Impact of Chemical Fertilizer on Surface Water Quality of the Downstream Bargarh Canal, Odisha, India Using Principal Component Analysis and Machine Learning Models

This study examined the impact of excessive application of chemical fertilizer on the surface water quality of the downstream Bargarh Canal, Odisha, India, during pre-harvest, during harvest, and post-harvest periods of rice cultivation. The average WQI found before cultivation is 39.88, during cultivation is 68.99, and after cultivation is 55.07, showing poor water quality during cultivation and after harvesting. In the pre-cultivation phase, PCA extracted the first four principal components with variances of 78.64%, 11.06%, 7.13%, and 2.90%; in the cultivation period, it extracted the first six PCs with variances of 51.77%, 27.34%, 8.98%, 6.83%, 2.81%, and 2.20%; in the post-harvest phase, it extracted the first four PCs with variances of 72.70%, 18.22%, 7.61%, and 1.05% by retaining maximum information from the dataset. The linear regression and Random Forest models reproduced and calculated WQI values with high agreement because they used the same physicochemical variables included in the WQI formulation. Therefore, the modeling results should be interpreted as WQI reconstruction analysis rather than independent prediction. The bacteriological analysis revealed that the bacterial load peaks during the cultivation period. The Kruskal–Wallis test revealed significant differences (p-values < 0.05) in median MPN values throughout all phases. Seasonal variations and PCA indicate that the addition of agricultural runoff in the canal water is the most vital source of contamination; however, the quantitative source attribution remains unclear.

Authors

Institutions

Publication Details

Journal
Environmental Forensics
Published
2026-11-19
DOI
https://doi.org/10.1080/15275922.2026.2762739
Primary Topic
Water Quality and Pollution Assessment
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Impact of Chemical Fertilizer on Surface Water Quality of the Downstream Bargarh Canal, Odisha, India Using Principal Component Analysis and Machine Learning Models

Pritisha Barik, Trinath Biswal, Subhrasmita Dash
Environmental Forensics
Water Quality and Pollution Assessment
article

Impact of Chemical Fertilizer on Surface Water Quality of the Downstream Bargarh Canal, Odisha, India Using Principal Component Analysis and Machine Learning Models

Pritisha Barik, Trinath Biswal, Subhrasmita Dash
article en

Abstract

This study examined the impact of excessive application of chemical fertilizer on the surface water quality of the downstream Bargarh Canal, Odisha, India, during pre-harvest, during harvest, and post-harvest periods of rice cultivation. The average WQI found before cultivation is 39.88, during cultivation is 68.99, and after cultivation is 55.07, showing poor water quality during cultivation and after harvesting. In the pre-cultivation phase, PCA extracted the first four principal components with variances of 78.64%, 11.06%, 7.13%, and 2.90%; in the cultivation period, it extracted the first six PCs with variances of 51.77%, 27.34%, 8.98%, 6.83%, 2.81%, and 2.20%; in the post-harvest phase, it extracted the first four PCs with variances of 72.70%, 18.22%, 7.61%, and 1.05% by retaining maximum information from the dataset. The linear regression and Random Forest models reproduced and calculated WQI values with high agreement because they used the same physicochemical variables included in the WQI formulation. Therefore, the modeling results should be interpreted as WQI reconstruction analysis rather than independent prediction. The bacteriological analysis revealed that the bacterial load peaks during the cultivation period. The Kruskal–Wallis test revealed significant differences (p-values < 0.05) in median MPN values throughout all phases. Seasonal variations and PCA indicate that the addition of agricultural runoff in the canal water is the most vital source of contamination; however, the quantitative source attribution remains unclear.

Environmental Forensics
Veer Surendra Sai University of Technology (IN)
Water Quality and Pollution Assessment
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon