Machine-learning based multi-layer soil moisture forecasts—an application case study of the Montana 2017 flash drought
Machine-learning based multi-layer soil moisture forecasts—an application case study of the Montana 2017 flash drought
Soil moisture (SM) is an essential climate variable, governing land-atmosphere interactions, runoff generation, and vegetation growth and productivity. Timely forecasts of SM spatial distribution and vertical profiles are needed for early detection and prediction of potential droughts. However, previous studies have primarily concentrated on historical or near real-time soil moisture mapping, with less effort devoted to the development and integration of soil moisture forecast components within drought assessment systems. A satellite-driven machine-learning approach was developed in this study to build complex relationships between diversified predictor data sets and in situ multi-layer SM measurements from the Montana Mesonet, a regionally dense environmental station network in the US upper Missouri and Columbia basins. The resulting 30-m daily SM predictions showed strong performance against in situ SM measurements from 4-, 8- and 20-inch soil layers, and with 1- to 2-week forecast lead times (R > 0.91; RMSE ≤ 0.047 cm3/cm3). The machine-learning model was subsequently applied to the entire Montana region, and the SM deficit forecasts with both 1- and 2-week lead times successfully depicted onset, progression, and termination phases of the 2017 Montana flash drought, which was not effectively identified from prevailing operational systems. The resulting system is capable of delineating local scale SM heterogeneity, and could be extended to predict other critical water cycle variables, potentially enhancing future drought forecasts through multivariate assessments and benefiting water resource management, agricultural practices, and the provision of ecosystem services.
flash drought, forecast, machine learning, Mesonet, remote sensing, soil moisture
Du, J.
19eb6508-a794-427a-b7f6-e85ed94e76d3
Kimball, J.S.
20bb351d-1453-4a3e-a42a-41df3ee66b07
Jencso, K.
439d0c26-702d-4ba1-8362-2b1dceb0d665
Hoylman, Z.
435c0ab7-731c-4c56-8ab4-f8a6403c340f
Brust, C.
be9fb07b-1195-425b-9864-38dedb647fd8
Ketchum, D.
08ffcf91-2e6c-4fcd-abd4-a67682bdf9b0
Xu, Y.
a291fff2-a831-4800-8f0a-681da3a0fb4b
Lu, H.
e6a1866d-87e4-49e6-8c78-37cc1d8dd235
Sheffield, J.
dd66575b-a4dc-4190-ad95-df2d6aaaaa6b
2 October 2024
Du, J.
19eb6508-a794-427a-b7f6-e85ed94e76d3
Kimball, J.S.
20bb351d-1453-4a3e-a42a-41df3ee66b07
Jencso, K.
439d0c26-702d-4ba1-8362-2b1dceb0d665
Hoylman, Z.
435c0ab7-731c-4c56-8ab4-f8a6403c340f
Brust, C.
be9fb07b-1195-425b-9864-38dedb647fd8
Ketchum, D.
08ffcf91-2e6c-4fcd-abd4-a67682bdf9b0
Xu, Y.
a291fff2-a831-4800-8f0a-681da3a0fb4b
Lu, H.
e6a1866d-87e4-49e6-8c78-37cc1d8dd235
Sheffield, J.
dd66575b-a4dc-4190-ad95-df2d6aaaaa6b
Du, J., Kimball, J.S., Jencso, K., Hoylman, Z., Brust, C., Ketchum, D., Xu, Y., Lu, H. and Sheffield, J.
(2024)
Machine-learning based multi-layer soil moisture forecasts—an application case study of the Montana 2017 flash drought.
Water Resources Research, 60 (10), [e2023WR036973].
(doi:10.1029/2023WR036973).
Abstract
Soil moisture (SM) is an essential climate variable, governing land-atmosphere interactions, runoff generation, and vegetation growth and productivity. Timely forecasts of SM spatial distribution and vertical profiles are needed for early detection and prediction of potential droughts. However, previous studies have primarily concentrated on historical or near real-time soil moisture mapping, with less effort devoted to the development and integration of soil moisture forecast components within drought assessment systems. A satellite-driven machine-learning approach was developed in this study to build complex relationships between diversified predictor data sets and in situ multi-layer SM measurements from the Montana Mesonet, a regionally dense environmental station network in the US upper Missouri and Columbia basins. The resulting 30-m daily SM predictions showed strong performance against in situ SM measurements from 4-, 8- and 20-inch soil layers, and with 1- to 2-week forecast lead times (R > 0.91; RMSE ≤ 0.047 cm3/cm3). The machine-learning model was subsequently applied to the entire Montana region, and the SM deficit forecasts with both 1- and 2-week lead times successfully depicted onset, progression, and termination phases of the 2017 Montana flash drought, which was not effectively identified from prevailing operational systems. The resulting system is capable of delineating local scale SM heterogeneity, and could be extended to predict other critical water cycle variables, potentially enhancing future drought forecasts through multivariate assessments and benefiting water resource management, agricultural practices, and the provision of ecosystem services.
Text
Water Resources Research - 2024 - Du - Machine‐Learning Based Multi‐Layer Soil Moisture Forecasts An Application Case Study
- Version of Record
More information
Accepted/In Press date: 21 September 2024
Published date: 2 October 2024
Keywords:
flash drought, forecast, machine learning, Mesonet, remote sensing, soil moisture
Identifiers
Local EPrints ID: 496094
URI: http://eprints.soton.ac.uk/id/eprint/496094
ISSN: 0043-1397
PURE UUID: 7f5a4536-43cf-4a9e-8521-378d192497f0
Catalogue record
Date deposited: 03 Dec 2024 17:46
Last modified: 04 Dec 2024 02:49
Export record
Altmetrics
Contributors
Author:
J. Du
Author:
J.S. Kimball
Author:
K. Jencso
Author:
Z. Hoylman
Author:
C. Brust
Author:
D. Ketchum
Author:
Y. Xu
Author:
H. Lu
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
