Longterm forecasting of solid waste generation by the artificial neural networks

Abdoli, Mohammad Ali; Nezhad, Maliheh Falah; Sede, Reza Salehi; Behboudian, Sadegh

doi:10.1002/ep.10591

Cited by 82 publications

(35 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data‐driven models without need of complete perception of MSWG process have high ability to model waste generation changes over times. Artificial neural network (ANN) and Adaptive Neuro‐Fuzzy Inference System are such artificial intelligence models that have been used for prediction of MSWG . These models have a good ability of MSWG prediction but the innate disadvantage such as over‐fitting training, local minimum, difficulty in determination of network architecture, and poor generalizing performance remain unsolved and limit the application of the ANN approach into practice.…”

Section: Introductionmentioning

confidence: 99%

Results uncertainty of support vector machine and hybrid of wavelet transform‐support vector machine models for solid waste generation forecasting

Abbasi

Abduli

Omidvar

et al. 2013

Env Prog and Sustain Energy

View full text Add to dashboard Cite

The prediction of municipal solid waste generation (MSWG) plays an important role in a solid waste management system. However, achieving the anticipated prediction accuracy with regard to the nonhomogeneous nature of waste and effect of various and out of control factors on MSWG is quite challenging. In this article, support vector machine (SVM), one of the artificial intelligence techniques, and hybrid of wavelet transform (WT) and support vector machine (WT‐SVM) are used to predict weekly time series of MSWG in Tehran and Mashhad cites during the period of January 2006–December 2011. To improve the performance of SVM model, considering the influence of noise and the disadvantages of traditional noise eliminating technologies, the wavelet denoising method is applied to reduce or eliminate the noise in MSWG time series. Since Data‐driven models such as SVM involve potential of uncertainty that is difficult to quantify, uncertainty determination is one of important gaps observed in SVM results analysis. Therefore, Monte Carlo method was used to analyze uncertainty of the model results. Results showed both models could precisely predict MSWG in Tehran and Mashhad cites. However, the preprocessing of input variables by WT led to develop a more accurate model for prediction of weekly MSWG in both cities. The uncertainty analysis also verified that the WT‐SVM model had more robustness than SVM and had a lower sensitivity to change of input variables. © 2013 American Institute of Chemical Engineers Environ Prog, 33: 220–228, 2014

show abstract

Section: Introductionmentioning

confidence: 99%

Results uncertainty of support vector machine and hybrid of wavelet transform‐support vector machine models for solid waste generation forecasting

Abbasi

Abduli

Omidvar

et al. 2013

Env Prog and Sustain Energy

View full text Add to dashboard Cite

show abstract

“…We found that our model captured similarly slightly higher amount of variability in MSW generation. A monthly model for Mashhad city, Iran explained 70% of variability in MSW generation, while a preprocessed ANN model explained 73% [33,34]. A recent seasonal model explained 73% of MSW generation variability [24].…”

Section: Resultsmentioning

confidence: 99%

“…Since socioeconomic data have been associated with MSW generation by previous researches, GDP, unemployment rate, and income were chosen as socioeconomic indicators. The correlation between MSW and meteorological condition has also been addressed in some studies . Maximum temperature and rain were also considered as meteorological indicators.…”

Section: Adaptive Neuro‐fuzzy Inference Systemmentioning

confidence: 99%

Monthly and seasonal modeling of municipal waste generation using radial basis function neural network

Abbasi

Rastgoo

Nakisa

2018

Env Prog and Sustain Energy

View full text Add to dashboard Cite

Accurate modeling of municipal solid waste (MSW) generation is vital as a reliable support for decision‐making processes ensuring the success of the future development and management of wastes. The present study aims to forecast monthly and seasonal MSW generation using radial basis function (RBF) neural network and assess the effect of the gender of educated people with a combination of meteorological, socioeconomic, and demographic variables on waste generation. The study was implemented on data obtained from a megacity for the period of 1991–2013. Cross validation technique was employed to evaluate modeling performance. Performance of the RBF model were also compared with adaptive neuro‐fuzzy inference system (ANFIS) and artificial neural network (ANN) models. The results proved that the number of educated women was highly associated with MSW generation while the number of educated men was not a significant factor. Modeling outputs demonstrated that the RBF neural network model could successfully predict both monthly and seasonal variations of MSW generation. Compared to ANFIS and ANN, RBF was the best‐performing model for monthly and seasonal forecasting of MSW generation. The results suggested that soft computing methods like RBF improve the estimate of MSW generation in metropolises. Hence, RBF network can be applied for forecasting and modeling MSW generation on a national scale. © 2018 American Institute of Chemical Engineers Environ Prog, 38:e13033, 2019

show abstract

“…The independent variables used for modelling of ANN1/1 and ANN1/2 models were year (2013-2016) and month (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12), while the output variables were the socioeconomic (ANN1/1) and waste management (ANN1/2) variables for the period from 2013 to 2016. ANN1/1 model was also used to predict the socio-economic indicators in 2017, according to a model developed using the data for a period between 2013 and 2016.…”

Section: Discussionmentioning

confidence: 99%

Predictive model for municipal waste generation using artificial neural networks—Case study City of Zagreb, Croatia

Ribić¹,

Pezo

Sinčić³

et al. 2019

Int J Energy Res

View full text Add to dashboard Cite

Summary The European Union's environmental legislation related to environmental protection, already implemented in the national legislation of the Republic of Croatia, aims to introduce a system of integrated and sustainable waste management. Within such a system, it is of utmost importance to have a better estimate of the amount of municipal waste generated, which directly influences future planning in the waste management sector. The aim of this research was to develop and optimize models for the estimation of generated municipal waste by application of methodology using neural network models, and taking into account the socio‐economic impact as well as the inputs regarding the actual waste management trends. In this paper, an artificial neural network models were used to predict the municipal waste generation in Zagreb, Croatia. The standardized socio‐economic and waste management variables were chosen to encompass 2013 to 2016 period. Moreover, the test prediction of the observed data was performed for 2017. Developed models sufficiently predicted the quantities of different municipal waste fractions and in that sense can contribute to better planning of upcoming waste management systems that will be sustainable and in order to meet the European Union commitments.

show abstract

Longterm forecasting of solid waste generation by the artificial neural networks

Cited by 82 publications

References 41 publications

Results uncertainty of support vector machine and hybrid of wavelet transform‐support vector machine models for solid waste generation forecasting

Results uncertainty of support vector machine and hybrid of wavelet transform‐support vector machine models for solid waste generation forecasting

Monthly and seasonal modeling of municipal waste generation using radial basis function neural network

Predictive model for municipal waste generation using artificial neural networks—Case study City of Zagreb, Croatia

Contact Info

Product

Resources

About