Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS)
Climate change may cause severe hydrological droughts, leading to water shortages which will require to be assessed using high-resolution data. Gravity Recovery and Climate Experiment (GRACE) satellite Terrestrial Water Storage (TWSA) estimates offer a promising solution to monitor hydrological drou...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/4/873 |
| _version_ | 1797618432235012096 |
|---|---|
| author | Shoaib Ali Behnam Khorrami Muhammad Jehanzaib Aqil Tariq Muhammad Ajmal Arfan Arshad Muhammad Shafeeque Adil Dilawar Iqra Basit Liangliang Zhang Samira Sadri Muhammad Ahmad Niaz Ahsan Jamil Shahid Nawaz Khan |
| author_facet | Shoaib Ali Behnam Khorrami Muhammad Jehanzaib Aqil Tariq Muhammad Ajmal Arfan Arshad Muhammad Shafeeque Adil Dilawar Iqra Basit Liangliang Zhang Samira Sadri Muhammad Ahmad Niaz Ahsan Jamil Shahid Nawaz Khan |
| author_sort | Shoaib Ali |
| collection | DOAJ |
| description | Climate change may cause severe hydrological droughts, leading to water shortages which will require to be assessed using high-resolution data. Gravity Recovery and Climate Experiment (GRACE) satellite Terrestrial Water Storage (TWSA) estimates offer a promising solution to monitor hydrological drought, but its coarse resolution (1°) limits its applications to small regions of the Indus Basin Irrigation System (IBIS). Here we employed machine learning models such as Extreme Gradient Boosting (XGBoost) and Artificial Neural Network (ANN) to downscale GRACE TWSA from 1° to 0.25°. The findings revealed that the XGBoost model outperformed the ANN model with Nash Sutcliff Efficiency (NSE) (0.99), Pearson correlation (R) (0.99), Root Mean Square Error (RMSE) (5.22 mm), and Mean Absolute Error (MAE) (2.75 mm) between the predicted and GRACE-derived TWSA. Further, Water Storage Deficit Index (WSDI) and WSD (Water Storage Deficit) were used to determine the severity and episodes of droughts, respectively. The results of WSDI exhibited a strong agreement when compared with the Standardized Precipitation Evapotranspiration Index (SPEI) at different time scales (1-, 3-, and 6-months) and self-calibrated Palmer Drought Severity Index (sc-PDSI). Moreover, the IBIS had experienced increasing drought episodes, e.g., eight drought episodes were detected within the years 2010 and 2016 with WSDI of −1.20 and −1.28 and total WSD of −496.99 mm and −734.01 mm, respectively. The Partial Least Square Regression (PLSR) model between WSDI and climatic variables indicated that potential evaporation had the largest influence on drought after precipitation. The findings of this study will be helpful for drought-related decision-making in IBIS. |
| first_indexed | 2024-03-11T08:12:47Z |
| format | Article |
| id | doaj.art-5d466fb61132448f9de9baddc3e086e0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T08:12:47Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-5d466fb61132448f9de9baddc3e086e02023-11-16T23:00:38ZengMDPI AGRemote Sensing2072-42922023-02-0115487310.3390/rs15040873Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS)Shoaib Ali0Behnam Khorrami1Muhammad Jehanzaib2Aqil Tariq3Muhammad Ajmal4Arfan Arshad5Muhammad Shafeeque6Adil Dilawar7Iqra Basit8Liangliang Zhang9Samira Sadri10Muhammad Ahmad Niaz11Ahsan Jamil12Shahid Nawaz Khan13School of Water Conservancy & Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaDepartment of GIS, The Graduate School of Applied and Natural Sciences, Dokuz Eylul University, 35220 Izmir, TurkeyResearch Institute of Engineering and Technology, Hanyang University, Ansan 15588, Republic of KoreaDepartment of Wildlife, Fisheries and Aquaculture, College of Forest Resources, Mississippi State University, 775 Stone Boulevard, Starkville, MS 39762, USADepartment of Agricultural Engineering, University of Engineering & Technology, Peshawar 25120, PakistanDepartment of Biosystems and Agricultural Engineering, Oklahoma State University, Stillwater, OK 74078, USAInstitute of Geography, University of Bremen, 28359 Bremen, GermanyState Key Laboratory of Resource and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, ChinaRemote Sensing, GIS, and Climate Research Lab (National Center of GIS and Space Application), Centre for Remote Sensing, University of The Punjab, Lahore 54590, PakistanSchool of Water Conservancy & Civil Engineering, Northeast Agricultural University, Harbin 150030, ChinaDepartment of Water Resources Engineering, Shahid Chamran University of