Soil Moisture Estimation Research Articles

Generation of root zone soil moisture from the integration of an all-weather satellite surface soil moisture estimates and an analytical model: A preliminary result in China

In addition to surface soil moisture (SSM) data, root zone soil moisture (RZSM) is particularly significant for irrigation decision-making and agricultural drought warnings since water uptake generally occurs through the root systems of plants. In this study, a daily/0.05° RZSM dataset covering the major land areas of China was generated from the synergistic use of satellite-derived SSM estimates and a RZSM-SSM analytical model. First, based on the SSM and RZSM datasets generated from the fifth generation of atmospheric reanalysis (ERA5-Land), the Markov Chain Monte Carlo algorithm was applied to optimize the soil moisture analytical relationship (SMAR) model to determine four essential parameters pixel-to-pixel over the study area. In addition, the optimized SMAR parameters were integrated with satellite-derived daily/0.05° SSM to predict the daily/0.05° RZSM in China. Finally, due to the lack of in situ RZSM measurements ground truth at a spatial resolution of 0.05°, two RZSM products, namely the Soil Moisture Active Passive (SMAP)-based RZSM and the China Meteorological Administration Land Data Assimilation System (CLDAS)-based RZSM, were used as references to preliminarily assess the estimated data. The results showed overall fair correlations between SMAP_RZSM and estimated RZSM (correlation coefficient R varying from 0.557 to 0.655), and between CLDAS_RZSM and estimated RZSM (correlation coefficient R varying from 0.496 to 0.596) over four typical days representing spring, summer, autumn, and winter in 2019. Although the proposed approach may overestimate or underestimate RZSM compared to the two referenced products in different seasons, an overall acceptable accuracy with unbiased root mean square error of ∼ 0.070–0.090 cm3/cm3 was obtained.

Machine learning‐driven microwave imaging for soil moisture estimation near leaky pipe

AbstractCharacterizing soil moisture around drip irrigation pipes is crucial for precise and optimized farming. Machine learning (ML) approaches are particularly suitable for this task as they can reduce uncertainties caused by soil conditions and the drip pipe positions, using features extracted from relevant datasets. This letter addresses local moisture detection in the vicinity of dripping pipes using a portable microwave imaging system. The employed ML approach is fed with two dimensional images generated using back projection as a radar‐based algorithm and the Born approximation as an inverse scattering method, based on spatio‐temporal (collected data at various positions over the soil surface and at different time points.) measurements at various frequencies. The study investigates the performance of K‐nearest neighbour (KNN) and convolutional neural networks (CNN) algorithms for moisture classification based on these imaging techniques. We also explore the potential of KNN and CNN for moisture estimation around the plant roots and in the presence of pebbles. In general, CNN outperforms KNN in moisture content detection from microwave data, especially after applying imaging algorithms. A combination of CNN as the ML approach and the back projection algorithm to provide training data, yielded accuracy more than other models for moisture content estimation. Also, the practical results demonstrate that our method can detect soil moisture with an estimation error of less than 10%.

Enhancing spatial resolution of satellite soil moisture data through stacking ensemble learning techniques

Soil moisture (SM) is a critical variable influencing various environmental processes, but traditional microwave sensors often lack the spatial resolution needed for local-scale studies. This study develops a novel stacking ensemble learning framework to enhance the spatial resolution of satellite-derived SM data to 1 km in the Urmia basin, a region facing significant water scarcity. We integrated in-situ SM measurements (obtained using time-domain reflectometry [TDR]), Soil Moisture Active Passive (SMAP) and Advanced Microwave Scanning Radiometer 2 (AMSR2) SM products, Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature and vegetation indices, precipitation records, and topography data. Ten base machine-learning models were evaluated using the Complex Proportional Assessment (COPRAS) method, and the top-performing models were selected as base learners for the stacking ensemble. The ensemble model, incorporating Random Forest, Gradient Boosting, and XGBoost, significantly improved SM estimation accuracy and resolution compared to individual models. The XGBoost and Gradient Boosting meta-models achieved the highest accuracy, with an unbiased root mean square error (ubRMSE) of 1.23% m3/m3 and a coefficient of determination (R2) of 0.97 during testing, demonstrating the exceptional predictive capabilities of our approach. SHapley Additive exPlanations (SHAP) analysis revealed the influence of each base model on the ensemble’s predictions, highlighting the synergistic benefits of combining diverse models. This study establishes new benchmarks for soil moisture monitoring by showcasing the potential of ensemble learning to improve the spatial resolution and accuracy of satellite-derived SM data, providing crucial insights for environmental science and agricultural planning, particularly in water-stressed regions.

