Technol, 2022, 345: 126433 doi: 10.1016/j.biortech.2021.126433

[9]

Guo H N, Wu S B, Tian Y J, et al. Application of machine learning methods for the prediction of organic solid waste treatment and recycling processes: A review. Bioresour Technol, 2021, 319: 124114 doi: 10.1016/j.biortech.2020.124114

[10]

Portugal I, Alencar P, Cowan D. The use of machine learning algorithms in recommender systems: A systematic review. Expert Syst Appl, 2018, 97: 205 doi: 10.1016/j.eswa.2017.12.020

[11]

Cipullo S, Snapir B, Prpich G, et al. Prediction of bioavailability and toxicity of complex chemical mixtures through machine learning models. Chemosphere, 2019, 215: 388 doi: 10.1016/j.chemosphere.2018.10.056

[12]

Chen C, Liang R, Song M Y, et al. Noise-assisted data enhancement promoting image classification of municipal solid waste. Resour Conserv Recycl, 2024, 209: 107790 doi: 10.1016/j.resconrec.2024.107790

[13]

Ahmad A, Yadav A K, Singh A, et al. A comprehensive machine learning-coupled response surface methodology approach for predictive modeling and optimization of biogas potential in anaerobic co-digestion of organic waste. Biomass Bioenergy, 2024, 180: 106995 doi: 10.1016/j.biombioe.2023.106995

[14]

Wu Q L, Bao X, Guo W Q, et al. Medium chain carboxylic acids production from waste biomass: Current advances and perspectives. Biotechnol Adv, 2019, 37(5): 599 doi: 10.1016/j.biotechadv.2019.03.003

[15]

Long F, Fan J, Xu W C, et al. Predicting the performance of medium-chain carboxylic acid (MCCA) production using machine learning algorithms and microbial community data. J Clean Prod, 2022, 377: 134223 doi: 10.1016/j.jclepro.2022.134223

[16]

Agrawal P, R G, Dhawane S H. Prediction of biodiesel yield employing machine learning: Interpretability analysis via shapley additive explanations. Fuel, 2024, 359: 130516 doi: 10.1016/j.fuel.2023.130516

[17]

Ma J J, Zhang S, Liu X J, et al. Machine learning prediction of biochar yield based on biomass characteristics. Bioresour Technol, 2023, 389: 129820 doi: 10.1016/j.biortech.2023.129820

[18]

Kulisz M, Kujawska J. Prediction of municipal waste generation in Poland using neural network modeling. Sustainability, 2020, 12(23): 10088 doi: 10.3390/su122310088

[19]

Elshaboury N, Mohammed Abdelkader E, Al-Sakkaf A, et al. Predictive analysis of municipal solid waste generation using an optimized neural network model. Processes, 2021, 9(11): 2045 doi: 10.3390/pr9112045

[20]

Soni U, Roy A, Verma A, et al. Forecasting municipal solid waste generation using artificial intelligence models-a case study in India. SN Appl Sci, 2019, 1(2): 162 doi: 10.1007/s42452-018-0157-x

[21]

Zheng Y, Bai J R, Xu J N, et al. A discrimination model in waste plastics sorting using NIR hyperspectral imaging system. Waste Manage, 2018, 72: 87 doi: 10.1016/j.wasman.2017.10.015

[22]

Serranti S, Gargiulo A, Bonifazi G. Classification of polyolefins from building and construction waste using NIR hyperspectral imaging system. Resour Conserv Recycl, 2012, 61: 52 doi: 10.1016/j.resconrec.2012.01.007

[23]

Toğaçar M, Ergen B, Cömert Z. Waste classification using AutoEncoder network with integrated feature selection method in convolutional neural network models. Measurement, 2020, 153: 107459 doi: 10.1016/j.measurement.2019.107459

[24]

Tao J Y, Gu Y D, Hao X L, et al. Combination of hyperspectral imaging and machine learning models for fast characterization and classification of municipal solid waste. Resour Conserv Recycl, 023, 188: 106731

[25]

Bunsan S, Chen W Y, Chen H W, et al. Modeling the dioxin emission of a municipal solid waste incinerator using neural networks. Chemosphere, 2013, 92(3): 258 doi: 10.1016/j.chemosphere.2013.01.083

[26]

