Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania

Neural network time series (NNTS) tool was used to predict municipal solid waste composition in Iasi, Romania. The nonlinear input output (NIO) time series model and nonlinear autoregressive model with external (exogenous) input (NARX) included in this tool were selected. The coefficient of determi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Cristina Ghinea, Petronela Cozma, Maria Gavrilescu
Formato:	article
Lenguaje:	EN
Publicado:	Vilnius Gediminas Technical University 2021
Materias:	artificial neural network environmental processes modeling population solid waste waste composition waste management technologies Environmental engineering TA170-171
Acceso en línea:	https://doaj.org/article/8380db33f9094a06bd3485c387388e34
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8380db33f9094a06bd3485c387388e34
record_format	dspace
spelling	oai:doaj.org-article:8380db33f9094a06bd3485c387388e342021-11-11T13:50:52ZArtificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania10.3846/jeelm.2021.155531648-68971822-4199https://doaj.org/article/8380db33f9094a06bd3485c387388e342021-11-01T00:00:00Zhttps://journals.vgtu.lt/index.php/JEELM/article/view/15553https://doaj.org/toc/1648-6897https://doaj.org/toc/1822-4199 Neural network time series (NNTS) tool was used to predict municipal solid waste composition in Iasi, Romania. The nonlinear input output (NIO) time series model and nonlinear autoregressive model with external (exogenous) input (NARX) included in this tool were selected. The coefficient of determination (R2) and root mean square error (RMSE) were chosen for evaluation. By applying NIO, the optimum model is 4-11-6 artificial neural network (ANN, R2 = 0.929) in the case of testing as for the validation, with all 0.849 and 0.885, respectively. Applying NARX, the suitable model became 4-13-6 ANN model, with R2 = 0.999 for training, 0.879 for testing, and 0.931, respectively 0.944 for validation and all. The resulted RMSE is zero for training and 0.0109 for validation in the case of this model which had 4 inputs, 13 neurons and 6 outputs. The four input variables were: number of residents, population aged 15–59 years, urban life expectancy, total municipal solid waste (ton/year). The suitable ANN model revealed the lowest root mean square error and the highest coefficient of determination. Results indicate that NNTS tool is a complex instrument, NARX is more accurate than NIO model, and can be used and applied easily. Cristina GhineaPetronela CozmaMaria GavrilescuVilnius Gediminas Technical Universityarticleartificial neural networkenvironmental processes modelingpopulationsolid wastewaste compositionwaste management technologiesEnvironmental engineeringTA170-171ENJournal of Environmental Engineering and Landscape Management, Vol 29, Iss 3 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial neural network environmental processes modeling population solid waste waste composition waste management technologies Environmental engineering TA170-171
spellingShingle	artificial neural network environmental processes modeling population solid waste waste composition waste management technologies Environmental engineering TA170-171 Cristina Ghinea Petronela Cozma Maria Gavrilescu Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
description	Neural network time series (NNTS) tool was used to predict municipal solid waste composition in Iasi, Romania. The nonlinear input output (NIO) time series model and nonlinear autoregressive model with external (exogenous) input (NARX) included in this tool were selected. The coefficient of determination (R2) and root mean square error (RMSE) were chosen for evaluation. By applying NIO, the optimum model is 4-11-6 artificial neural network (ANN, R2 = 0.929) in the case of testing as for the validation, with all 0.849 and 0.885, respectively. Applying NARX, the suitable model became 4-13-6 ANN model, with R2 = 0.999 for training, 0.879 for testing, and 0.931, respectively 0.944 for validation and all. The resulted RMSE is zero for training and 0.0109 for validation in the case of this model which had 4 inputs, 13 neurons and 6 outputs. The four input variables were: number of residents, population aged 15–59 years, urban life expectancy, total municipal solid waste (ton/year). The suitable ANN model revealed the lowest root mean square error and the highest coefficient of determination. Results indicate that NNTS tool is a complex instrument, NARX is more accurate than NIO model, and can be used and applied easily.
format	article
author	Cristina Ghinea Petronela Cozma Maria Gavrilescu
author_facet	Cristina Ghinea Petronela Cozma Maria Gavrilescu
author_sort	Cristina Ghinea
title	Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
title_short	Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
title_full	Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
title_fullStr	Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
title_full_unstemmed	Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania
title_sort	artificial neural network applied in forecasting the composition of municipal solid waste in iasi, romania
publisher	Vilnius Gediminas Technical University
publishDate	2021
url	https://doaj.org/article/8380db33f9094a06bd3485c387388e34
work_keys_str_mv	AT cristinaghinea artificialneuralnetworkappliedinforecastingthecompositionofmunicipalsolidwasteiniasiromania AT petronelacozma artificialneuralnetworkappliedinforecastingthecompositionofmunicipalsolidwasteiniasiromania AT mariagavrilescu artificialneuralnetworkappliedinforecastingthecompositionofmunicipalsolidwasteiniasiromania
_version_	1718439051937185792

Artificial neural network applied in forecasting the composition of municipal solid waste in Iasi, Romania

Ejemplares similares