Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence
AbstractThe estimation of water depth in coastal areas and shallow waters is crucial for marine management and monitoring. However, direct measurements using fieldwork methods can be costly and time-consuming. Therefore, remote sensing imagery is a promising source of geospatial information for coas...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Geomatics, Natural Hazards & Risk |
| Subjects: | |
| Online Access: | https://www.tandfonline.com/doi/10.1080/19475705.2023.2225691 |
| _version_ | 1827582572523159552 |
|---|---|
| author | Vahideh Saeidi Seyd Teymoor Seydi Bahareh Kalantar Naonori Ueda Bahman Tajfirooz Farzin Shabani |
| author_facet | Vahideh Saeidi Seyd Teymoor Seydi Bahareh Kalantar Naonori Ueda Bahman Tajfirooz Farzin Shabani |
| author_sort | Vahideh Saeidi |
| collection | DOAJ |
| description | AbstractThe estimation of water depth in coastal areas and shallow waters is crucial for marine management and monitoring. However, direct measurements using fieldwork methods can be costly and time-consuming. Therefore, remote sensing imagery is a promising source of geospatial information for coastal planning and development. To this end, this study investigates advanced machine learning (ML) methods and redesigned morphological profiles for water depth estimation using high-resolution Sentinel-2 satellite imagery. The proposed framework involves three main steps: (1) morphological feature generation, (2) model training using several ML methods (Decision Tree, Random Forest, eXtreme Gradient BOOSTing, Light Gradient Boosting Machine, Deep Neural Network, and CatBoost), and (3) model interpretation using eXplainable Artificial Intelligence (XAI). The performance of the proposed method was evaluated in two different coastal areas (port and jetty) with reference data from accurate hydrographic data (Echo-sounder and differential global positioning systems). The statistical analysis revealed that the proposed method had high efficiency for depth estimation of the coastal area, achieving a best R2 value of 0.96 and Root Mean Square Error (RMSE) of 0.27 m in water depth estimation in the shallow water of Chabahar Bay in the Oman Sea. Additionally, the higher impact and interaction of the morphological features were verified using XAI for water depth mapping. |
| first_indexed | 2024-03-08T22:52:35Z |
| format | Article |
| id | doaj.art-7cd8f62884dc4dc5b2f4fe701a87aeb4 |
| institution | Directory Open Access Journal |
| issn | 1947-5705 1947-5713 |
| language | English |
| last_indexed | 2024-03-08T22:52:35Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Geomatics, Natural Hazards & Risk |
| spelling | doaj.art-7cd8f62884dc4dc5b2f4fe701a87aeb42023-12-16T08:49:46ZengTaylor & Francis GroupGeomatics, Natural Hazards & Risk1947-57051947-57132023-12-0114110.1080/19475705.2023.2225691Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligenceVahideh Saeidi0Seyd Teymoor Seydi1Bahareh Kalantar2Naonori Ueda3Bahman Tajfirooz4Farzin Shabani5Department of Mapping and Surveying, Darya Tarsim Consulting Engineers Co. Ltd, Tehran, IranSchool of Technology, Department of Geoinformatics and Surveying, Mainz University of Applied Sciences, Mainz, GermanyRIKEN Center for Advanced Intelligence Project, Goal-Oriented Technology Research Group, Disaster Resilience Science Team, Tokyo, JapanRIKEN Center for Advanced Intelligence Project, Goal-Oriented Technology Research Group, Disaster Resilience Science Team, Tokyo, JapanDepartment of Hydrography, Darya Tarsim Consulting Engineers Co. Ltd, Tehran, IranDepartment of Biological and Environmental Sciences, College of Arts and Sciences, Qatar University, Doha, QatarAbstractThe estimation of water depth in coastal areas and shallow waters is crucial for marine management and monitoring. However, direct measurements using fieldwork methods can be costly and time-consuming. Therefore, remote sensing imagery is a promising source of geospatial information for coastal planning and development. To this end, this study investigates advanced machine learning (ML) methods and redesigned morphological profiles for water depth estimation using high-resolution Sentinel-2 satellite imagery. The proposed framework involves three main steps: (1) morphological feature generation, (2) model training using several ML methods (Decision Tree, Random Forest, eXtreme Gradient BOOSTing, Light Gradient Boosting Machine, Deep Neural Network, and CatBoost), and (3) model interpretation using eXplainable Artificial Intelligence (XAI). The performance of the proposed method was evaluated in two different coastal areas (port and jetty) with reference data from accurate hydrographic data (Echo-sounder and differential global positioning systems). The statistical analysis revealed that the proposed method had high efficiency for depth estimation of the coastal area, achieving a best R2 value of 0.96 and Root Mean Square Error (RMSE) of 0.27 m in water depth estimation in the shallow water of Chabahar Bay in the Oman Sea. Additionally, the higher impact and interaction of the morphological features were verified using XAI for water depth mapping.https://www.tandfonline.com/doi/10.1080/19475705.2023.2225691Explainable artificial intelligencecoastal managementdepth estimationsatellite derived bathymetryhydrographymachine learning |
| spellingShingle | Vahideh Saeidi Seyd Teymoor Seydi Bahareh Kalantar Naonori Ueda Bahman Tajfirooz Farzin Shabani Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence Geomatics, Natural Hazards & Risk Explainable artificial intelligence coastal management depth estimation satellite derived bathymetry hydrography machine learning |
| title | Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence |
| title_full | Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence |
| title_fullStr | Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence |
| title_full_unstemmed | Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence |
| title_short | Water depth estimation from Sentinel-2 imagery using advanced machine learning methods and explainable artificial intelligence |
| title_sort | water depth estimation from sentinel 2 imagery using advanced machine learning methods and explainable artificial intelligence |
| topic | Explainable artificial intelligence coastal management depth estimation satellite derived bathymetry hydrography machine learning |
| url | https://www.tandfonline.com/doi/10.1080/19475705.2023.2225691 |
| work_keys_str_mv | AT vahidehsaeidi waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence AT seydteymoorseydi waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence AT baharehkalantar waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence AT naonoriueda waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence AT bahmantajfirooz waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence AT farzinshabani waterdepthestimationfromsentinel2imageryusingadvancedmachinelearningmethodsandexplainableartificialintelligence |