Norhayati I, Rashid M. Adaptive neuro-fuzzy prediction of carbon monoxide emission from a clinical waste incineration plant. Neural Comput Appl, 2018, 30(10): 3049 doi: 10.1007/s00521-017-2921-z

[27]

Tavoosi J, Mohammadzadeh A. A new recurrent radial basis function network-based model predictive control for a power plant boiler temperature control. Int J Eng, 2021, 34(3): 667

[28]

Alitasb G K, Salau A O. Multiple-input multiple-output Radial Basis Function Neural Network modeling and model predictive control of a biomass boiler. Energy Rep, 2024, 11: 442 doi: 10.1016/j.egyr.2023.11.063

[29]

Liu Z Y, Lu M, Zhang Y F, et al. Identification of heavy metal leaching patterns in municipal solid waste incineration fly ash based on an explainable machine learning approach. J Environ Manag, 2022, 317: 115387 doi: 10.1016/j.jenvman.2022.115387

[30]

Guo L S, Xu X, Wang Q, et al. Machine learning-based prediction of heavy metal immobilization rate in the solidification/stabilization of municipal solid waste incineration fly ash (MSWIFA) by geopolymers. J Hazard Mater, 2024, 467: 133682 doi: 10.1016/j.jhazmat.2024.133682

[31]

Li J S, Yao X W, Xu K L. A comprehensive model integrating BP neural network and RSM for the prediction and optimization of syngas quality. Biomass Bioenergy, 2021, 155: 106278 doi: 10.1016/j.biombioe.2021.106278

[32]

Zhao S H, Xu W J, Chen L H. The modeling and products prediction for biomass oxidative pyrolysis based on PSO-ANN method: An artificial intelligence algorithm approach. Fuel, 2022, 312: 122966 doi: 10.1016/j.fuel.2021.122966

[33]

Leng L J, Zhang W J, Liu T G, et al. Machine learning predicting wastewater properties of the aqueous phase derived from hydrothermal treatment of biomass. Bioresour Technol, 2022, 358: 127348 doi: 10.1016/j.biortech.2022.127348

[34]

Shu H Y, Lu H C, Fan H J, et al. Prediction for energy content of Taiwan municipal solid waste using multilayer perceptron neural networks. J Air Waste Manag Assoc, 2006, 56(6): 852

[35]

Taki M, Rohani A. Machine learning models for prediction the Higher Heating Value (HHV) of Municipal Solid Waste (MSW) for waste-to-energy evaluation. Case Stud Therm Eng, 2022, 31: 101823 doi: 10.1016/j.csite.2022.101823

[36]

Leng L J, Li H, Yuan X Z, et al. Bio-oil upgrading by emulsification/microemulsification: A review. Energy, 2018, 161: 214 doi: 10.1016/j.energy.2018.07.117

[37]

Aghbashlo M, Peng W X, Tabatabaei M, et al. Machine learning technology in biodiesel research: A review. Prog Energy Combust Sci, 2021, 85: 100904 doi: 10.1016/j.pecs.2021.100904

[38]

Tang Q H, Chen Y Q, Yang H P, et al. Prediction of bio-oil yield and hydrogen contents based on machine learning method: Effect of biomass compositions and pyrolysis conditions. Energy Fuels, 2020, 34(9): 11050 doi: 10.1021/acs.energyfuels.0c01893

[39]

Ma Z Y, Wang H N, Li Y L, et al. Optimized bio-oil emulsification for sustainable asphalt production: A step towards a low-carbon pavement. Constr Build Mater, 2024, 419: 135218 doi: 10.1016/j.conbuildmat.2024.135218

[40]

Liu Y, Sayed B T, Sivaraman R, et al. Novel and robust machine learning model to optimize biodiesel production from algal oil using CaO and CaO/Al2O3 as catalyst: Sustainable green energy. Environ Technol Innov, 2023, 30: 103018 doi: 10.1016/j.eti.2023.103018

[41]

Zhu X Z, Li Y N, Wang X N. Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions. Bioresour Technol, 2019, 288: 121527. doi: 10.1016/j.biortech.2019.121527

[42]

Greses S, Tomás-Pejó E, González-Fernández C. Short-chain fatty acids and hydrogen production in one single anaerobic fermentation stage using carbohydrate-rich food waste. J Clean Prod, 2021, 284: 124727 doi: 10.1016/j.jclepro.2020.124727

[43]

