Explore the vast range of titles available.

Machine learning (ML) has gained significant attention for unraveling the complex, nonlinear relationships between soil moisture (SM) and various predictive variables, including remote sensing (RS; reflectance, brightness temperature, backscatter coefficients) and biophysical (topographic, soil, vegetation, and weather) variables. We reviewed the literature to extract and synthesize ML algorithms, reliable input features, and challenges in SM estimation using RS data. We analyzed results from 144 articles published from 2010 to 2024. Random forest (40 out of 67 studies), support vector regressor (13 out of 39 studies), and artificial neural networks (12 out of 27 studies) often outperformed other algorithms to estimate SM using RS datasets. Multi-source RS data often outperformed single-source data in SM estimation. Satellite-derived features, such as vegetation indices and backscattering coefficients, provided critical information on surface SM (SSM) variability to estimate SSM. For root zone SM estimation, soil properties and SSM generally were more reliable predictors than surface information derived solely from RS. Two recent advances—the use of semi-empirical models and L-band SAR to mitigate vegetation effects, and transfer learning to improve model transferability—have shown promise in addressing key challenges in SM estimation.

Root zone soil moisture (RZSM) controls vegetation transpiration and hydraulic distribution processes and plays a key role in energy and water exchange between land surface and atmosphere; hence, accurate estimation of RZSM is crucial for agricultural irrigation management practices. Traditional methods to measure soil moisture at stations are laborious and spatially uneven, making it difficult to obtain soil moisture data on a large scale. Remote sensing techniques can provide soil moisture in a large-scale range, but they can only provide surface soil moisture (SSM) with a depth of approximately 5–10 cm. In order to obtain a large range of soil moisture for deeper soil layers, especially the crop root zone with a depth of about 100–200 cm, numerous methods based on remote sensing inversion have been proposed. This paper analyzes and summarizes the research progress of remote sensing-based RZSM estimation methods in the past few decades and classifies these methods into four categories: empirical methods, semi-empirical methods, physics-based methods, and machine learning methods. Then, the advantages and disadvantages of various methods are outlined. Additionally an outlook on the future development of RZSM estimation methods is made and discussed.

Traditional soil moisture prediction methods often face challenges in providing spatially and temporally comprehensive root zone soil moisture (RZSM) with complex soil environment. In this paper, a novel method is proposed for predicting RZSM using images obtained from ground penetrating radar (GPR) data and processed with the convolutional neural network (CNN). The CNN encompasses two major stages: classification and regression. Initially, a CNN is tailored to classify tree root images obtained by GPR into distinct water content categories. Subsequently, through transfer learning, the pre-trained classification network is adapted for regression to predict continuous soil moisture levels. Then, the field experimental results demonstrate the efficacy and robustness of our approach, offering promising avenues for enhancing root zone water management and sustainability.

Regional quantification of energy and water balance fluxes depends inevitably on the estimation of surface and rootzone soil moisture. The simulation of soil moisture depends on the soil retention characteristics, which are difficult to estimate at a regional scale. Thus, the present study proposes a new method to estimate high-resolution Soil Hydraulic Parameters (SHPs) which in turn help to provide high-resolution (spatial and temporal) rootzone soil moisture (RZSM) products. The study is divided into three phases—(I) involves the estimation of finer surface soil moisture (1 km) from the coarse resolution satellite soil moisture. The algorithm utilizes MODIS 1 km Land Surface Temperature (LST) and 1 km Normalized difference vegetation Index (NDVI) for downscaling 25 km C-band derived soil moisture from AMSR-2 to 1 km surface soil moisture product. At one of the test sites, soil moisture is continuously monitored at 5, 20, and 50 cm depth, while at 44 test sites data were collected randomly for validation. The temporal and spatial correlation for the downscaled product was 70% and 83%, respectively. (II) In the second phase, downscaled soil moisture product is utilized to inversely estimate the SHPs for the van Genuchten model (1980) at 1 km resolution. The numerical experiments were conducted to understand the impact of homogeneous SHPs as compared to the three-layered parameterization of the soil profile. It was seen that the SHPs estimated using the downscaled soil moisture (I-d experiment) performed with similar efficiency as compared to SHPs estimated from the in-situ soil moisture data (I-b experiment) in simulating the soil moisture. The normalized root mean square error (nRMSE) for the two treatments was 0.37 and 0.34, respectively. It was also noted that nRMSE for the treatment with the utilization of default SHPs (I-a) and AMSR-2 soil moisture (I-c) were found to be 0.50 and 0.43, respectively. (III) Finally, the derived SHPs were used to simulate both surface soil moisture and RZSM. The final product, RZSM which is the daily 1 km product also showed a nearly 80% correlation at the test site. The estimated SHPs are seen to improve the mean NSE from 0.10 (I-a experiment) to 0.50 (I-d experiment) for the surface soil moisture simulation. The mean nRMSE for the same was found to improve from 0.50 to 0.31.

