Abstract Municipal solid waste (MSW) is a result of human activities. Accurate forecasting of MSW generation is crucial for sustainable management systems and planning. MSW is considered as an important resource for renewable energy development plans of cities. Due to the uncertainties and unavailability of sufficient MSW generation information in developing countries, including the difference of local conditions, various modeling methods were developed to predict MSW generation. The objectives of this paper are to identify influential variables that affect the amount of MSW generation and to predict the future MSW in Bangkok by employing linear and nonlinear models. The major factors of MSW in these two models are accounted by number of residents, people aged 15-59 years, number of households, income per household, and number of tourists. In the linear model, principal component analysis is capable to reduce multi-collinearity factors. This leads to the improvement of the performance of regression by a stepwise algorithm with R2=0.86. In the nonlinear model, artificial neural network (ANN) is conducted by designing an appropriate network architecture in the Matlab tool. This approach with one neuron demand in hidden layer exhibits the fitting value of R2=0.96, which is better than linear regression model. In these regards, the designed network in ANN is possibly stored for further analysis under the same conditions for high percentage of accuracy. All the results in this research can be utilized as part of solid plans for renewable energy development and eco-environmental recycle industry which require MSW as raw material.
[1]
Azin Khosravi,et al.
The Iranian Vital Horoscope; Appropriate Tool to Collect Health Statistics in Rural Areas
,
2009
.
[2]
Silvia Curteanu,et al.
Forecasting municipal solid waste generation using prognostic tools and regression analysis.
,
2016,
Journal of environmental management.
[3]
Tumpa Hazra,et al.
A Review on Prediction of Municipal Solid Waste Generation Models
,
2016
.
[4]
Daniel Hoornweg,et al.
What a waste? : a global review of solid waste management
,
2012
.
[5]
S. Probert,et al.
Municipal solid waste: a prediction methodology for the generation rate and composition in the European Union countries and the United States of America
,
1998
.
[6]
E. Ordonez Ponce.
A model for assessing waste generation factors and forecasting waste generation using artificial neural networks : a case study of Chile
,
2004
.
[7]
Thanwadee Chinda,et al.
THE STUDY OF LANDFILL SITUATIONS IN THAILAND
,
2012
.
[8]
Viktor Pocajt,et al.
The forecasting of municipal waste generation using artificial neural networks and sustainability indicators
,
2012,
Sustainability Science.
[9]
Thaniya Kaosol,et al.
Sustainable Solutions for Municipal Solid Waste Management in Thailand
,
2009
.