Muzaffarpur city land changes and impact on urban runoff and water quality of the river Burhi Gandak

• Published in: International journal of environmental science and technology (Tehran) Vol. 21; no. 2; pp. 2071 - 2082
• Main Authors: Arman Ali, Md, Roy, L. B.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.01.2024
• Subjects: Aquatic Pollution; cropland; Earth and Environmental Science; Ecotoxicology; Environment; Environmental Chemistry; Environmental Science and Engineering; forests; land use; Original Paper; river water; rivers; satellites; Soil Science & Conservation; urban runoff; urbanization; Waste Water Technology; Water Management; Water Pollution Control; water quality; Dove optimization; Satellite image; Varying coefficient neural network; Water quality standards; Feature analysis
• ISSN: 1735-1472; 1735-2630
• DOI: 10.1007/s13762-023-05008-2

Nowadays, river water is continuously polluting due to rapid urban growth. Hence, measuring the water quality (WQ) year wise is the most needed task for today’s culture. However, usual neural network features are limited to forecasting the WQ that was resulted in poor estimation exactness. So, a novel Dove-based varying coefficient neural network ( DbVCNet) was executed to find the WQ of Burhi Gandak river and the land use changes of Muzaffarpur city and their surroundings. Hence, the specific region’s satellite images and WQ data were utilized to attain these objectives. Hence, the WQ was analyzed by recognizing the changes in chemical quantity in river water. In addition, the percentage of land use changes was estimated based on cropland, urban growth and forest region. Subsequently, it was tested in the MATLAB Tool, and robustness was estimated against the recent existing model. A novel DbVCNet scores the widest range of WQ estimation rate at 98.5%, which is the finest exactness range compared to past studies.