The current study analyses the effect of root zone soil moisture in the calibration and validation of Soil and Water Assessment Tool (SWAT) model. A multi-algorithm, genetically adaptive multi-objective method (AMALGAM) is used for the calibration of the model. The multi-variable calibration considering both streamflow and soil moisture is compared with a single-variable calibration considering streamflow and then analysed the effectiveness of root zone soil moisture in the calibration of SWAT. The results of the analysis show that the root zone soil moisture significantly influences the simulation of evapotranspiration component in SWAT. The SOL_AWC and SOL_K are found to be the key parameters for the simulation of hydrological fluxes in SWAT. The multi-variable calibration at the watershed outlet ensures a better process representation and spatial prediction in SWAT compared to the single-variable calibration approach.

Accurate estimation of root-zone soil moisture (SM) is of great significance for accurate irrigation management. This study was purposed to identify planted-by-planted mapping of root-zone SM on three critical fruit growth periods based on UAV multispectral images using three machine learning (ML) algorithms in a kiwifruit orchard in Shaanxi, China. Several spectral variables were selected based on variable importance (VIP) rankings, including reflectance Ri at wavelengths 560, 668, 740, and 842 nm. Results indicated that the VIP method effectively reduced 42 vegetation indexes (VIs) to less than 7 with an evaluation accuracy of root-zone SM models. Compared with deep root-zone SM models (SM40 and SM60), shallow root-zone SM models (SM10, SM20, and SM30) have better performance (R2 from 0.65 to 0.82, RRMSE from 0.02 to 0.03, MAE from 0.20 to 0.54) in the three fruit growth stages. Among three ML algorithms, random forest models were recommended for simulating kiwi root-zone SM during the critical fruit growth period. Overall, the proposed planted-by-planted root-zone SM estimation approach can be considered a great tool to upgrade the toolbox of the growers in site-specific field management for the high spatiotemporal resolution of SM maps.

The evaporation of water from land into the atmosphere is a key component of the hydrological cycle. Accurate estimates of this flux are essential for proper water management and irrigation scheduling. However, continuous and qualitative information on land evaporation is currently not available at the required spatio-temporal scales for agricultural applications and regional-scale water management. Here, we apply the Global Land Evaporation Amsterdam Model (GLEAM) at 100 m spatial resolution and daily time steps to provide estimates of land evaporation over The Netherlands, Flanders, and western Germany for the period 2013–2017. By making extensive use of microwave-based geophysical observations, we are able to provide data under all weather conditions. The soil moisture estimates from GLEAM at high resolution compare well with in situ measurements of surface soil moisture, resulting in a median temporal correlation coefficient of 0.76 across 29 sites. Estimates of terrestrial evaporation are also evaluated using in situ eddy-covariance measurements from five sites, and compared to estimates from the coarse-scale GLEAM v3.2b, land evaporation from the Satellite Application Facility on Land Surface Analysis (LSA-SAF), and reference grass evaporation based on Makkink’s equation. All datasets compare similarly with in situ measurements and differences in the temporal statistics are small, with correlation coefficients against in situ data ranging from 0.65 to 0.95, depending on the site. Evaporation estimates from GLEAM-HR are typically bounded by the high values of the Makkink evaporation and the low values from LSA-SAF. While GLEAM-HR and LSA-SAF show the highest spatial detail, their geographical patterns diverge strongly due to differences in model assumptions, model parameterizations, and forcing data. The separate consideration of rainfall interception loss by tall vegetation in GLEAM-HR is a key cause of this divergence: while LSA-SAF reports maximum annual evaporation volumes in the Green Heart of The Netherlands, an area dominated by shrubs and grasses, GLEAM-HR shows its maximum in the national parks of the Veluwe and Heuvelrug, both densely-forested regions where rainfall interception loss is a dominant process. The pioneering dataset presented here is unique in that it provides observational-based estimates at high resolution under all weather conditions, and represents a viable alternative to traditional visible and infrared models to retrieve evaporation at field scales.

