Prediction of Industrial Solid Waste with ANFIS Model and its comparison with ANN Model- A Case Study of Durg-Bhilai Twin City India

This paper is an attempt to estimate the quantity of Industrial solid waste (ISW) that can be generated in the Durg-Bhilai Twin city (DBTC), C.G, India from 2010 to 2026. The prediction of Industrial solid waste generation plays an important role in solid waste management. Yet achieving the anticipated prediction accuracy with regard to the generation trends facing many fast growing regions is quite challenging. In addition to the population growth and migration, underlying economic development, household size, employment changes, and the impact of waste recycling would influences the solid waste generation interactively. The development of a reliable model for predicting the aggregate impact of economic trends, population changes, and recycling impact on solid waste generation would be a useful advance in the practice of solid waste management [7]. The four input variables considered in the ANFIS model to predict ISW in the study area are Population of Durg-Bhilai Twin City (DBTC), ISW generated at DBTC, Percentage of urban population of the nation and GDP per capita of the nation. ANFIS is used in function approximation, time series prediction, and control [1] [2] [4]. In the absence of the adequate past data on waste generation rates, it is extremely difficult to decide upon the methodology to make any kind of prediction for the future. Hardly any primary survey studies have been made in the study area, which indicates the actual waste quantum generated. As a result, except for data points from 1961 to 2001 population based on census , Industrial solid waste generated at DBTC from 1961 to 2001 and 2009 based on the data collected from the DBTC. The estimates of waste quantum for period from 2010 to 2026,shows that if the growth of industrialization and growth of percentage increase in per capita waste generation, are considered as per the nation projections, the ISW in the study area can be expected by ANFIS model using MAT Lab Version 7.8.0.347 as around 88,980 MT per year in DBTC by 2026. Due to the important role of Waste Generation (WG) prediction in ISWMS, a proper model was developed using ANN and ANFIS models [24][26] [30]. In this study, first WG in DBTC was predicted using ANN and ANFIS models; also uncertainty analysis was used to determine the uncertainty of two hybrid models.