Triple Collocation-Based Model Error Estimation of VIC-Simulated Soil Moisture at Spatial and Temporal Scales in the Continental United States in 2010–2020

Triple Collocation-Based Model Error Estimation of VIC-Simulated Soil Moisture at Spatial and Temporal Scales in the Continental United States in 2010–2020

Geographic analysis of soil moisture recorded and estimated in Erbil governorate

Calculating of soil moisture and its monitoring is one of the important processes of water balance and sustainable agriculture. The intended goal of this study is to determine soil moisture values in Erbil Governorate and reveal the correlation coefficient and the degree of influence between its values with the elevation and total annual rainfall. The importance of the study lies In its discussion of the accuracy of extracting soil moisture values using satellite images, by comparing its results with the soil moisture values recorded in the governorate’s climate stations, the study reached a set of conclusions, the most important of which is: The results of using satellite images to estimate soil moisture are inaccurate. It is closer than guessing, and the results of applying the linear regression process indicated that there was a significant statistical relationship between the soil moisture values recorded with the two factors of elevation and the total annual rainfall, where the probability values were less than 0.01 and the values of the degree of influence between them reached 0.583 and 0.491 for each of them, respectively.‏

Soil moisture estimation in the unsaturated zone using surface wave measurements and hybrid modeling framework

Abstract Soil moisture plays a critical role in influencing various facets of ecosystem dynamics. The preference for measuring soil moisture without physical intrusion has been desirable for precise assessments while minimizing disruptions to soil structural, hydraulic, and biological characteristics. In this study, we explored the potential of surface elastic waves as a proxy to estimate soil moisture profiles to a depth of 1.05 m at intervals of 0.1 m. We conducted a multichannel analysis of surface waves (MASW) survey and measured soil moisture at depths of 0.15 m and 0.35 m. To address the limited availability of soil moisture measurements, we developed a mechanistic soil moisture model as a substitute for measured soil moisture profiles. Our results showed that as soil moisture increased, the propagation of surface waves became more pronounced due to reduced frictional resistance. However, it was not straightforward to link measured surface wave responses and subsurface soil moisture profile. To address these challenges, we developed a convolutional neural network (CNN) with the inputs of the frequency-velocity and frequency-wavenumber images obtained from the measured surface waves. We found that the integration of MASW and CNN proved effective in estimating soil moisture profiles to a depth of 1.05 m at intervals of 0.1 m without causing disturbances to the soil (MAE = 0.0035 m3 m−3). This study suggested that the combined use of surface waves and CNN hold promise in measuring soil moisture profiles without physical disruptions. As such, the proposed approach could serve as a viable alternative to noninvasive soil moisture sensors.

An Integrated Approach to the Regional Estimation of Soil Moisture

Automatic or smart irrigation systems benefit irrigation water management. However, measurement sensor networks in automatic irrigation systems are complex, and maintenance is essential. Regional soil moisture estimation avoids the multiple measurements necessary when deploying an irrigation system. In this sense, a fuzzy estimation approach based on decision-making (FEADM) has been used to obtain soil moisture point estimates. However, FEADM requires intelligent weather adjustment based on spatial features (IWeCASF) to perform regional soil moisture estimation. The IWeCASF-FEADM integrated approach for regional soil moisture estimation is developed in this work. IWeCASF provides the inputs for FEADM. FEADM is performed R times; R is the number of checkpoints at which a point estimate is obtained. In this way, regional estimation is achieved when the set of R soil moisture point estimates is completed. Additionally, IWeCASF-FEADM considers the irrigation water records, which are not included in either method individually. This method can detect when the soil moisture is deficient in a region, allowing actions to prevent water stress. This regional estimation reduces an irrigation system’s operational and maintenance complexity. This integrated approach has been tested over several years by comparing the results of regional soil moisture estimation with measurements obtained at many points in the study region.

Generation and evaluation of energy and water fluxes from the HOLAPS framework: Comparison with satellite-based products during extreme hot weather

