Prediction of municipal solid waste generation using nonlinear autoregressive network

Abstract

Most of the developing countries have solid waste management problems. Solid waste strategic planning requires accurate prediction of the quality and quantity of the generated waste. In developing countries, such as Malaysia, the solid waste generation rate is increasing rapidly, due to population growth and new consumption trends that characterize society. This paper proposes an artificial neural network (ANN) approach using feedforward nonlinear autoregressive network with exogenous inputs (NARX) to predict annual solid waste generation in relation to demographic and economic variables like population number, gross domestic product, electricity demand per capita and employment and unemployment numbers. In addition, variable selection procedures are also developed to select a significant explanatory variable. The model evaluation was performed using coefficient of determination (R(2)) and mean square error (MSE). The optimum model that produced the lowest testing MSE (2.46) and the highest R(2) (0.97) had three inputs (gross domestic product, population and employment), eight neurons and one lag in the hidden layer, and used Fletcher-Powell's conjugate gradient as the training algorithm.

Prediction of Municipal Waste Generation in Poland Using Neural Network Modeling

“…In a similar study on predicting the amount of generated municipal waste, Younes et al selected the best model with MSE = 2.46 and R = 0.97, with gross domestic product, population and employment as the input data [30].…”

“…Typically, in the majority of models, the ANN will consist of three layers: the input layer that provides input to the model; the hidden layer where all the computational simulations on the input data occur; and the output layer that produces the outcome. A neural network can be taught through training, which serves to establish the relationships between a set of independent and dependent input variables, consequently constructing a complex non-linear system [27][28][29][30][31]. It is precisely the capability of ANN models to predict the non-linear systems and the ease of implementation that have contributed to the growing interest in their application in solving the waste management problems, e.g., with respect to determining various relevant characteristics, such as the amount or the type of waste and their correlation with socioeconomic factors [27,29].…”

Estimation of municipal waste generation of Turkey using socio-economic indicators by Bayesian optimization tuned Gaussian process regression

“…These models range from traditional to advanced ones such as artificial neural network, grey model, multiple linear regression, principal component analysis, support vector regression and etc. (Abbasi et al, 2019; Abbasi and El Hanandeh, 2016; Antanasijević et al, 2013; Azadi and Karimi-Jashni, 2016; Chhay et al, 2018; Singh and Satija, 2018; Sun and Chungpaibulpatana, 2017; Younes et al, 2015). However, these models have several weaknesses such as over-fitting problems, need for big data, slow convergence speed, and poor generalization performance.…”

Avaliação De Impacto Ambiental De Pisciculturas No Rio São Francisco

“…Normalmente, possui três camadas denominadas entrada (input), saída (output) e camada oculta (hidden layer), sendo a quantidade de neurônios nas camadas de entrada e saída iguais à respectivamente à quantidade de variáveis de entrada e saída do conjunto de dados. (YOUNES et al, 2015).…”