Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques
Water quality is deteriorating in the world's freshwater bodies, and Lake Tana in Ethiopia is becoming unpleasant to biodiversity. The objective of this study is to retrieve non-optical water quality data, specifically total nitrogen (TN) and total phosphorus (TP) concentrations, in Lake Tana using...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal Article |
| Language: | Inglés |
| Published: |
Frontiers Media
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10568/152513 |
| _version_ | 1855524770588655616 |
|---|---|
| author | Leggesse, E. S. Zimale, F. A. Sultan, D. Enku, T. Tilahun, Seifu A. |
| author_browse | Enku, T. Leggesse, E. S. Sultan, D. Tilahun, Seifu A. Zimale, F. A. |
| author_facet | Leggesse, E. S. Zimale, F. A. Sultan, D. Enku, T. Tilahun, Seifu A. |
| author_sort | Leggesse, E. S. |
| collection | Repository of Agricultural Research Outputs (CGSpace) |
| description | Water quality is deteriorating in the world's freshwater bodies, and Lake Tana in Ethiopia is becoming unpleasant to biodiversity. The objective of this study is to retrieve non-optical water quality data, specifically total nitrogen (TN) and total phosphorus (TP) concentrations, in Lake Tana using Machine Learning (ML) techniques applied to Landsat 8 OLI imagery. The ML methods employed include Artificial Neural Networks (ANN), Support Vector Regression (SVR), Random Forest Regression (RF), XGBoost Regression (XGB), AdaBoost Regression (AB), and Gradient Boosting Regression (GB). The XGB algorithm provided the best result for TN retrieval, with determination coefficient (R2), mean absolute error (MARE), relative mean square error (RMSE) and Nash Sutcliff (NS) values of 0.80, 0.043, 0.52, and 0.81 mg/L, respectively. The RF algorithm was most effective for TP retrieval, with R2 of 0.73, MARE of 0.076, RMSE of 0.17 mg/L, and NS index of 0.74. These methods accurately predicted TN and TP spatial concentrations, identifying hotspots along river inlets and northeasters. The temporal patterns of TN, TP, and their ratios were also accurately represented by combining in-situ, RS and ML-based models. Our findings suggest that this approach can significantly improve the accuracy of water quality retrieval in large inland lakes and lead to the development of potential water quality digital services. |
| format | Journal Article |
| id | CGSpace152513 |
| institution | CGIAR Consortium |
| language | Inglés |
| publishDate | 2024 |
| publishDateRange | 2024 |
| publishDateSort | 2024 |
| publisher | Frontiers Media |
| publisherStr | Frontiers Media |
| record_format | dspace |
| spelling | CGSpace1525132025-12-08T10:29:22Z Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques Leggesse, E. S. Zimale, F. A. Sultan, D. Enku, T. Tilahun, Seifu A. water quality monitoring inland waters landsat machine learning remote sensing satellite imagery total nitrogen total phosphorus neural networks Water quality is deteriorating in the world's freshwater bodies, and Lake Tana in Ethiopia is becoming unpleasant to biodiversity. The objective of this study is to retrieve non-optical water quality data, specifically total nitrogen (TN) and total phosphorus (TP) concentrations, in Lake Tana using Machine Learning (ML) techniques applied to Landsat 8 OLI imagery. The ML methods employed include Artificial Neural Networks (ANN), Support Vector Regression (SVR), Random Forest Regression (RF), XGBoost Regression (XGB), AdaBoost Regression (AB), and Gradient Boosting Regression (GB). The XGB algorithm provided the best result for TN retrieval, with determination coefficient (R2), mean absolute error (MARE), relative mean square error (RMSE) and Nash Sutcliff (NS) values of 0.80, 0.043, 0.52, and 0.81 mg/L, respectively. The RF algorithm was most effective for TP retrieval, with R2 of 0.73, MARE of 0.076, RMSE of 0.17 mg/L, and NS index of 0.74. These methods accurately predicted TN and TP spatial concentrations, identifying hotspots along river inlets and northeasters. The temporal patterns of TN, TP, and their ratios were also accurately represented by combining in-situ, RS and ML-based models. Our findings suggest that this approach can significantly improve the accuracy of water quality retrieval in large inland lakes and lead to the development of potential water quality digital services. 2024-08-20 2024-09-30T20:48:54Z 2024-09-30T20:48:54Z Journal Article https://hdl.handle.net/10568/152513 en Open Access Frontiers Media Leggesse, E. S.; Zimale, F. A.; Sultan, D.; Enku, T.; Tilahun, Seifu A. 2024. Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques. Frontiers in Water, 6:1432280. [doi: https://doi.org/10.3389/frwa.2024.1432280] |
| spellingShingle | water quality monitoring inland waters landsat machine learning remote sensing satellite imagery total nitrogen total phosphorus neural networks Leggesse, E. S. Zimale, F. A. Sultan, D. Enku, T. Tilahun, Seifu A. Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title | Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title_full | Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title_fullStr | Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title_full_unstemmed | Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title_short | Advancing non-optical water quality monitoring in Lake Tana, Ethiopia: insights from machine learning and remote sensing techniques |
| title_sort | advancing non optical water quality monitoring in lake tana ethiopia insights from machine learning and remote sensing techniques |
| topic | water quality monitoring inland waters landsat machine learning remote sensing satellite imagery total nitrogen total phosphorus neural networks |
| url | https://hdl.handle.net/10568/152513 |
| work_keys_str_mv | AT leggessees advancingnonopticalwaterqualitymonitoringinlaketanaethiopiainsightsfrommachinelearningandremotesensingtechniques AT zimalefa advancingnonopticalwaterqualitymonitoringinlaketanaethiopiainsightsfrommachinelearningandremotesensingtechniques AT sultand advancingnonopticalwaterqualitymonitoringinlaketanaethiopiainsightsfrommachinelearningandremotesensingtechniques AT enkut advancingnonopticalwaterqualitymonitoringinlaketanaethiopiainsightsfrommachinelearningandremotesensingtechniques AT tilahunseifua advancingnonopticalwaterqualitymonitoringinlaketanaethiopiainsightsfrommachinelearningandremotesensingtechniques |