Comparing Artificial Neural Networks with Multiple Linear Regression for Forecasting Heavy Metal Content
Journal Title: Acadlore Transactions on Geosciences - Year 2022, Vol 1, Issue 1
Abstract
This paper adopts two modeling tools, namely, multiple linear regression (MLR) and artificial neural networks (ANNs), to predict the concentrations of heavy metals (zinc, boron, and manganese) in surface waters of the Oued Inaouen watershed flowing towards Inaouen, using a set of physical-chemical parameters. XLStat was employed to perform multiple linear and nonlinear regressions, and Statista 10 was chosen to construct neural networks for modeling and prediction. The effectiveness of the ANN- and MLR-based stochastic models was assessed by the determination coefficient (R²), the sum squared error (SSE) and a review of fit graphs. The results demonstrate the value of ANNs for prediction modeling. Drawing on supervised learning and back propagation, the ANN-based prediction models adopt an architecture of [18-15-1] for zinc, [18-11-1] for manganese, and [18-8-1] for boron, and perform effectively with a single cached layer. It was found that the MLR-based prediction models are substantially less accurate than those based on the ANNs. In addition, the physical-chemical parameters being investigated are nonlinearly correlated with the levels of heavy metals in the surface waters of the Oued Inaouen watershed flowing towards Inaouen.
Authors and Affiliations
Rachid El Chaal, Moulay Othman Aboutafail
Keywords
Related Articles
- EP ID EP732406
- DOI 10.56578/atg010102
- Views 62
- Downloads 0
Reassessing the Water Invasion Intensity Indicator Curve and Endpoint Equation in Water-Drive Gas Reservoirs
The traditional view that the production indicator curve of water-drive gas reservoirs exhibits an upward trend is not entirely consistent with production practices. Additionally, the classical method of calibrating gas...
Comparative Analysis of Trigonometric and Polynomial Models in Meteorological Parameter Prediction for Sub-Saharan West African Stations
Meteorological parameter modeling is imperative for predicting future atmospheric conditions. This study focuses on the Sub-Saharan region of West Africa, a region characterized by its climatic diversity and unique weath...
Development and Application of Eco-Friendly Micro-Nano Filtrate Reducers and High-Performance Water-Based Drilling Fluids
The utilization of oil-based drilling fluids is a significant technical approach for drilling in ultra-deep, unconventional, and other complex hydrocarbon reservoirs. However, these fluids present notable disadvantages,...
Dynamic Responses of Embankment Dams, Constituted from Varied Soil Types, to Seismic Activity
This research delineates a numerical elucidation concerning the flow through an embankment, utilising PLAXIS2D software, and underscores the pivotal influence of soil composition—encompassing gravel, sand, and clay—on th...
Common Mistakes and Their Fixes in Earthquake-Resistant Buildings
The primary way to design building structures refers to the stationary loads specified by the governing laws. However, the load pattern does not guarantee the appropriateness of the seismic design. To make matters worse,...