Forecasting the electronic waste quantity with a decomposition-ensemble approach.

Waste electrical and electronic equipment (viz., WEEE or e-waste) is the fastest-growing type of hazardous solid waste in the worldwide. The accurate prediction of the amount of e-waste might help improve the efficiency of e-waste disposal. In this study, a novel decomposition-ensemble-based hybrid forecasting methodology that integrates variational mode decomposition (VMD), exponential smoothing model (ESM), and grey modeling (GM) methods (named VMD-ESM-GM) is proposed for e-waste quantity prediction. For verification purposes, sample data from Washington State, US, and UK Environment Agency are analyzed. Compared to benchmark models, the proposed VMD-ESM-GM methodology not only obtains a satisfactory prediction result for e-waste data but also predicts the future fluctuation trend of e-waste. These results indicate that the proposed VMD-ESM-GM methodology based on the decomposition-ensemble principle is a suitable model for the prediction of the e-waste quantity and could help decision-makers develop both e-waste recycling plans and circular economy plans.

[1]  Prasanta Kumar Dey,et al.  Investigating the factors that affect the time of maximum rejection rate of e-waste using survival analysis , 2017, Comput. Ind. Eng..

[2]  Bo Zeng,et al.  A new-structure grey Verhulst model: Development and performance comparison , 2020 .

[3]  Yuzhe Qin,et al.  Emission reduction benefits and efficiency of e-waste recycling in China. , 2019, Waste management.

[4]  James W. Taylor.  Exponential smoothing with a damped multiplicative trend , 2003 .

[5]  Shaolong Sun,et al.  A novel hybrid decomposition-ensemble model based on VMD and HGWO for container throughput forecasting , 2018 .

[6]  Weihua Gui,et al.  Non-ferrous metals price forecasting based on variational mode decomposition and LSTM network , 2020, Knowl. Based Syst..

[7]  Callie W. Babbitt,et al.  Forecasting electronic waste flows for effective circular economy planning , 2019 .

[8]  Kelsea A. Schumacher,et al.  Towards comprehensive e-waste legislation in the United States: Design considerations based on quantitative and qualitative assessments , 2019, Resources, Conservation and Recycling.

[9]  Emmanouil Stiakakis,et al.  Estimation of computer waste quantities using forecasting techniques , 2016 .

[10]  Tasbirul Islam,et al.  Reshaping WEEE management in Australia: An investigation on the untapped WEEE products , 2020 .

[11]  Jinhui Li,et al.  Circular economy and electronic waste , 2019, Nature Electronics.

[12]  Valeria Ibáñez-Forés,et al.  A survey on consumers' attitude towards storing and end of life strategies of small information and communication technology devices in Spain. , 2018, Waste management.

[13]  N. Huda,et al.  E-waste in Australia: Generation estimation and untapped material recovery and revenue potential , 2019, Journal of Cleaner Production.

[14]  Surendra M. Gupta,et al.  Estimation of electronic waste using optimized multivariate grey models. , 2019, Waste management.

[15]  Dominique Zosso,et al.  Variational Mode Decomposition , 2014, IEEE Transactions on Signal Processing.

[16]  Maisa Mendonça Silva,et al.  A time series model for estimating the generation of lead acid battery scrap , 2016, Clean Technologies and Environmental Policy.

[17]  Rodrigo Fernandes de Mello,et al.  Decomposing time series into deterministic and stochastic influences: A survey , 2019, Digit. Signal Process..

[18]  K. Petridis,et al.  Global e-waste trade network analysis , 2020 .

[19]  Jinchao Li,et al.  Monthly crude oil spot price forecasting using variational mode decomposition , 2019, Energy Economics.

[20]  Xianlai Zeng,et al.  Uncovering the Recycling Potential of "New" WEEE in China. , 2016, Environmental science & technology.

[21]  Zheng-Xin Wang,et al.  Modelling the nonlinear relationship between CO2 emissions and economic growth using a PSO algorithm-based grey Verhulst model , 2019, Journal of Cleaner Production.

[22]  Yan Yang,et al.  Logistic model-based forecast of sales and generation of obsolete computers in the U.S. , 2009 .

[23]  Jeffrey Forrest,et al.  New progress of Grey System Theory in the new millennium , 2016, Grey Syst. Theory Appl..

[24]  Huayou Chen,et al.  A novel decomposition-ensemble approach to crude oil price forecasting with evolution clustering and combined model , 2019, International Journal of Machine Learning and Cybernetics.

[25]  Jianxin Yang,et al.  Estimation of retired mobile phones generation in China: A comparative study on methodology. , 2015, Waste management.

[26]  Shouyang Wang,et al.  A new multiscale decomposition ensemble approach for forecasting exchange rates , 2019, Economic Modelling.

[27]  K. Lai,et al.  Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm , 2008 .

[28]  Ling Tang,et al.  Forecasting Patient Visits to Hospitals using a WD&ANN-based Decomposition and Ensemble Model , 2017 .

[29]  Yanhui Chen,et al.  Multi-step-ahead crude oil price forecasting using a hybrid grey wave model , 2018, Physica A: Statistical Mechanics and its Applications.

[30]  G. Jiang,et al.  E-waste Recycling in China: A Challenging Field. , 2018, Environmental science & technology.

[31]  Christine Cole,et al.  An assessment of achievements of the WEEE Directive in promoting movement up the waste hierarchy: experiences in the UK. , 2019, Waste management.

[32]  Yanhui Chen,et al.  A novel grey wave forecasting method for predicting metal prices , 2016 .

[33]  Bo Liu,et al.  Improved particle swarm optimization combined with chaos , 2005 .

[34]  E. Yamasue,et al.  Estimation of the metal flow of WEEE in Vietnam considering lifespan transition , 2020 .

[35]  Zhao Min,et al.  Prediction and Analysis of WEEE in China Based on the Gray Model , 2016 .

[36]  Qiang Ji,et al.  Forecasting China's natural gas demand based on optimised nonlinear grey models , 2017 .

[37]  Zhong-kai Feng,et al.  A hybrid short-term load forecasting model based on variational mode decomposition and long short-term memory networks considering relevant factors with Bayesian optimization algorithm , 2019, Applied Energy.