Hybrid model for the prediction of municipal solid waste generation in Hangzhou, China
Accurate prediction of municipal solid waste (MSW) generation is necessary for choosing appropriate waste treatment methods and for planning the distribution of disposal facilities. In this study, a hybrid model was established to forecast MSW generation through the combination of the ridge regressi...
| Publié dans: | Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA. - 1991. - 37(2019), 8 vom: 15. Aug., Seite 781-792 |
|---|---|
| Auteur principal: | |
| Autres auteurs: | , |
| Format: | Article en ligne |
| Langue: | English |
| Publié: |
2019
|
| Accès à la collection: | Waste management & research : the journal of the International Solid Wastes and Public Cleansing Association, ISWA |
| Sujets: | Journal Article GM(1,N) model Municipal solid waste hybrid model influencing factor prediction ridge regression model Solid Waste |
| Résumé: | Accurate prediction of municipal solid waste (MSW) generation is necessary for choosing appropriate waste treatment methods and for planning the distribution of disposal facilities. In this study, a hybrid model was established to forecast MSW generation through the combination of the ridge regression and GM(1,N) models. The hybrid model is multivariate and involves total urban population, total retail sales of social consumer goods, per capita consumption expenditure of urban areas, tourism, and college graduation. Compared with the constituent models alone, the hybrid model yields higher accuracy, with a mean absolute percentage error (MAPE) of only 2.59%. Through weight allocation and optimal treatment of residuals, the hybrid model also balances the growth trends of the individual models, making the prediction curve smoother. The model coefficients and correlation analysis show that population, economics, and educational factors are influential for waste generation. MSW output in Hangzhou will gradually increase in the future, and is expected to reach 5.12 million tons in 2021. Results can help decision makers to develop the measures and policies of waste management in the future |
|---|---|
| Description: | Date Completed 09.09.2019 Date Revised 09.09.2019 published: Print-Electronic Citation Status MEDLINE |
| ISSN: | 1096-3669 |
| DOI: | 10.1177/0734242X19855434 |