Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia
Water quality degradation of freshwater bodies is a concern worldwide, particularly in Africa, where data are scarce and standard water quality monitoring is expensive. This study explored the use of remote sensing imagery and machine learning (ML) algorithms as an alternative to standard field meas...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Hydrology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5338/10/5/110 |
| _version_ | 1797599880665890816 |
|---|---|
| author | Elias S. Leggesse Fasikaw A. Zimale Dagnenet Sultan Temesgen Enku Raghavan Srinivasan Seifu A. Tilahun |
| author_facet | Elias S. Leggesse Fasikaw A. Zimale Dagnenet Sultan Temesgen Enku Raghavan Srinivasan Seifu A. Tilahun |
| author_sort | Elias S. Leggesse |
| collection | DOAJ |
| description | Water quality degradation of freshwater bodies is a concern worldwide, particularly in Africa, where data are scarce and standard water quality monitoring is expensive. This study explored the use of remote sensing imagery and machine learning (ML) algorithms as an alternative to standard field measuring for monitoring water quality in large and remote areas constrained by logistics and finance. Six machine learning (ML) algorithms integrated with Landsat 8 imagery were evaluated for their accuracy in predicting three optically active water quality indicators observed monthly in the period from August 2016 to April 2022: turbidity (TUR), total dissolved solids (TDS) and Chlorophyll a (Chl-a). The six ML algorithms studied were the artificial neural network (ANN), support vector machine regression (SVM), random forest regression (RF), XGBoost regression (XGB), AdaBoost regression (AB), and gradient boosting regression (GB) algorithms. XGB performed best at predicting Chl-a, with an R<sup>2</sup> of 0.78, Nash–Sutcliffe efficiency (NSE) of 0.78, mean absolute relative error (MARE) of 0.082 and root mean squared error (RMSE) of 9.79 µg/L. RF performed best at predicting TDS (with an R<sup>2</sup> of 0.79, NSE of 0.80, MARE of 0.082, and RMSE of 12.30 mg/L) and TUR (with an R<sup>2</sup> of 0.80, NSE of 0.81, and MARE of 0.072 and RMSE of 7.82 NTU). The main challenges were data size, sampling frequency, and sampling resolution. To overcome the data limitation, we used a K-fold cross validation technique that could obtain the most out of the limited data to build a robust model. Furthermore, we also employed stratified sampling techniques to improve the ML modeling for turbidity. Thus, this study shows the possibility of monitoring water quality in large freshwater bodies with limited observed data using remote sensing integrated with ML algorithms, potentially enhancing decision making. |
| first_indexed | 2024-03-11T03:40:35Z |
| format | Article |
| id | doaj.art-74cb06d6a83f4a5d8794e6f809ea679d |
| institution | Directory Open Access Journal |
| issn | 2306-5338 |
| language | English |
| last_indexed | 2024-03-11T03:40:35Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Hydrology |
| spelling | doaj.art-74cb06d6a83f4a5d8794e6f809ea679d2023-11-18T01:35:29ZengMDPI AGHydrology2306-53382023-05-0110511010.3390/hydrology10050110Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of EthiopiaElias S. Leggesse0Fasikaw A. Zimale1Dagnenet Sultan2Temesgen Enku3Raghavan Srinivasan4Seifu A. Tilahun5Faculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar H9FX+Q62, EthiopiaFaculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar H9FX+Q62, EthiopiaFaculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar H9FX+Q62, EthiopiaFaculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar H9FX+Q62, EthiopiaTemple Research and Extension Center, Texas A&M AgriLife Extension, Texas A&M AgriLife Research, Temple, TX 75684, USAFaculty of Civil and Water Resources Engineering, Bahir Dar Institute of Technology, Bahir Dar University, Bahir Dar H9FX+Q62, EthiopiaWater quality degradation of freshwater bodies is a concern worldwide, particularly in Africa, where data are scarce and standard water quality monitoring is expensive. This study explored the use of remote sensing imagery and machine learning (ML) algorithms as an alternative to standard field measuring for monitoring water quality in large and remote areas constrained by logistics and finance. Six machine learning (ML) algorithms integrated with Landsat 8 imagery were evaluated for their accuracy in predicting three optically active water quality indicators observed monthly in the period from August 2016 to April 2022: turbidity (TUR), total dissolved solids (TDS) and Chlorophyll a (Chl-a). The six ML algorithms studied were the artificial neural network (ANN), support vector machine regression (SVM), random forest regression (RF), XGBoost regression (XGB), AdaBoost regression (AB), and gradient boosting regression (GB) algorithms. XGB performed best at predicting Chl-a, with an R<sup>2</sup> of 0.78, Nash–Sutcliffe efficiency (NSE) of 0.78, mean absolute relative error (MARE) of 0.082 and root mean squared error (RMSE) of 9.79 µg/L. RF performed best at predicting TDS (with an R<sup>2</sup> of 0.79, NSE of 0.80, MARE of 0.082, and RMSE of 12.30 mg/L) and TUR (with an R<sup>2</sup> of 0.80, NSE of 0.81, and MARE of 0.072 and RMSE of 7.82 NTU). The main challenges were data size, sampling frequency, and sampling resolution. To overcome the data limitation, we used a K-fold cross validation technique that could obtain the most out of the limited data to build a robust model. Furthermore, we also employed stratified sampling techniques to improve the ML modeling for turbidity. Thus, this study shows the possibility of monitoring water quality in large freshwater bodies with limited observed data using remote sensing integrated with ML algorithms, potentially enhancing decision making.https://www.mdpi.com/2306-5338/10/5/110water qualityLandsatmachine learningLake Tana |
| spellingShingle | Elias S. Leggesse Fasikaw A. Zimale Dagnenet Sultan Temesgen Enku Raghavan Srinivasan Seifu A. Tilahun Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia Hydrology water quality Landsat machine learning Lake Tana |
| title | Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia |
| title_full | Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia |
| title_fullStr | Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia |
| title_full_unstemmed | Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia |
| title_short | Predicting Optical Water Quality Indicators from Remote Sensing Using Machine Learning Algorithms in Tropical Highlands of Ethiopia |
| title_sort | predicting optical water quality indicators from remote sensing using machine learning algorithms in tropical highlands of ethiopia |
| topic | water quality Landsat machine learning Lake Tana |
| url | https://www.mdpi.com/2306-5338/10/5/110 |
| work_keys_str_mv | AT eliassleggesse predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia AT fasikawazimale predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia AT dagnenetsultan predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia AT temesgenenku predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia AT raghavansrinivasan predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia AT seifuatilahun predictingopticalwaterqualityindicatorsfromremotesensingusingmachinelearningalgorithmsintropicalhighlandsofethiopia |