The North China Plain is a crucial agricultural region in China, but irregular precipitation patterns have led to significant water shortages. To address this, analyzing the high-resolution dynamics of root-zone soil moisture transport is essential for optimizing irrigation strategies and improving water resource efficiency. The Richards equation is a robust model for describing soil moisture transport dynamics across multiple soil layers, yet its application at large spatial scales is hindered by its sensitivity to boundary conditions and model parameters. This study introduces a novel approach that, for the first time, employs a continuous time series of near-surface soil moisture as the upper boundary condition in the Richards equation to estimate high-resolution root-zone soil moisture in the North China Plain, thus enabling its large-scale application. Singular spectrum analysis (SSA) was first applied to reconstruct site-specific time series, filling in missing and singular values. Leveraging observational data from 617 monitoring sites across the North China Plain and multiple spatial covariates, we developed a machine learning model to estimate near-surface soil moisture at a 1 km resolution. This high-resolution, continuous near-surface soil moisture series then served as the upper boundary condition for the Richards equation, facilitating the estimation of root-zone soil moisture across the region. The results indicated that the machine learning model achieved a correlation coefficient (R) of 0.92 for estimating spatial near-surface soil moisture. Analysis of spatial covariates showed that atmospheric forcing factors, particularly temperature and evaporation, had the most substantial impact on model performance, followed by static factors such as latitude, longitude, and soil texture. With a continuous time series of near-surface soil moisture, the Richards equation method accurately predicted multi-layer soil moisture and demonstrated its applicability for large-scale spatial use. The model yielded R values of 0.97, 0.78, 0.618, and 0.43, with RMSEs of 0.024, 0.06, 0.08, and 0.11, respectively, for soil layers at depths of 10 cm, 20 cm, 40 cm, and 100 cm across the North China Plain.

Soil moisture (SM) is a bridge between the atmosphere, vegetation and soil, and its dynamics reflect the energy exchange and transformation between the three. Among SM at different soil profiles, root zone soil moisture (RZSM) plays a significant role in vegetation growth. Therefore, reliable estimation of RZSM at the regional scale is of great importance for drought warning, agricultural yield estimation, forest fire monitoring, etc. Many satellite products provide surface soil moisture (SSM) at the thin top layer of the soil, approximately 2 cm from the surface. However, the acquisition of RZSM at the regional scale is still a tough issue to solve, especially in the semi-arid areas with a lack of in situ observations. Linking the dynamics of SSM and RZSM is promising to solve this issue. The soil moisture analytical relationship (SMAR) model can relate RZSM to SSM based on a simplified soil water balance equation, which is suitable for the simulation of soil moisture mechanisms in semi-arid areas. In this study, the Xiliaohe River Basin is the study area. The SMAR model at the pixels where in situ sites were located is established, and parameters (a, b, sw2, sc1) at these pixels are calibrated by a genetic algorithm (GA). Then the spatial parameters are estimated by the random forest (RF) regression method with the soil, meteorological and vegetation characteristics of the study area as explanatory variables. In addition, the importance of soil, climatic and vegetation characteristics for predicting SMAR parameters is analyzed. Finally, the spatial RZSM in the Xiliaohe River Basin is estimated by the SMAR model at the regional scale with the predicted spatial parameters, and the variation of the regional SMAR model performance is discussed. A comparison of estimated RZSM and in-situ RZSM showed that the SMAR model at the point and regional scales can both meet the RMSE benchmark from NASA of 0.06 cm3·cm−3, indicating that the method this study proposed could effectively estimate RZSM in semi-arid areas based on remotely sensed SSM data.

Soil moisture in root zone soil layers is one of the most important indicators of agricultural drought. Thus, monitoring agricultural drought requires not only knowledge of rainfall anomaly but also quantification of soil moisture. In this study, the effects of various methods of quantifying the green vegetation fraction green vegetation fraction (GVF) on the land-surface-model (LSM)-based soil moisture drought index (SMDI) were assessed using the harvest area data of the World Meteorological Organization together with the widely used vegetation health index and drought severity index. GVF data used in this study include monthly climatological GVF, weekly advanced very high-resolution radiometer (AVHRR)-normalized difference vegetation index-based and 8-daily moderate-resolution imaging spectroradiometer (MODIS) leaf area index (LAI)-based GVF. The results show that SMDI is optimized when using the near-real-time GVF and that LAI-based GVF increases the accuracy of SMDI when monitoring early agricultural drought. The study shows that we can be confident in the accuracy of signals of emerging drought, particularly during the rapid onset of drought.