Machine learning for sustainable reutilization of waste materials as energy sources – a comprehensive review

ABSTRACTThis work reviews Machine Learning applications in the sustainable utilization of waste materials as energy source so that analysis of the past works exposed the lack of reviewing study. To solve it, the origin of waste biomass raw materials is explained, and the application of Machine Learning in this section is scrutinized. After analysis of numerous papers, it is concluded that Machine Learning and Deep Learning are widely utilized in waste biomass production areas to enhance the quality and quantity of production, improve the predictions, diminish the losses, as well as increase storage and transformation conditions. The positive effects and application with the utilized algorithms and other effective information are collected in this work for the first time. According to the statistical analysis, in 20% out of the studies conducted about the application of Machine Learning and Deep Learning in waste biomass raw materials, Artificial Neural Network (ANN) algorithm has been applied. Afterward, the Super Vector Machine (SVM) and Random Forest (RF) are the second and third most-utilized algorithms applied in 15% and 14% of studies. Meanwhile, 27% of studies focused on the applications of Machine Learning and Deep Learning in the Forest wastes.KEYWORDS: Machine LearningDeep learningwaste materialssustainable production, energy source Abbreviations Abbreviation=MeaningML=Machine LearningDL=Deep LearningANN=Artificial Neural NetworkIoT=Internet of ThingsSVM=Super Vector MachineNB=Naive BayesKNN=K-nearest NeighborDT=Decision TreeRF=Random ForestANFIS=Adaptive Network Fuzzy Inference SystemXGBoost=Extreme Gradient BoostingGAM=Generalized Additive ModelRNN=Recurrent Neural NetworkMLR=Multiple Linear RegressionRBNN=Radial-basis Neural NetworkSMOR=Sequential Minimal Optimization RegressionLDA=Linear Discriminant AnalysisFRBS=Fuzzy Rule-based SystemsDBN=Deep Belief NetworkCL=Classification TreesC=CarbonO=OxygenS=SulphurA=AshK=PotassiumP=PhosphorusCa=CalciumZn=ZinkCO2=Carbon DioxideNIR=Near InfraredRBF=Radial Basis FunctionET=Extra TreesSPA=Successive Projection AlgorithmLRM=Linear Regression ModelCRBM=Conditional Restricted Boltzmann MachineGA=Genetic AlgorithmRO=Reverse Osmosist-SNE=t-Distributed Stochastic Neighbor EmbeddingDBSCAN=Density-Based Spatial Clustering of Applications with NoiseGAN=Generative Adversial NetworkGRU=Gated Recurrent UnitsSMR=Stepwise Multiple RegressionLSTM=Long Short Term MemoryCNN=Convolutional Neural NetworkMLP=Multilayer PerceptronFPN Mask=Feature Pyramid Network MaskGP=Gaussian ProcessDNN=Deep Neural NetworkPR=Polynomial RegressionGBDT=Gradient Boosting Decision TreeAdaBoost=Adaptive boostingPLSDA=Partial Least Square Discriminant AnalysisRCCN=Region-based CNNPGM=Probabilistic Graphical ModelsGPR=Gaussian Processes RegressionBNN=Bayesian Neural NetworkLR=Logistics RegressionPLS-DA=Partial Least Squares Discriminant AnalysisBRT=Boosted Regression TreeGMMs=Gaussian Mixture ModelsLSSVR=Least-Squares Support Vector RegressionGBM=Generalized Boosted ModelH=HudrogenN=NitrogenCl=chlorinePb=Lead (Plumbum)Na=SodiumMg=MagnesiumSi=SilicaHHV=Higher Heating ValuePMF=Positive Matrix FactorizationPLS=Partial Least SquaresKRR=Kernel Ridge RegressionMARS=Multivariate Adaptive Regression SplinesCARS=Competitive Adaptive Reweighted SamplingSVR=Supper Vector RegressionPCA=Principal Component AnalysisDO=Dissolved OxygenNF=Nano-filtrationLSA=Latent Semantic AnalysisGNN=Graph Neural NetworksGAT=Graph Attention NetworkLRLS=Kernel-based Regularized Least SquaresGLM=Generalized Linear ModelDisclosure statementNo potential conflict of interest was reported by the author(s).