Upscaling dryland carbon and water fluxes with artificial neural networks of optical, thermal, and microwave satellite remote sensing

Authors: DANNENBERG, M.P. - University Of Iowa; BARNES, M,.L. - University Of Indiana; SMITH, W.K. - University Of Arizona; JOHNSTON, M.R. - University Of Iowa; MEERDINK, S.K. - University Of Iowa; WANG, X, - University Of Arizona; Scott, Russell - Russ; Biederman, Joel

Submitted to: Biogeosciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/20/2022
Publication Date: 1/15/2023
Citation: Dannenberg, M., Barnes, M., Smith, W., Johnston, M., Meerdink, S., Wang, X., Scott, R.L., Biederman, J.A. 2023. Upscaling dryland carbon and water fluxes with artificial neural networks of optical, thermal, and microwave satellite remote sensing. Biogeosciences. 20(2):383-404. https://doi.org/10.5194/bg-20-383-2023.
DOI: https://doi.org/10.5194/bg-20-383-2023

Interpretive Summary: Earth’s semiarid and arid lands (collectively, drylands) are home to more than two billion people, provide key ecosystem services, and exert a large influence on the trends and variability in Earth’s carbon cycle. However, determining dryland carbon and water fluxes with satellite remote sensing suffers from unique challenges not typically encountered in wetter regions, particularly in capturing soil moisture stress. Here, we develop and evaluate an approach for joint modeling of dryland gross primary production (GPP), net ecosystem exchange (NEE), and evapotranspiration (ET) in the western United States (U.S.) using a suite of measurements sites spanning major functional types and aridity regimes. We use a computer approach called artificial neural networks (ANNs) to predict dryland ecosystem fluxes by using a combination of numerous satellite data streams. Our new model explains the majority of variation in measured GPP and ET, improving upon existing satellite estimates at most measurement sites. Our model predictions of NEE were considerably worse than its predictions of GPP and ET, likely because soil and plant respiratory processes are largely invisible to satellite sensors. Our results show that a combination of ANNs and a suite of satellite observations can substantially improve estimates of carbon and water fluxes in drylands, potentially providing the means to better monitor vegetation function and ecosystem services in these important regions that are undergoing rapid hydroclimatic change.

Technical Abstract: Earth’s drylands are home to more than two billion people, provide key ecosystem services, and exert a large influence on the trends and variability in Earth’s carbon cycle. However, modeling dryland carbon and water fluxes with remote sensing suffers from unique challenges not typically encountered in mesic systems, particularly in capturing soil moisture stress. Here, we develop and evaluate an approach for joint modeling of dryland gross primary production (GPP), net ecosystem exchange (NEE), and evapotranspiration (ET) in the western United States (U.S.) using a suite of AmeriFlux eddy covariance sites spanning major functional types and aridity regimes. We use artificial neural networks (ANNs) to predict dryland ecosystem fluxes by fusing optical vegetation indices, multitemporal thermal observations, and microwave soil moisture/temperature retrievals from the Soil Moisture Active Passive (SMAP) sensor. Our new dryland ANN (DrylANNd) carbon and water flux model explains more than 70% of monthly variance in GPP and ET, improving upon existing MODIS GPP and ET estimates at most dryland eddy covariance sites. DrylANNd predictions of NEE were considerably worse than its predictions of GPP and ET, likely because soil and plant respiratory processes are largely invisible to satellite sensors. Optical vegetation indices, particularly the normalized difference vegetation index (NDVI) and near-infrared reflectance of vegetation (NIRv), were generally the most important variables contributing to model skill. However, daytime and nighttime land surface temperatures and SMAP soil moisture and soil temperature also contributed to model skill, with SMAP especially improving model predictions of shrubland, grassland, and savanna fluxes and land surface temperatures improving predictions in evergreen needleleaf forests. Our results show that a combination of optical vegetation indices, thermal infrared, and microwave observations can substantially improve estimates of carbon and water fluxes in drylands, potentially providing the means to better monitor vegetation function and ecosystem services in these important regions that are undergoing rapid hydroclimatic change.