Alemneh et al. (2026) Retrieval of Optically Active and Inactive Water Quality Parameters Using Remote Sensing and Machine Learning: Evidence from Water Hyacinth-Infested Lake Tana, Ethiopia

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Remote Sensing
• Year: 2026
• Date: 2026-09-16
• Authors: Lakachew Y. Alemneh, Dagnachew Aklog, Ann van Griensven, Minychl G. Dersseh, Goraw Goshu, Seleshi Yalew, Demesew Alemaw Mhiret, Sisay Asress, Tigistu Wassie Agegnehu, Shawl Abebe Desta, Samuel Berihun Kassa
• DOI: 10.3390/rs18183185

Research Groups

• Ethiopian Institute of Water Resources (EIWR)
• University of Addis Ababa, Department of Geology
• Google Earth Engine Team

Short Summary

This study developed an integrated remote sensing and machine learning framework to estimate key water quality parameters in Lake Tana, Ethiopia, providing a scalable and cost-effective approach for monitoring freshwater ecosystems.

Objective

• Investigate the feasibility of using Sentinel-2 remote sensing data and machine learning algorithms to predict chlorophyll-a (Chl-a), turbidity (TU), total nitrogen (TN), and total phosphorus (TP) in Lake Tana, Ethiopia.

Study Configuration

• Spatial Scale: Lake Tana watershed, Ethiopia
• Temporal Scale: 2016-2025

Methodology and Data

• Models used: Random Forest (RF), Extreme Gradient Boosting (XGB), Artificial Neural Networks (ANN), Support Vector Regression (SVR)
• Data sources: Sentinel-2 satellite imagery, in situ observations, Google Earth Engine

Main Results

• RF provided the best predictions for Chl-a (R2 = 0.94 ± 0.01; RMSE = 2.11 ± 0.18 µg L−1; MARE = 5%) and TP (R2 = 0.91 ± 0.01; RMSE = 0.26 ± 0.01 mg L−1; MARE = 8.7%)
• XGB performed best for TU (R2 = 0.93 ± 0.01; RMSE = 5.17 ± 0.43 NTU; MARE = 7%) and TN (R2 = 0.94 ± 0.02; RMSE = 0.18 ± 0.02 mg L−1; MARE = 9.9%)

Contributions

• This study provides a novel, transferable framework for monitoring diverse water quality parameters in data-scarce regions using remote sensing and machine learning.
• The results highlight the importance of considering seasonal variations and long-term trends in water quality assessments.

Funding

• Ethiopian Ministry of Water, Irrigation, and Electricity (MoWIE) - Project Code: 001/2020
• Google Earth Engine Research Award

Citation

@article{Alemneh2026Retrieval,
  author = {Alemneh, Lakachew Y. and Aklog, Dagnachew and Griensven, Ann van and Dersseh, Minychl G. and Goshu, Goraw and Yalew, Seleshi and Mhiret, Demesew Alemaw and Asress, Sisay and Agegnehu, Tigistu Wassie and Desta, Shawl Abebe and Kassa, Samuel Berihun},
  title = {Retrieval of Optically Active and Inactive Water Quality Parameters Using Remote Sensing and Machine Learning: Evidence from Water Hyacinth-Infested Lake Tana, Ethiopia},
  journal = {Remote Sensing},
  year = {2026},
  doi = {10.3390/rs18183185},
  url = {https://doi.org/10.3390/rs18183185}
}