Improving our understanding of the energy and water exchanges between the land surface and the lower atmosphere (i.e. land–atmosphere interactions), and how climate change may affect them, is crucial to predict changes in temperature and precipitation extremes. Observations of energy and water fluxes at the land surface are typically retrieved from the eddy covariance method, which presents limitations related to spatial and temporal gaps, and the non-closure of the energy and water balances. Meanwhile, soil moisture (SM) products derived from satellite data have been widely used at regional and global scales, but they are limited to capture only surface soil water content and variations. The combination of remote sensing (RS) data and modelling frameworks is called to be the solution to improve the spatial coverage and vertical resolution of land–atmosphere interactions data, ensuring the energy and water balance closure. Here, we explore the combination of remote sensing and meteorological data with a physical-based modelling framework, the High resOlution Land Atmosphere Parameters from Space (HOLAPS). We used HOLAPS to produce hourly consistent estimates of energy and water fluxes over Europe at 5 km resolution. HOLAPS and other satellite-based evapotranspiration and sensible heat flux products from the literature are evaluated against the water balance method and eddy covariance measurements. HOLAPS SM estimates together with other RS-modelling products are also evaluated against ground-based measurements at the surface and in the root zone. The evaluation of HOLAPS ET estimates show similar performance to the other products with Kling–Gupta efficiency (KGE) ¿ -0.41 in comparison with eddy covariance measurements from FLUXNET in all seasons but in boreal winter. The simulation of H is more uncertain than for ET with KGE values ranging from -2.5 to 0.8 along the products and stations at monthly scales. HOLAPS reaches slightly better results than the rest of ET and H products at daily scales in summer (KGE ¿ 0.3 for ET and KGE ¿ 0.0 for H) and during hot conditions (KGE ¿ 0.2 for ET and KGE ¿-0.2 for H), while the state-of-the-art products show KGE ¿ 0.1 for ET and KGE ¿ -0.41 for H in summer and KGE ¿ -0.1 for ET and KGE ¿ -0.6 for H during hot conditions. All products evaluated here yield a reasonable performance (KGE ¿-0.41 at most sites) in simulating SM at the surface and in the root zone. Our results expose the need for further investigating and improving product performances during extreme conditions. The good performance of HOLAPS together with its inherent advantages (RS data driven, high temporal and spatial resolution, spatial and temporal continuity, soil moisture at different depths and long-term consistent evapotranspiration and sensible heat flux estimates) support its use for agricultural and forest management activities as well as to study land–atmosphere interactions based on Earth Observations.

Estimating soil moisture from environmental gamma radiation monitoring data

AbstractSoil moisture (SM) information is invaluable for a wide range of applications, including weather forecasting, hydrological and land surface modeling, and agricultural production. However, there is still a lack of sensing information that adequately represents root‐zone SM for longer periods and larger spatial scales. One option for root‐zone SM observation is terrestrial gamma radiation (TGR), as it is inversely related to SM. Hence, the near real‐time data of more than 5000 environmental gamma radiation (EGR) monitoring stations archived by the EUropean Radiological Data Exchange Platform (EURDEP) is a potential source to develop a root‐zone SM product for Europe without extra investments in SM sensors. This study aims to investigate to what extent the EURDEP data can be used for SM estimation. For this, two EGR monitoring stations were equipped with in situ SM sensors to measure reference SM. The terrestrial component of EGR was extracted after eliminating the contributions of rain washout and secondary cosmic radiation, and used to obtain a functional relationship with SM. We predicted the weekly volumetric SM with a root mean square error of 7%–9% from TGR measurements. Nevertheless, we believe that this technique, due to its greater penetration depth and long data legacy, can provide useful data complementary to satellite‐based remote sensing techniques to estimate root‐zone SM at the continental scale.

Estimation of surface soil moisture from Sentinel-1 synthetic aperture radar imagery using machine learning method

Surface soil moisture (SM) is a crucial variable representing the water content in soil at the topmost soil layer. Accurate data of SM are essential for various purposes, including the monitoring of drought, vegetation modeling, weather forecasting, and agriculture management. Over the past decades, microwave remote sensing has been employed to estimate SM at large scales, with the Sentinel-1 satellite mission recently offering Synthetic Aperture Radar (SAR) data and enabling to estimate SM at high spatial resolution. Machine learning (ML) techniques have further enhanced these estimations, with random forest (RF) emerging as a promising method due to its strong capabilities. However, the performance of RF in estimating SM with satellite data has not yet been thoroughly evaluated across large areas. This study presents a new RF-based model for estimating SM over Europe with SAR data from Sentinel-1, along with the climate and terrain data. The predictions from the RF model were compared against the ground measurements from the International Soil Moisture Network (ISMN), Integrated Carbon Observation System (ICOS), and official SMAP/Sentinel-1 SM products. The results demonstrated that the RF model yielded accurate predictions with a Pearson's correlation coefficient (R) of 0.847 outperforming the official SMAP/Sentinel-1 product at spatial resolutions of 1 km and 3 km, which achieved R values of 0.599 and 0.616, respectively. Additionally, the impact of vegetation cover that is represented by using multiple satellite vegetation products on the RF model was investigated. Despite a moderate correlation between backscattering coefficients and vegetation cover, no correlation was found between the RF model's errors and vegetation cover. The results suggest that the RF model and Sentinel-1 SAR data can be used to provide SM estimations at high spatial resolution, characterizing the fine-scale variations in SM, to support various applications such as precision agriculture at the small, localized scales.

