Impacts of nested forward validation techniques on machine learning and regression waste disposal time series models |
| |
| Institution: | 1. Environmental Systems Engineering, Faculty of Engineering and Applied Science, University of Regina, 3737 Wascana Parkway, Saskatchewan S4S 0A2, Canada;2. Environmental Engineering Program, School of Engineering, University of Northern British Columbia (UNBC), 3333 University Way, Prince George V2N 4Z9, British Columbia, Canada;1. College of Energy and Power Engineering, Lanzhou University of Technology, Lanzhou 730050, China;2. Key Laboratory of Ecohydrology of Inland River Basin, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou, Gansu 730000, China;3. Gansu Provincial Soil and Water Conservation Research Institute, Lanzhou 730000, China;4. State Key Laboratory of Cryospheric Science, Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, China;1. Institute of Forest Ecology, Slovak Academy of Sciences, ?. ?túra 2, 960 01 Zvolen, Slovakia;2. Institute of Informatics, Slovak Academy of Sciences, Dúbravská cesta 9, 845 07 Bratislava, Slovakia;3. Faculty of Ecology and Environmental Sciences, Technical University in Zvolen, T. G. Masaryka 24, 960 01 Zvolen, Slovakia |
| |
| Abstract: | Dataset partitioning and validation techniques are required in all artificial neural network based waste models. However, there is currently no consensual approach on the validation techniques. This study examines the effects of three time series nested forward validation techniques (rolling origin - RO, rolling window - RW, and growing window - GW) on total municipal waste disposal estimates using recurrent neural network (RNN) models, and benchmarks model performance with respect to multiple linear regression (MLR) models. Validation selection techniques appear important to waste disposal time series model construction and evaluation. Sample size is found as an important factor on model accuracy for both RNN and MLR models. Better performance in Trial RW4 is observed, probably due to a more consistent testing set in 2019. Overall, the MAPE of the waste disposal models ranging from 10.4% to 12.7%. Both GW and RO validation techniques appear appropriate for RNN waste models. However, MLR waste models are more sensitive to the dataset characteristics, and RO validation technique appears more suitable to MLR models. It is found that data characteristics are more important than training period duration. It is recommended data set normality and skewness be examined for waste disposal modeling. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
