Using technical artificial intelligence Modeling to forecast the management of the water quality index. | ||
| المجلة العلمية للدراسات التجارية والبيئية | ||
| Volume 16, Issue 1, January 2025, Pages 463-482 PDF (1.07 M) | ||
| Document Type: المقالة الأصلية | ||
| DOI: 10.21608/jces.2025.419258 | ||
| Author | ||
| Dalia Younis* | ||
| Arab Academy of Science Technology - And Maritime Transport (AASTMT) - Egypt | ||
| Abstract | ||
| An essential tool for risk-based management of water resource systems is the assessment and forecasting of water quality. Numerous water quality indicators, charts, and standards have been produced for these objectives, and they have been applied based on water uses. Since the advent of computing technology, numerical models have been used frequently to simulate processes affecting water quality. But because these numerical models are not sufficiently user-friendly, there is a significant knowledge gap between model developers and practitioners. Since Artificial Intelligence (AI) has advanced over the past ten years, it is now viable to incorporate the technologies into numerical modeling systems to fill in the gaps. Among the numerous AI-based algorithms available, For predicting water quality, artificial neural networks are more often used. These models, however, need a sizable dataset for both training and validation. The management of water resources for conservation has increased the necessity for forecasting techniques today. In this study, the parameters for the water quality index were determined using an artificial neural network model (ANN). In the calibration of an ANN model, we can obtain a set of coefficients for a linear model. In 2020, seven Sohag and kena water quality metrics were selected at four different locations. The results show that, in comparison to the Multiple Regression Model, the Water Quality Index (WQI) predicted with ANN model produces better output (correlation coefficient). | ||
| Keywords | ||
| water quality index; wáter modelling by AI; water quality in AI; water model prediction; neural network water quality | ||
|
Statistics Article View: 26 PDF Download: 28 |
||
