Field evaluation of semi‐automated moisture estimation from geophysics using machine learning
Abstract Geophysical methods can provide three‐dimensional (3D), spatially continuous estimates of soil moisture. However, point‐to‐point comparisons of geophysical properties to measure soil moisture data are frequently unsatisfactory, resulting in geophysics being used for qualitative purposes onl...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Vadose Zone Journal |
| Online Access: | https://doi.org/10.1002/vzj2.20246 |
| _version_ | 1827987633330978816 |
|---|---|
| author | Neil Terry Frederick D. Day‐Lewis John W. Lane Jr. Carole D. Johnson Dale Werkema |
| author_facet | Neil Terry Frederick D. Day‐Lewis John W. Lane Jr. Carole D. Johnson Dale Werkema |
| author_sort | Neil Terry |
| collection | DOAJ |
| description | Abstract Geophysical methods can provide three‐dimensional (3D), spatially continuous estimates of soil moisture. However, point‐to‐point comparisons of geophysical properties to measure soil moisture data are frequently unsatisfactory, resulting in geophysics being used for qualitative purposes only. This is because (1) geophysics requires models that relate geophysical signals to soil moisture, (2) geophysical methods have potential uncertainties resulting from smoothing and artifacts introduced from processing and inversion, and (3) results from multiple geophysical methods are not easily combined within a single soil moisture estimation framework. To investigate these potential limitations, an irrigation experiment was performed wherein soil moisture was monitored through time, and several surface geophysical datasets indirectly sensitive to soil moisture were collected before and after irrigation: ground penetrating radar, electrical resistivity tomography (ERT), and frequency domain electromagnetics (FDEM). Data were exported in both raw and processed form, and then snapped to a common 3D grid to facilitate moisture prediction by standard calibration techniques, multivariate regression, and machine learning. A combination of inverted ERT data, raw FDEM, and inverted FDEM data was most informative for predicting soil moisture using a random regression forest model (one‐thousand 60/40 training/test cross‐validation folds produced root mean squared errors ranging from 0.025–0.046 cm3/cm3). This cross‐validated model was further supported by a separate evaluation using a test set from a physically separate portion of the study area. Machine learning was conducive to a semi‐automated model‐selection process that could be used for other sites and datasets to locally improve accuracy. |
| first_indexed | 2024-04-09T23:51:07Z |
| format | Article |
| id | doaj.art-1f049a0c7f8c4269baefdb9b25cf0a23 |
| institution | Directory Open Access Journal |
| issn | 1539-1663 |
| language | English |
| last_indexed | 2024-04-09T23:51:07Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Vadose Zone Journal |
| spelling | doaj.art-1f049a0c7f8c4269baefdb9b25cf0a232023-03-17T09:41:57ZengWileyVadose Zone Journal1539-16632023-03-01222n/an/a10.1002/vzj2.20246Field evaluation of semi‐automated moisture estimation from geophysics using machine learningNeil Terry0Frederick D. Day‐Lewis1John W. Lane Jr.2Carole D. Johnson3Dale Werkema4U.S. Geological Survey, New York Water Science Center 126 Cooke Hall, University at Buffalo North Campus Buffalo New York USAPacific Northwest National Laboratory Richland Washington USAU.S. Geological Survey Office of International Programs Storrs Connecticut USAU.S. Geological Survey, Observing Systems Division Hydrologic Remote Sensing Branch Storrs Connecticut USAU.S. Environmental Protection Agency, Office of Research and Development, Center for Public Health and Environmental Assessment Pacific Ecology Systems Division Newport Oregon USAAbstract Geophysical methods can provide three‐dimensional (3D), spatially continuous estimates of soil moisture. However, point‐to‐point comparisons of geophysical properties to measure soil moisture data are frequently unsatisfactory, resulting in geophysics being used for qualitative purposes only. This is because (1) geophysics requires models that relate geophysical signals to soil moisture, (2) geophysical methods have potential uncertainties resulting from smoothing and artifacts introduced from processing and inversion, and (3) results from multiple geophysical methods are not easily combined within a single soil moisture estimation framework. To investigate these potential limitations, an irrigation experiment was performed wherein soil moisture was monitored through time, and several surface geophysical datasets indirectly sensitive to soil moisture were collected before and after irrigation: ground penetrating radar, electrical resistivity tomography (ERT), and frequency domain electromagnetics (FDEM). Data were exported in both raw and processed form, and then snapped to a common 3D grid to facilitate moisture prediction by standard calibration techniques, multivariate regression, and machine learning. A combination of inverted ERT data, raw FDEM, and inverted FDEM data was most informative for predicting soil moisture using a random regression forest model (one‐thousand 60/40 training/test cross‐validation folds produced root mean squared errors ranging from 0.025–0.046 cm3/cm3). This cross‐validated model was further supported by a separate evaluation using a test set from a physically separate portion of the study area. Machine learning was conducive to a semi‐automated model‐selection process that could be used for other sites and datasets to locally improve accuracy.https://doi.org/10.1002/vzj2.20246 |
| spellingShingle | Neil Terry Frederick D. Day‐Lewis John W. Lane Jr. Carole D. Johnson Dale Werkema Field evaluation of semi‐automated moisture estimation from geophysics using machine learning Vadose Zone Journal |
| title | Field evaluation of semi‐automated moisture estimation from geophysics using machine learning |
| title_full | Field evaluation of semi‐automated moisture estimation from geophysics using machine learning |
| title_fullStr | Field evaluation of semi‐automated moisture estimation from geophysics using machine learning |
| title_full_unstemmed | Field evaluation of semi‐automated moisture estimation from geophysics using machine learning |
| title_short | Field evaluation of semi‐automated moisture estimation from geophysics using machine learning |
| title_sort | field evaluation of semi automated moisture estimation from geophysics using machine learning |
| url | https://doi.org/10.1002/vzj2.20246 |
| work_keys_str_mv | AT neilterry fieldevaluationofsemiautomatedmoistureestimationfromgeophysicsusingmachinelearning AT frederickddaylewis fieldevaluationofsemiautomatedmoistureestimationfromgeophysicsusingmachinelearning AT johnwlanejr fieldevaluationofsemiautomatedmoistureestimationfromgeophysicsusingmachinelearning AT caroledjohnson fieldevaluationofsemiautomatedmoistureestimationfromgeophysicsusingmachinelearning AT dalewerkema fieldevaluationofsemiautomatedmoistureestimationfromgeophysicsusingmachinelearning |