Soil moisture (SM) derived from satellite-based remote sensing measurements plays a vital role for understanding Earth’s land and near-surface atmosphere interactions. Bistatic Global Navigation Satellite System (GNSS) Reflectometry (GNSS-R) has emerged in recent years as a new domain of microwave remote sensing with great potential for SM retrievals, particularly at high spatio-temporal resolutions. In this work, a machine learning (ML)-based framework is presented for obtaining SM data products over the International Soil Moisture Network (ISMN) sites in the Continental United States (CONUS) by leveraging spaceborne GNSS-R observations provided by NASA’s Cyclone GNSS (CYGNSS) constellation alongside remotely sensed geophysical data products. Three widely-used ML approaches—artificial neural network (ANN), random forest (RF), and support vector machine (SVM)—are compared and analyzed for the SM retrieval through utilizing multiple validation strategies. Specifically, using a 5-fold cross-validation method, overall RMSE values of 0.052, 0.061, and 0.065 cm3/cm3 are achieved for the RF, ANN, and SVM techniques, respectively. In addition, both a site-independent and a year-based validation techniques demonstrate satisfactory accuracy of the proposed ML model, suggesting that this SM approach can be generalized in space and time domains. Moreover, the achieved accuracy can be further improved when the model is trained and tested over individual SM networks as opposed to combining all available SM networks. Additionally, factors including soil type and land cover are analyzed with respect to their impacts on the accuracy of SM retrievals. Overall, the results demonstrated here indicate that the proposed technique can confidently provide SM estimates over lightly-vegetated areas with vegetation water content (VWC) less than 5 kg/m2 and relatively low spatial heterogeneity.
1 September 2018 in Bulletin of the American Meteorological Society
Particularly in light of California’s recent multiyear drought, there is a critical need for accurate and timely evapotranspiration (ET) and crop stress information to ensure long-term sustainability of high-value crops. Providing this information requires the development of tools applicable across the continuum from subfield scales to improve water management within individual fields up to watershed and regional scales to assess water resources at county and state levels. High-value perennial crops (vineyards and orchards) are major water users, and growers will need better tools to improve water-use efficiency to remain economically viable and sustainable during periods of prolonged drought. To develop these tools, government, university, and industry partners are evaluating a multiscale remote sensing–based modeling system for application over vineyards. During the 2013–17 growing seasons, the Grape Remote Sensing Atmospheric Profile and Evapotranspiration eXperiment (GRAPEX) project has collected micrometeorological and biophysical data within adjacent pinot noir vineyards in the Central Valley of California. Additionally, each year ground, airborne, and satellite remote sensing data were collected during intensive observation periods (IOPs) representing different vine phenological stages. An overview of the measurements and some initial results regarding the impact of vine canopy architecture on modeling ET and plant stress are presented here. Refinements to the ET modeling system based on GRAPEX are being implemented initially at the field scale for validation and then will be integrated into the regional modeling toolkit for large area assessment.
Earth system models (ESMs) from the Coupled Model Intercomparison Project Phase 6 (CMIP6) experiment exhibit a well-known summertime warm bias in mid-latitude land regions – most notably in the central contiguous United States (CUS). The dominant source of this bias is still under debate. Using validated datasets and both coupled and off-line modeling, we find that the CUS summertime warm bias is driven by the incorrect partitioning of evapotranspiration (ET) into its canopy transpiration and soil evaporation components. Specifically, CMIP6 ESMs do not effectively use available rootzone soil moisture for summertime transpiration and instead rely excessively on shallow soil and canopy-intercepted water storage to supply ET. As such, expected summertime precipitation deficits in CUS induce a negative ET bias into CMIP6 ESMs and a corresponding positive temperature bias via local land-atmosphere coupling. This tendency potentially biases CMIP6 projections of regional water stress and summertime air temperature variability under elevated CO2 conditions.
This paper presents a machine learning (ML) framework to derive a quasi-global soil moisture (SM) product by direct use of the Cyclone Global Navigation Satellite System (CYGNSS)’s high spatio-temporal resolution observations over the tropics (within latitudes) at L-band. The learning model is trained by using in-situ SM data from the International Soil Moisture Network (ISMN) sites and various space-borne ancillary data. The approach produces daily SM retrievals that are gridded to 3 km and 9 km within the CYGNSS spatial coverage. The performance of the model is independently evaluated at various temporal scales (daily, 3-day, weekly, and monthly) against Soil Moisture Active Passive (SMAP) mission’s enhanced SM products at a resolution of 9 km × 9 km. The mean unbiased root-mean-square difference (ubRMSD) between concurrent (same calendar day) CYGNSS and SMAP SM retrievals for about three years (from 2017 to 2019) is 0.044 cm cm with a correlation coefficient of 0.66 over SMAP recommended grids. The performance gradually improves with temporal averaging and degrades over regions regularly flagged by SMAP such as dense forest, high topography, and coastlines. Furthermore, CYGNSS and SMAP retrievals are evaluated against 170 ISMN in-situ observations that result in mean unbiased root-mean-square errors (ubRMSE) of 0.055 cm cm and 0.054 cm cm, respectively, and a higher correlation coefficient with CYGNSS retrievals. It is important to note that the proposed approach is trained over limited in-situ observations and is independent of SMAP observations in its training. The retrieval performance indicates current applicability and future growth potential of GNSS-R-based, directly measured spaceborne SM products that can provide improved spatio-temporal resolution than currently available datasets.