Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach
Gravity Recovery and Climate Experiment (GRACE) data have become a widely used global dataset for evaluating the variability in groundwater storage for the different major aquifers. Moreover, the application of GRACE has been constrained to the local scale due to lower spatial resolution. The curren...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-06-01
|
| Series: | Environments |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3298/6/6/63 |
| _version_ | 1811298713346244608 |
|---|---|
| author | Md Mafuzur Rahaman Balbhadra Thakur Ajay Kalra Ruopu Li Pankaj Maheshwari |
| author_facet | Md Mafuzur Rahaman Balbhadra Thakur Ajay Kalra Ruopu Li Pankaj Maheshwari |
| author_sort | Md Mafuzur Rahaman |
| collection | DOAJ |
| description | Gravity Recovery and Climate Experiment (GRACE) data have become a widely used global dataset for evaluating the variability in groundwater storage for the different major aquifers. Moreover, the application of GRACE has been constrained to the local scale due to lower spatial resolution. The current study proposes Random Forest (RF), a recently developed unsupervised machine learning method, to downscale a GRACE-derived groundwater storage anomaly (GWSA) from 1° × 1° to 0.25° × 0.25° in the Northern High Plains aquifer. The RF algorithm integrated GRACE to other satellite-based geospatial and hydro-climatological variables, obtained from the Noah land surface model, to generate a high-resolution GWSA map for the period 2009 to 2016. This RF approach replicates local groundwater variability (the combined effect of climatic and human impacts) with acceptable Pearson correlation (0.58 ~ 0.84), percentage bias (−14.67 ~ 2.85), root mean square error (15.53 ~ 46.69 mm), and Nash-Sutcliffe efficiency (0.58 ~ 0.84). This developed RF model has significant potential to generate finer scale GWSA maps for managing groundwater at both local and regional scales, especially for areas with sparse groundwater monitoring wells. |
| first_indexed | 2024-04-13T06:24:19Z |
| format | Article |
| id | doaj.art-20ee3fb72752467e93f4950001b91f39 |
| institution | Directory Open Access Journal |
| issn | 2076-3298 |
| language | English |
| last_indexed | 2024-04-13T06:24:19Z |
| publishDate | 2019-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Environments |
| spelling | doaj.art-20ee3fb72752467e93f4950001b91f392022-12-22T02:58:30ZengMDPI AGEnvironments2076-32982019-06-01666310.3390/environments6060063environments6060063Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest ApproachMd Mafuzur Rahaman0Balbhadra Thakur1Ajay Kalra2Ruopu Li3Pankaj Maheshwari4Department of Civil and Environmental Engineering, Southern Illinois University, 1230 Lincoln Drive, Carbondale, IL 62901, USADepartment of Civil and Environmental Engineering, Southern Illinois University, 1230 Lincoln Drive, Carbondale, IL 62901, USADepartment of Civil and Environmental Engineering, Southern Illinois University, 1230 Lincoln Drive, Carbondale, IL 62901, USADepartment of Geography and Environmental Resources, Southern Illinois University, 1000 Faner Drive, Carbondale, IL 62901, USATransportation Engineer, Louis Berger, 444 E. Warm Springs Road, Suite 118, Las Vegas, NV 89119, USAGravity Recovery and Climate Experiment (GRACE) data have become a widely used global dataset for evaluating the variability in groundwater storage for the different major aquifers. Moreover, the application of GRACE has been constrained to the local scale due to lower spatial resolution. The current study proposes Random Forest (RF), a recently developed unsupervised machine learning method, to downscale a GRACE-derived groundwater storage anomaly (GWSA) from 1° × 1° to 0.25° × 0.25° in the Northern High Plains aquifer. The RF algorithm integrated GRACE to other satellite-based geospatial and hydro-climatological variables, obtained from the Noah land surface model, to generate a high-resolution GWSA map for the period 2009 to 2016. This RF approach replicates local groundwater variability (the combined effect of climatic and human impacts) with acceptable Pearson correlation (0.58 ~ 0.84), percentage bias (−14.67 ~ 2.85), root mean square error (15.53 ~ 46.69 mm), and Nash-Sutcliffe efficiency (0.58 ~ 0.84). This developed RF model has significant potential to generate finer scale GWSA maps for managing groundwater at both local and regional scales, especially for areas with sparse groundwater monitoring wells.https://www.mdpi.com/2076-3298/6/6/63GRACERandom ForestNorthern High Plains aquiferland surface model |
| spellingShingle | Md Mafuzur Rahaman Balbhadra Thakur Ajay Kalra Ruopu Li Pankaj Maheshwari Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach Environments GRACE Random Forest Northern High Plains aquifer land surface model |
| title | Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach |
| title_full | Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach |
| title_fullStr | Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach |
| title_full_unstemmed | Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach |
| title_short | Estimating High-Resolution Groundwater Storage from GRACE: A Random Forest Approach |
| title_sort | estimating high resolution groundwater storage from grace a random forest approach |
| topic | GRACE Random Forest Northern High Plains aquifer land surface model |
| url | https://www.mdpi.com/2076-3298/6/6/63 |
| work_keys_str_mv | AT mdmafuzurrahaman estimatinghighresolutiongroundwaterstoragefromgracearandomforestapproach AT balbhadrathakur estimatinghighresolutiongroundwaterstoragefromgracearandomforestapproach AT ajaykalra estimatinghighresolutiongroundwaterstoragefromgracearandomforestapproach AT ruopuli estimatinghighresolutiongroundwaterstoragefromgracearandomforestapproach AT pankajmaheshwari estimatinghighresolutiongroundwaterstoragefromgracearandomforestapproach |