Application of artificial intelligence neural network modeling to predict the generation of domestic, commercial and construction wastes

Abstract

Reliable prediction of municipal solid waste (MSW) generation rates is a significant element of planning and implementation of sustainable solid waste management strategies. In this study, the multi-layer perceptron artificial neural network (MLP-ANN) is applied to verify the prediction of annual generation rates of domestic, commercial and construction and demolition (C&D) wastes from the year 1997 to 2016 in Askar Landfill site in the Kingdom of Bahrain. The proposed robust predictive models incorporated selected explanatory variables to reflect the influence of social, demographical, economic, geographical and touristic factors upon waste generation rates (WGRs). The Mean Squared Error (MSE) and coefficient of determination ( R2) are used as performance indicators to evaluate effectiveness of the developed models. MLP-ANN models exhibited strong accuracy in predictions with high R2 and low MSE values. The R2 values for domestic, commercial and C&D wastes are 0.95, 0.99 and 0.91, respectively. Our results show that the developed MLP-ANN models are effective for the prediction of WGRs from different sources and could be considered as a cost-effective approach for planning integrated MSW management systems.

The use of a recurrent neural network model with separated time-series and lagged daily inputs for waste disposal rates modeling during COVID-19

“…Values close to unity suggest perfect agreement. Both R and IA are common indicators of ANN-based model performance ( Adamović et al, 2018 , Radojević et al, 2018 , Coskuner et al, 2020 , Fallah et al, 2020 ). These indicators are computed using the following equations: Where: n: Number of data points…”

Development of a Prediction Model for Demolition Waste Generation Using a Random Forest Algorithm Based on Small DataSets

“…However, recently, artificial intelligence (AI) technologies have been increasingly employed to accurately predict C&D waste generation [ 15 ]. AI algorithms are regarded as state-of-the-art models for reliable prediction of a waste generation because of their unique features (i.e., data input, learning, and prediction) [ 16 ].…”

Data mining and knowledge discovery in databases for urban solid waste management: A scientific literature review

“…The Pearson correlation coefficient was the method most used by the authors. In this regard, the aspects associated with solid waste in publications were: total number of inhabitants (Pérez-López et al, 2016); population density (Colvero et al, 2019;Coskuner et al, 2020); average minimum and maximum temperature (Kumar et al, 2016); precipitation rate (Vu et al, 2019b); per capita income; schooling; unemployment rate (Ceylan, 2020); waste category; residence size (Abbasi et al, 2019); amount collected by category of waste (Kontokosta et al, 2018) and emissions of gases (Dimishkovsk et al, 2019) into the atmosphere. Among these, we can highlight that the correlation coefficient between the generation of waste, per capita income (Vu et al, 2019b) and educational level (Kumar and Samadder, 2017) showed a strong and positive connection, showing a link between the socioeconomic profile and level of development with the generation of solid waste.…”

“…Within the scope of this review, the approaches adopted by researchers to estimate and predict generation took place as follows: monthly generation of municipal solid waste (MSW) (Abbasi and El Hanandeh, 2016;Abbasi et al, 2019;Ahmmed et al, 2020;Ali and Ahmad, 2019;Araiza-Aguilar et al, 2020;Azarmi et al, 2018), annual MSW generation (Coskuner et al, 2020), seasonal generation of MSW (Ahmad and Kim (2020)), annual national generation (Ceylan, 2020), national generation of hazardous waste (Adamović et al, 2018), monthly generation of hospital waste (Çetinkaya et al, 2020;), annual generation of hospital waste (Ceylan et al, 2020), generation of construction waste (Kupusamy et al, 2019;Li et al, 2016;Ram and Kalidindi, 2017), annual generation (kg/inhabitant/year) of collected packaging waste separately (Oliveira et al, 2019), generation of waste by type, biodegradable and non-biodegradable (Kumar and Samadder, 2017) and generation of recyclable waste (Vu et al, 2019a(Vu et al, , 2019b.…”