Ahvaz, Ahvaz 6135783151, IranDepartment of Computer Science, Islamia University, Bahawalpur 63100, PakistanDepartment of Plant and Environmental Sciences, New Mexico State University, 3170S Espina Str., Las Cruces, NM 88003, USAGeospatial Sciences Center of Excellence, Department of Geography and Geospatial Sciences, South Dakota State University, Brookings, SD 57007, USAClimate change may cause severe hydrological droughts, leading to water shortages which will require to be assessed using high-resolution data. Gravity Recovery and Climate Experiment (GRACE) satellite Terrestrial Water Storage (TWSA) estimates offer a promising solution to monitor hydrological drought, but its coarse resolution (1°) limits its applications to small regions of the Indus Basin Irrigation System (IBIS). Here we employed machine learning models such as Extreme Gradient Boosting (XGBoost) and Artificial Neural Network (ANN) to downscale GRACE TWSA from 1° to 0.25°. The findings revealed that the XGBoost model outperformed the ANN model with Nash Sutcliff Efficiency (NSE) (0.99), Pearson correlation (R) (0.99), Root Mean Square Error (RMSE) (5.22 mm), and Mean Absolute Error (MAE) (2.75 mm) between the predicted and GRACE-derived TWSA. Further, Water Storage Deficit Index (WSDI) and WSD (Water Storage Deficit) were used to determine the severity and episodes of droughts, respectively. The results of WSDI exhibited a strong agreement when compared with the Standardized Precipitation Evapotranspiration Index (SPEI) at different time scales (1-, 3-, and 6-months) and self-calibrated Palmer Drought Severity Index (sc-PDSI). Moreover, the IBIS had experienced increasing drought episodes, e.g., eight drought episodes were detected within the years 2010 and 2016 with WSDI of −1.20 and −1.28 and total WSD of −496.99 mm and −734.01 mm, respectively. The Partial Least Square Regression (PLSR) model between WSDI and climatic variables indicated that potential evaporation had the largest influence on drought after precipitation. The findings of this study will be helpful for drought-related decision-making in IBIS.https://www.mdpi.com/2072-4292/15/4/873Indus Basin Irrigation SystemGRACETWSmachine learning modelsdownscalingdrought monitoring |
| spellingShingle | Shoaib Ali Behnam Khorrami Muhammad Jehanzaib Aqil Tariq Muhammad Ajmal Arfan Arshad Muhammad Shafeeque Adil Dilawar Iqra Basit Liangliang Zhang Samira Sadri Muhammad Ahmad Niaz Ahsan Jamil Shahid Nawaz Khan Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) Remote Sensing Indus Basin Irrigation System GRACE TWS machine learning models downscaling drought monitoring |
| title | Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) |
| title_full | Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) |
| title_fullStr | Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) |
| title_full_unstemmed | Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) |
| title_short | Spatial Downscaling of GRACE Data Based on XGBoost Model for Improved Understanding of Hydrological Droughts in the Indus Basin Irrigation System (IBIS) |
| title_sort | spatial downscaling of grace data based on xgboost model for improved understanding of hydrological droughts in the indus basin irrigation system ibis |
| topic | Indus Basin Irrigation System GRACE TWS machine learning models downscaling drought monitoring |
| url | https://www.mdpi.com/2072-4292/15/4/873 |
| work_keys_str_mv | AT shoaibali spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT behnamkhorrami spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT muhammadjehanzaib spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT aqiltariq spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT muhammadajmal spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT arfanarshad spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT muhammadshafeeque spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT adildilawar spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT iqrabasit spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT liangliangzhang spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT samirasadri spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT muhammadahmadniaz spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT ahsanjamil spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis AT shahidnawazkhan spatialdownscalingofgracedatabasedonxgboostmodelforimprovedunderstandingofhydrologicaldroughtsintheindusbasinirrigationsystemibis |