This paper presents a learning-based, physics-aware soil moisture (SM) retrieval algorithm for NASA’s Cyclone Global Navigation Satellite System (CYGNSS) mission. The goal of the proposed novel method is to advance CYGNSS-based SM estimations, exploiting the spatio-temporal resolution of the GNSS reflectometry (GNSS-R) signals to its highest potential within a machine learning framework. The methodology employs a fully connected Artificial Neural Network (ANN) regression model to perform SM predictions through learning the nonlinear relations of SM and other land geophysical parameters to the CYGNSS observables. In situ SM measurements from several International SM Network (ISMN) sites are used as reference labels; CYGNSS incidence angles, derived reflectivity and trailing edge slope (TES) values, as well as ancillary data, are exploited as input features for training and validation of the ANN model. In particular, the utilized ancillary data consist of normalized difference vegetation index (NDVI), vegetation water content (VWC), terrain elevation, terrain slope, and h-parameter (surface roughness). Land cover classification and inland water body masks are also used for the intermediate derivations and quality control purposes. The proposed algorithm assumes uniform SM over a 0.0833 ${}^{\circ }\times$ 0.0833 ${}^{\circ }$ (approximately 9 km × 9 km around the equator) lat/lon grid for any CYGNSS observation that falls within this window. The proposed technique is capable of generating sub-daily and high-resolution SM predictions as it does not rely on time-series or spatial averaging of the CYGNSS observations. Once trained on the data from ISMN sites, the model is independent from other SM sources for retrieval. The estimation results obtained over unseen test data are promising: SM predictions with an unbiased root mean squared error of 0.0544 cm ${}^3$ /cm ${}^3$ and Pearson correlation coefficient of 0.9009 are reported for 2017 and 2018.

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.

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 $\pm 38°$ 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${}^3$ cm${}^{-3}$ 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${}^3$ cm${}^{-3}$ and 0.054 cm${}^3$ cm${}^{-3}$, 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.

In this study, we conducted an empirical investigation on mobile Global Navigation Satellite System (GNSS) Transmissometry (GNSS-T) measurements to explore vegetation optical depth (VOD). Our approach involved using a dual-receiver setup, with one receiver located in open terrain to capture direct signals as a reference and another deployed on an unmanned ground vehicle (UGV) to sample vegetation across expansive forested regions. Noteworthy findings reveal the negligible influence of ground multipath effects within these forested terrains, effectively resulting in sampling the forest canopy rather than the ground itself as the receiver moves. The UGV-based method also uncovers VOD fluctuations inside the forest, offering insights into spatial distribution and the influence of satellite position on VOD measurements. The study further examines the effect of tree heterogeneity and seasonal dynamics on the VOD estimates. This empirical study contributes to our understanding of the VOD mapping capabilities of the mobile GNSS-T approach and can potentially lead to non-intrusive quantification of Vegetation Water Content (VWC) at a landscape scale in forest terrains. These results are significant for advancing our knowledge of forest ecosystem dynamics and sustainable resource management.

This study investigates the potential of mobile global navigation satellite system (GNSS) transmissometry (GNSS-T) measurements for estimating vegetation optical depth (VOD) in temperate forests, focusing on the Soil Moisture Active Passive (SMAP) validation experiment in 2022 (SMAPVEX22). Our methodology employed a dual-GNSS receiver setup, with one receiver positioned in open terrain to serve as a reference for direct signals, and another deployed on a mobile unit (helmet-based or robotic system) to spatially sample vegetation across expansive forested regions during SMAPVEX22. We assessed the stability of direct signal measurements over multiple days, demonstrating the reliability of the GNSS-T measurements. We reported the VOD measurement results for various sites across different forest regions during intensive observation periods and evaluated their correlation with respect to in situ vegetation parameters such as basal area, biomass, canopy height, and diameter breast height, finding a strong correlation with the basal area ($R^{2}=0.73$). In addition, with a predictive regression model, we demonstrated a strong dependence of the measured VOD on combination of such forest parameters. An evaluation of the VOD values at different satellite elevation angles highlighted an increasing trend in VOD with the incidence angle. The results showed the potential utility of mobile GNSS-T for generating large-scale VOD observations. Although spatially averaged VOD maps might not be directly comparable to spaceborne observations, combining mobile GNSS-T data with other sensors such as LiDAR can provide a reliable reference for airborne or spaceborne VOD estimates.

Signals of opportunity (SoOp) reflectometry (SoOp-R) is a maturing field for geophysical remote sensing as evidenced by the growing number of airborne and spaceborne experiments. As this approach receives more attention, it is worth analyzing SoOp-R's capabilities to retrieve subsurface soil moisture (SM) by leveraging communication and navigation satellite transmitters. In this research, the Cramer-Rao lower bound (CRLB) is used to identify the effects of variable SoOp-R parameters on the best achievable estimation error for root-zone soil moisture (RZSM). This study investigates the use of multiple frequency, polarization, and incidence angle measurement configurations on a two-layered dielectric profile. The results also detail the effects of variable SM conditions on the capability of SoOp-R systems to predict subsurface SM. The most prevalent observation is the importance of using at least two frequencies to limit uncertainties from subsurface SM estimates. If at least two frequencies are used, the CRLB of a profile is retrievable within the root-zone depending on the surface SM content as well as the number of independent measurements of the profile. For a depth of 30 cm, it is observed that a CRLB corresponding to 4% RZSM estimation accuracy is achievable with as few as two dual-frequency-based SoOp-R measurements. For this depth, increasing number of measurements provided by polarization and incidence angle allow for sensing of increasingly wet SM profile structures. This study, overall, details a methodology by which SoOp-R receiver system can be designed to achieve a desired CRLB using a tradeoff study between the available measurements and SM profile.