Dong W J, Yang Y L, Liu C, et al. Caproic acid production from anaerobic fermentation of organic waste - Pathways and microbial perspective. Renew Sustain Energy Rev, 2023, 175: 113181 doi: 10.1016/j.rser.2023.113181

[44]

Perez-Esteban N, Vinardell S, Vidal-Antich C, et al. Potential of anaerobic co-fermentation in wastewater treatments plants: A review. Sci Total Environ, 2022, 813: 152498 doi: 10.1016/j.scitotenv.2021.152498

[45]

Iglesias-Iglesias R, Kennes C, Veiga M C. Valorization of sewage sludge in co-digestion with cheese whey to produce volatile fatty acids. Waste Manage, 2020, 118: 541 doi: 10.1016/j.wasman.2020.09.002

[46]

Barik D, Murugan S. An artificial neural network and genetic algorithm optimized model for biogas production from co-digestion of seed cake of karanja and cattle dung. Waste Biomass Valorization, 2015, 6(6): 1015 doi: 10.1007/s12649-015-9392-1

[47]

Abu Qdais H, Bani Hani K, Shatnawi N. Modeling and optimization of biogas production from a waste digester using artificial neural network and genetic algorithm. Resour Conserv Recycl, 2010, 54(6): 359 doi: 10.1016/j.resconrec.2009.08.012

[48]

Wang X M, Bai X, Li Z F, et al. Evaluation of artificial neural network models for online monitoring of alkalinity in anaerobic co-digestion system. Biocheml Eng J, 2018, 140: 85 doi: 10.1016/j.bej.2018.09.010

[49]

Li H, Ke L T, Chen Z, et al. Estimating the fates of C and N in various anaerobic codigestions of manure and lignocellulosic biomass based on artificial neural networks. Energy Fuels, 2016, 30(11): 9490 doi: 10.1021/acs.energyfuels.6b01883

[50]

Alejo L, Atkinson J, Guzmán-Fierro V, et al. Effluent composition prediction of a two-stage anaerobic digestion process: Machine learning and stoichiometry techniques. Environ Sci Pollut Res Int, 2018, 25(21): 21149 doi: 10.1007/s11356-018-2224-7

[51]

Kazemi P, Bengoa C, Steyer J P, et al. Data-driven techniques for fault detection in anaerobic digestion process. Process Saf Environ Protect, 2021, 146: 905 doi: 10.1016/j.psep.2020.12.016

[52]

Xu W C, Long F, Zhao H, et al. Performance prediction of ZVI-based anaerobic digestion reactor using machine learning algorithms. Waste Manage, 2021, 121: 59 doi: 10.1016/j.wasman.2020.12.003

[53]

Vendruscolo E C G, Mesa D, Rissi D V, et al. Microbial communities network analysis of anaerobic reactors fed with bovine and swine slurry. Sci Total Environ, 2020, 742: 140314 doi: 10.1016/j.scitotenv.2020.140314

[54]

Coelho M M H, Morais N W S, Pereira E L, et al. Potential assessment and kinetic modeling of carboxylic acids production using dairy wastewater as substrate. Biochem Eng J, 2020, 156: 107502 doi: 10.1016/j.bej.2020.107502

[55]

Candry P, Radić L, Favere J, et al. Mildly acidic pH selects for chain elongation to caproic acid over alternative pathways during lactic acid fermentation. Water Res, 2020, 186: 116396 doi: 10.1016/j.watres.2020.116396

[56]

Long F, Fan J, Liu H. Prediction and optimization of medium-chain carboxylic acids production from food waste using machine learning models. Bioresour Technol, 2023, 370: 128533 doi: 10.1016/j.biortech.2022.128533

[57]

Guo X X, Liu H T, Wu S B. Humic substances developed during organic waste composting: Formation mechanisms, structural properties, and agronomic functions. Sci Total Environ, 2019, 662: 501 doi: 10.1016/j.scitotenv.2019.01.137

[58]

Déportes I, Benoit-Guyod J L, Zmirou D. Hazard to man and the environment posed by the use of urban waste compost: A review. Sci Total Environ, 1995, 172(2-3): 197 doi: 10.1016/0048-9697(95)04808-1

[59]

Sharma D, Pandey A K, Yadav K D, et al. Response surface methodology and artificial neural network modelling for enhancing maturity parameters during vermicomposting of floral waste. Bioresour Technol, 2021, 324: 124672 doi: 10.1016/j.biortech.2021.124672

