Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields
<p>Soil moisture is highly variable in space and time, and deficits (i.e., droughts) play an important role in modulating crop yields. Limited hydroclimate and yield data, however, hamper drought impact monitoring and assessment at the farm field scale. This study demonstrates the potential of...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2021-04-01
|
Series: | Hydrology and Earth System Sciences |
Online Access: | https://hess.copernicus.org/articles/25/1827/2021/hess-25-1827-2021.pdf |
id |
doaj-2a222270f6d9419ab9ee1d73707dcfed |
---|---|
record_format |
Article |
spelling |
doaj-2a222270f6d9419ab9ee1d73707dcfed2021-04-09T04:21:12ZengCopernicus PublicationsHydrology and Earth System Sciences1027-56061607-79382021-04-01251827184710.5194/hess-25-1827-2021Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yieldsN. Vergopolan0S. Xiong1L. Estes2N. Wanders3N. W. Chaney4E. F. Wood5M. Konar6K. Caylor7K. Caylor8H. E. Beck9N. Gatti10T. Evans11J. Sheffield12Civil and Environmental Engineering Department, Princeton University, Princeton, NJ, USASchool of Geography, Clark University, Worcester, MA, USASchool of Geography, Clark University, Worcester, MA, USADepartment of Physical Geography, Faculty of Geosciences, Utrecht University, Utrecht, the NetherlandsDepartment of Civil and Environmental Engineering, Duke University, Durham, NC, USACivil and Environmental Engineering Department, Princeton University, Princeton, NJ, USACivil and Environmental Engineering Department, University of Illinois at Urbana-Champaign, Urbana, IL, USADepartment of Geography, University of California, Santa Barbara, CA, USABren School of Environmental Science and Management, University of California, Santa Barbara, CA, USACivil and Environmental Engineering Department, Princeton University, Princeton, NJ, USADepartment of Agricultural and Consumer Economics, University of Illinois at Urbana-Champaign, Urbana, IL, USASchool of Geography, Development and Environment, University of Arizona, Tucson, AZ, USASchool of Geography and Environmental Science, University of Southampton, Southampton, UK<p>Soil moisture is highly variable in space and time, and deficits (i.e., droughts) play an important role in modulating crop yields. Limited hydroclimate and yield data, however, hamper drought impact monitoring and assessment at the farm field scale. This study demonstrates the potential of using field-scale soil moisture simulations to support high-resolution agricultural yield prediction and drought monitoring at the smallholder farm field scale. We present a multiscale modeling approach that combines HydroBlocks – a physically based hyper-resolution land surface model (LSM) – with machine learning. We used HydroBlocks to simulate root zone soil moisture and soil temperature in Zambia at 3 h 30 <span class="inline-formula">m</span> resolution. These simulations, along with remotely sensed vegetation indices, meteorological data, and descriptors of the physical landscape (related to topography, land cover, and soils) were combined with district-level maize data to train a random forest (RF) model to predict maize yields at district and field scales (250 <span class="inline-formula">m</span>). Our model predicted yields with an average testing coefficient of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) of 0.57 and mean absolute error (MAE) of 310 <span class="inline-formula">kg ha<sup>−1</sup></span> using year-based cross-validation. Our predicted maize losses due to the 2015–2016 El Niño drought agreed well with losses reported by the Food and Agriculture Organization (FAO). Our results reveal that soil moisture is the strongest and most reliable predictor of maize yield, driving its spatial and temporal variability. Soil moisture was also a more effective indicator of drought impacts on crops than precipitation, soil and air temperatures, and remotely sensed normalized difference vegetation index (NDVI)-based drought indices. This study demonstrates how field-scale modeling can help bridge the spatial-scale gap between drought monitoring and agricultural impacts.</p>https://hess.copernicus.org/articles/25/1827/2021/hess-25-1827-2021.pdf |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
N. Vergopolan S. Xiong L. Estes N. Wanders N. W. Chaney E. F. Wood M. Konar K. Caylor K. Caylor H. E. Beck N. Gatti T. Evans J. Sheffield |
spellingShingle |
N. Vergopolan S. Xiong L. Estes N. Wanders N. W. Chaney E. F. Wood M. Konar K. Caylor K. Caylor H. E. Beck N. Gatti T. Evans J. Sheffield Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields Hydrology and Earth System Sciences |
author_facet |
N. Vergopolan S. Xiong L. Estes N. Wanders N. W. Chaney E. F. Wood M. Konar K. Caylor K. Caylor H. E. Beck N. Gatti T. Evans J. Sheffield |
author_sort |
N. Vergopolan |
title |
Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
title_short |
Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
title_full |
Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
title_fullStr |
Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
title_full_unstemmed |
Field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
title_sort |
field-scale soil moisture bridges the spatial-scale gap between drought monitoring and agricultural yields |
publisher |
Copernicus Publications |
series |
Hydrology and Earth System Sciences |
issn |
1027-5606 1607-7938 |
publishDate |
2021-04-01 |
description |
<p>Soil moisture is highly variable in space and time, and deficits (i.e.,
droughts) play an important role in modulating crop yields. Limited
hydroclimate and yield data, however, hamper drought impact monitoring and
assessment at the farm field scale. This study demonstrates the potential of using field-scale soil moisture simulations to support high-resolution agricultural yield prediction and drought monitoring at the smallholder farm field scale. We present a multiscale modeling approach that combines HydroBlocks – a physically based hyper-resolution land surface model (LSM) – with machine learning. We used HydroBlocks to simulate root zone soil moisture and soil temperature in Zambia at 3 h 30 <span class="inline-formula">m</span> resolution. These simulations, along with remotely sensed vegetation indices, meteorological data, and descriptors of the physical landscape (related to topography, land cover, and soils) were combined with district-level maize data to train a random forest (RF) model to predict maize yields at district and field scales (250 <span class="inline-formula">m</span>). Our model predicted yields with an average testing coefficient of determination (<span class="inline-formula"><i>R</i><sup>2</sup></span>) of 0.57 and mean absolute error (MAE) of 310 <span class="inline-formula">kg ha<sup>−1</sup></span> using year-based cross-validation. Our predicted maize losses due to the 2015–2016 El Niño drought agreed well with losses reported by the Food and Agriculture Organization (FAO). Our results reveal that soil moisture is the strongest and most reliable predictor of maize yield, driving its spatial and temporal variability. Soil moisture was also a more effective indicator of drought impacts on crops than precipitation, soil and air temperatures, and remotely sensed normalized difference vegetation index (NDVI)-based drought indices. This study
demonstrates how field-scale modeling can help bridge the spatial-scale gap
between drought monitoring and agricultural impacts.</p> |
url |
https://hess.copernicus.org/articles/25/1827/2021/hess-25-1827-2021.pdf |
work_keys_str_mv |
AT nvergopolan fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT sxiong fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT lestes fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT nwanders fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT nwchaney fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT efwood fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT mkonar fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT kcaylor fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT kcaylor fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT hebeck fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT ngatti fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT tevans fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields AT jsheffield fieldscalesoilmoisturebridgesthespatialscalegapbetweendroughtmonitoringandagriculturalyields |
_version_ |
1721533139463962624 |