Prototype of Circular Split Ring Resonator-Based Sensor for Estimating Soil Moisture as a Function of Soil Particle Distribution

Prototype of Circular Split Ring Resonator-Based Sensor for Estimating Soil Moisture as a Function of Soil Particle Distribution

Remote sensing retrieval of surface soil moisture in Mu Us Sandy Land based on optical trapezoid model

Abstract Maowuosu sandland ecosystem is fragile, and moisture is a key factor restricting the growth and development of sandland plants and ecological construction in semi-arid areas. Therefore, this study constructed the eigenspace based on the data of the 4th period of 2016, fitted the dry and wet edge equations of the eigenspace, calculated the OPTRAM, and utilized the measured in situ soil moisture data from various depths during the corresponding period. The OPTRAM was regressed to construct a model for estimating soil moisture. This model was then subjected to a series of validation procedures to ensure its accuracy. The coefficients for the shortwave infrarouges conversion reflection coefficient (STR) - standardized differential vegetation index (NDVI) feature space dry and wet edge fits increased with the increase of the month, where the dry and the R2 for the wet side in September was 0.88 and 0.87, respectively. OPTRAM and the measured soil moisture content data in the surface layer were all correlated to some extent, with correlation coefficients above 0.45. The OPTRAM model is more accurate than other models in inverting in situ moisture content at the 0∼10 cm depths within this area.

Mesoscale soil moisture measurements along the rover route using the mobile cosmic-ray neutron sensing in the eastern Tibetan Plateau

Water resources in the soil play an essential role in hydrological processes and ecosystem functions on the Tibetan Plateau. However, accurately measuring soil moisture distribution in this region presents challenges due to the diverse ecosystem types, complex terrain, and harsh environmental conditions. In this study, we introduce an approach for estimating mesoscale soil moisture in the Qilian Mountains (QLM) region of the eastern Tibetan Plateau using a cosmic-ray neutron rover. Soil moisture estimates derived from neutron count rates, newly adjusted by vegetation effects, demonstrated good agreement with soil moisture measurements obtained through soil sampling at 26 calibration sites across the region (RMSE = 0.025 g g−1). The calibration parameter N0_NDVI was 443 cpm in the QLM. Utilizing NDVI as vegetation correction method showed potential improvements in the accuracy of converting neutron counts to soil moisture across the diverse mountainous ecosystem types. The newly developed calibration equation provided a high-precision, high spatial resolution soil moisture transect across various landscapes measured by the rover. The average mesoscale soil moisture along the rover route varied by ecosystem types, with values of 0.10 g/g in deserts, 0.17 g/g in grasslands, 0.13 g/g in forests, 0.18 g/g in subalpine shrublands, and 0.20 g/g in croplands. Land cover types emerged as crucial determinants of mesoscale soil moisture variability in the QLM region. These findings offer valuable mesoscale soil moisture data and new insights into soil water information at the transect scale across diverse ecosystem types in the Tibetan Plateau.

A soil moisture experiment for validating high-resolution satellite products and monitoring irrigation at agricultural field scale

Validating the satellite soil moisture products is always an active research topic for the application of the products and improvement of the retrieval algorithms, attracting extensive attention. Nevertheless, seldom existing validation activities focus on the validation of high-resolution soil moisture products at the fine scale. To this end, an experiment was conducted in the middle stream of the Heihe River Basin in northwestern China in August to October of 2021, aiming to validate high-resolution satellite remote sensing products of soil moisture. The paper introduces the design, composite, and preliminary results of the experiment. A soil moisture observation network was established with two kinds of sensors (CS616 and Stevens Hydra Probe) validated against soil core measurements. Several synchronized campaigns were performed, and data were collected to validate the SMAP/Sentinel-1 L2 Radiometer/Radar 30-Second Scene 3 and 1 km EASE-Grid Soil Moisture (SPL2SMAP_S) products. Besides, an optical trapezoid model (OPTRAM) and collected Sentinel-2 data were applied to estimate soil moisture and to map irrigated area. Preliminary analyses show that: 1) Steven probes perform best, with an RMSE = 0.040 m3m−3 and ubRMSE=0.034 m3m−3; 2) Both the SPL2SMAP_S products at 3 km and 1 km show large RMSE (0.128 m3m−3 for 3 km and 0.158 m3m−3 for 1 km) and ubRMSE (0.115 m3m−3 for 3 km and 0.158 m3m−3 for 1 km); 3) The OPTRAM retrievals over bare surface present relatively smaller RMSE (0.06 m3m−3) and ubRMSE (0.057 m3m−3), while retrievals over vegetated croplands present a relatively large RMSE/ubRMSE (0.083/0.083 m3m−3), and the retrievals can identify the irrigated area at field scale. Overall, the experiment provides fruitful methodologies and datasets for the validation of high-resolution remote sensing products, benefiting the development and improvement of soil moisture retrieval algorithms and products to support irrigation scheduling and management at a precision agricultural scale in the future.