[60]

Muthuveni M, Deebika S, Boopathy T, et al. I-optimal mixture design and artificial neural network for the sustainable production of vermicompost. Biomass Convers Biorefin, 2024, 14(9): 10147 doi: 10.1007/s13399-022-02962-8

[61]

Xue W, Hu X J, Wei Z, et al. A fast and easy method for predicting agricultural waste compost maturity by image-based deep learning. Bioresour Technol, 2019, 290: 121761 doi: 10.1016/j.biortech.2019.121761

[62]

Kujawa S, Mazurkiewicz J, Czekała W. Using convolutional neural networks to classify the maturity of compost based on sewage sludge and rapeseed straw. J Clean Prod, 2020, 258: 120814 doi: 10.1016/j.jclepro.2020.120814

[63]

Soto-Paz J, Alfonso-Morales W, Caicedo-Bravo E, et al. A new approach for the optimization of biowaste composting using artificial neural networks and particle swarm optimization. Waste Biomass Valorization, 2020, 11(8): 3937 doi: 10.1007/s12649-019-00716-8

[64]

Bayındır Y, Cagcag Yolcu O, Aydın Temel F, et al. Evaluation of a cascade artificial neural network for modeling and optimization of process parameters in co-composting of cattle manure and municipal solid waste. J Environ Manag, 2022, 318: 115496 doi: 10.1016/j.jenvman.2022.115496

[65]

Alavi N, Sarmadi K, Goudarzi G, et al. Attenuation of tetracyclines during chicken manure and bagasse co-composting: Degradation, kinetics, and artificial neural network modeling. J Environ Manag, 2019, 231: 1203 doi: 10.1016/j.jenvman.2018.11.003

[66]

Yamawaki R, Tei A, Ito K, et al. Decomposition factor analysis based on virtual experiments throughout Bayesian optimization for compost-degradable polymers. Appl Sci, 2021, 11(6): 2820 doi: 10.3390/app11062820

[67]

Kim S, Lee M H, Wiwasuku T, et al. Human sensor-inspired supervised machine learning of smartphone-based paper microfluidic analysis for bacterial species classification. Biosens Bioelectron, 2021, 188: 113335 doi: 10.1016/j.bios.2021.113335

[68]

Galan E A, Zhao H R, Wang X K, et al. Intelligent microfluidics: The convergence of machine learning and microfluidics in materials science and biomedicine. Matter, 2020, 3(6): 1893 doi: 10.1016/j.matt.2020.08.034

[69]

Li R, Xu A K, Zhao Y, et al. Genetic algorithm (GA) - Artificial neural network (ANN) modeling for the emission rates of toxic volatile organic compounds (VOCs) emitted from landfill working surface. J Environ Manag, 2022, 305: 114433 doi: 10.1016/j.jenvman.2022.114433

[70]

Ramachandran S, Jayalal M L, Vasudevan M, et al. Combining machine learning techniques and genetic algorithm for predicting run times of high performance computing jobs. Appl Soft Comput, 2024, 165: 112053 doi: 10.1016/j.asoc.2024.112053

[71]

Wang Z N, Wu F X, Hao N, et al. The combined machine learning model SMOTER-GA-RF for methane yield prediction during anaerobic digestion of straw lignocellulose based on random forest regression. J Clean Prod, 2024, 466: 142909 doi: 10.1016/j.jclepro.2024.142909

[72]

Nair V V, Dhar H, Kumar S, et al. Artificial neural network based modeling to evaluate methane yield from biogas in a laboratory-scale anaerobic bioreactor. Bioresour Technol, 2016, 217: 90 doi: 10.1016/j.biortech.2016.03.046

[73]

Beltramo T, Hitzmann B. Evaluation of the linear and non-linear prediction models optimized with metaheuristics: Application to anaerobic digestion processes. Eng Agric Environ Food, 2019, 12(4): 397

[74]

Chakraborty S, Das B S, Nasim Ali M, et al. Rapid estimation of compost enzymatic activity by spectral analysis method combined with machine learning. Waste Manage, 2014, 34(3): 623 doi: 10.1016/j.wasman.2013.12.010

[75]

Olden J D, Jackson D A. Illuminating the “black box”: A randomization approach for understanding variable contributions in artificial neural networks. Ecol Model, 2002, 154(1-2): 135 doi: 10.1016/S0304-3800(02)00064-9