Citation :

Sachchidanand Bhagat, L.B. Roy, "A Deep Learning and Bayesian Regression Framework for Water Quality Assessment in Dam Reservoirs using Landsat Imagery," International Journal of Civil Engineering, vol. 13, no. 4, pp. 318-332, 2026. Crossref, https://doi.org/10.14445/23488352/IJCE-V13I4P119

Abstract

Water quality management in dam reservoirs plays a vital role in public health, aquatic ecosystems, and irrigation sustainability. Nagi and Nakti dam reservoirs in India, located in the state of Bihar, are affected by harmful substances such as pesticides, industrial chemicals, and untreated sewage water. These harmful substances increase nutrient levels such as nitrogen (N) and phosphorus (P), which affect aquatic life by increasing algal blooms, depleting oxygen, and altering the ratios of N: P. Hence, water quality is measured frequently in Nagi and Nakti dams. Traditional water quality management techniques, such as manual sampling, laboratory, and sensor-based methods, alter the contamination level due to delayed lab results and data loss because of human error, which prevents the predictive forecasting of eutrophication. To address the limitations of water quality management in dam reservoirs at an early stage, artificial intelligence-based techniques are proposed in this study. In this study, we proposed a Pixel-Based Optimized Deep Learning (PODL) framework, which consists of (I) deep Denoised Convolutional Neural Network (DnCNN) models to enhance the pixel level at the edges of Landsat satellite dam images to detect water and mass regions. Salp Swarm-Optimized layers of DnCNN (SSO-DnCNN) are proposed. The dual threshold graph cut segmentation technique is used to separate the mass region from the enhanced Landsat satellite image by minimizing energy at high green and red pixels. Then, textural features are extracted from the segmented mass region of the Landsat image. Bayesian-Optimized Multilinear Regression (BO-MLR) model predicts the water hydrogen level (pH) and dissolved oxygen (DO) from the extracted textural image and ground truth laboratory values, achieving an accuracy of about 91%-97%.

Keywords

Water quality monitoring, Landsat satellite imagery, Deep Convolutional Neural Networks, Bayesian multilevel regression, dam reservoir analysis.

References

1. Divakar Yadav et al., “Satellite Image Classification using Deep Learning Approach,” Earth Science Informatics, vol. 17, no. 3, pp. 2495-2508, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
2. Anja Batina, and Andrija Krtalić, “Integrating Remote Sensing Methods for Monitoring Lake Water Quality: A Comprehensive Review,” Hydrology, vol. 11, no. 7, pp. 1-27, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
3. Peng Zhang et al., “Forecasting Do of the River-Type Reservoirs using Input Variable Selection and Machine Learning Techniques-Taking Shuikou Reservoir in the Minjiang River as an Example,” Ecological Indicators, vol. 155, pp. 1-12, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
4. Muhammad Umar Farooq et al., “Assessment of Algorithm Performance on Predicting Total Dissolved Solids using Artificial Neural Network and Multiple Linear Regression for the Groundwater Data,” Water, vol. 14, no. 13, pp. 1-12, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Benjamin J. Britton et al., “Evaluating Broadscale Deep Learning for Maya Settlement Detection in G-LiHT Lidar,” Journal of Archaeological Method and Theory, vol. 33, no. 2, pp. 1-38, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Amar Lokman, Wan Zakiah Wan Ismail, and Nor Azlina Ab Aziz, “Enhancing Water Quality Index Prediction Accuracy in Mranti Lake and Rivers in Malaysia using Regression Forest Model,” Applied Water Science, vol. 16, no. 2, pp. 1-27, 2025.
   [CrossRef] [Google Scholar] [Publisher Link]
7. M. Uma Maheswari et al., “Efficient Drinking Water Quality Analysis using Machine Learning Model with Hyper-Parameter Tuning,” 2023 7^th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 401-406, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
8. Manish Kumar et al., “Quality Assessment and Monitoring of River Water using IoT Infrastructure,” IEEE Internet of Things Journal, vol. 10, no. 12, pp. 10280-10290, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Swapna A. Jaywant, and Khalid Mahmood Arif, “Remote Sensing Techniques for Water Quality Monitoring: A Review,” Sensors, vol. 24, no. 24, pp. 1-31, 2024.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Jin-Geun Park et al., “Contamination of Sediment after the Construction of the Yeongju Dam,” Journal of Environmental Science International, vol. 33, no. 10, pp. 745-752, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Bugeon Jo et al., “Drought Impact on Water Quality Environment Through Linkage Analysis with Meteorological Data in the Gamcheon Mid-Basin,” Journal of Korea Water Resources Association, vol. 56, no. 11, pp. 823-835, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Bu Li et al., “Enhancing Process-based Hydrological Models with Embedded Neural Networks: A Hybrid Approach,” Journal of Hydrology, vol. 625, pp. 1-42, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Il-Hoon Choi, Eu-Ru Lee, and Hyung-Sup Jung, “Performance Comparison of Water Body Detection from Sentinel-1 SAR and Sentinel-2 Optical Imagery using Attention U-Net Model,” Korean Journal of Remote Sensing, vol. 40, no. 5, pp. 507-523, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Sanae Kang, and Chul-Hee Lim, “Detecting Inaccessible Flood Damage in North Korea using Sentinel-1 Synthetic Aperture Radar Imagery: A Case of Flooding at 2023 Summer,” Korean Journal of Remote Sensing, vol. 41, no. 1, pp. 173-184, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
15. F. Torres-Bejarano et al., “Impact of Land Cover Changes on Water Quality: An Application to the Guájaro Reservoir, Colombia,” International Journal of Environmental Science and Technology, vol. 20, no. 4, pp. 3577-3590, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Alice Nureen Omondi et al., “Estimation and Mapping of Water Quality Parameters using Satellite Images: A Case Study of Two Rivers Dam, Kenya,” Water Practice and Technology, vol. 18, no. 2, pp. 428-443, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Nidal M. Hussein, and Mohammed N. Assaf, “Multispectral Remote Sensing Utilization for Monitoring Chlorophyll-A Levels in Inland Water Bodies in Jordan,” The Scientific World Journal, vol. 2020, no. 1, pp. 1-14, 2020.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Liming Zhang et al., “An Infrared and Visible Image Fusion Algorithm based on Resnet-152,” Multimedia Tools and Applications, vol. 81, no. 7, pp. 9277-9287, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
19. Jie Long et al., “Application of an Improved LSTM Model based on FECA and CEEMDAN-VMD Decomposition in Water Quality Prediction,” Scientific Reports, vol. 15, no. 1, pp. 1-15, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
20. Yas Barzegar et al., “Data-Centric Water Safety Monitoring: A Machine Learning Pipeline with Intelligent Feature Selection for Potability Prediction,” Procedia Computer Science, vol. 270, pp. 6035-6044, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
21. Jing Bi et al., “STMF: A Spatiotemporal Multimodal Fusion Model for Long-Term Water Quality Forecasting,” IEEE Internet of Things Journal, vol. 12, no. 18, pp. 37146-37159, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
22. Bhavana Reddy Tadimarri, and Ahyoung Lee, “IoT-based Real-Time Water Quality Assessment with Predictive Analytics,” 2025 IEEE Opportunity Research Scholars Symposium (ORSS), Atlanta, GA, USA, pp. 1-4, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]
23. R. Maruthamuthu et al., “Enhanced Water Quality Index Prediction using a Dual-Key Convolutional Transformer Autoencoder Network Integrating with Poplar Optimization,” Franklin Open, vol. 13, pp. 1-13, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]