Machine Learning Modelling for Soil Moisture Retrieval from Simulated NASA-ISRO SAR (NISAR) L-Band Data

Soil moisture is a critical factor that supports plant growth, improves crop yields, and reduces erosion. Therefore, obtaining accurate and timely information about soil moisture across large regions is crucial. Remote sensing techniques, such as microwave remote sensing, have emerged as powerful tools for monitoring and mapping soil moisture. Synthetic aperture radar (SAR) is beneficial for estimating soil moisture at both global and local levels. This study aimed to assess soil moisture and dielectric constant retrieval over agricultural land using machine learning (ML) algorithms and decomposition techniques. Three polarimetric decomposition models were used to extract features from simulated NASA-ISRO SAR (NISAR) L-Band radar images. Machine learning techniques such as random forest regression, decision tree regression, stochastic gradient descent (SGD), XGBoost, K-nearest neighbors (KNN) regression, neural network regression, and multilinear regression were used to retrieve soil moisture from three different crop fields: wheat, soybean, and corn. The study found that the random forest regression technique produced the most precise soil moisture estimations for soybean fields, with an R2 of 0.89 and RMSE of 0.050 without considering vegetation effects and an R2 of 0.92 and RMSE of 0.042 considering vegetation effects. The results for real dielectric constant retrieval for the soybean field were an R2 of 0.89 and RMSE of 6.79 without considering vegetation effects and an R2 of 0.89 and RMSE of 6.78 with considering vegetation effects. These findings suggest that machine learning algorithms and decomposition techniques, along with a semi-empirical technique like Water Cloud Model (WCM), can be effective tools for estimating soil moisture and dielectric constant values precisely. The methodology applied in the current research contributes essential insights that could benefit upcoming missions, such as the Radar Observing System for Europe in L-band (ROSE-L) and the collaborative NASA-ISRO SAR (NISAR) mission, for future data analysis in soil moisture applications.

Assessment of the effects of winter wheat scattering on SAR backscatter for soil moisture estimation based on a radiative transfer model

ABSTRACT This study evaluated the potential of the Single Scattering Radiative Transfer (SSRT) model coupled with the Oh model to retrieve surface soil moisture (SSM) in two drip-irrigated wheat fields in the Tensift al Haouz plain, over three growing seasons (2016–2019). This research focuses on evaluating isotropic scattering and Rayleigh scattering by calibrating the coupled SSRT_Oh model, using data gathered on the calibrated field. The data includes measured SSM at 5 cm depth, Leaf Area Index (LAI) and vegetation height (H). The aim is to fit the extinction coefficient through comparing simulated and Sentinel-1 backscatter, at VV and VH polarizations. The validated field data were used to retrieve SSM. Calibration revealed the best retrieval for Rayleigh scattering, at VV polarization, with an RMSE of 1.25 dB, a correlation coefficient (r) of 0.86, and a bias of 0.1 dB, whereas, the isotropic approach yielded r, RMSE and bias values of 0.83, 1.37 dB and −0.01 dB, respectively. Rayleigh’s performance remained unchanged throughout the inversion process for SSM retrieval, at VV polarization, with r of 0.87 against 0.86 for isotropic scattering. To enhance our findings, the introduction of dynamic extinction parameter and exclusive use of Sentinel-1 data to describe vegetation could improve SSM retrieval.

Enhanced root zone soil moisture monitoring using multitemporal remote sensing data and machine learning techniques

Accurate root zone soil moisture (RZSM) estimation using remote sensing (RS) in areas with dense vegetation is essential for real-time field monitoring and precise irrigation scheduling. Traditional methods often face challenges due to the dense crop cover and the complexity of soil and climate interactions. These challenges include the coarse spatial resolution of available soil moisture products, the influence of vegetation and surface roughness, and the difficulty of estimating RZSM from surface data. Aiming to overcome these limitations, two RZSM estimation methods were developed by combining synthetic aperture radar (SAR) data from Sentinel-1 (VV and VH polarizations) and optical and thermal RS data from Landsat-8. These data sources were used in conjunction with various machine learning (ML) models such as M5-pruned (M5P), support vector regression (SVR), extreme gradient boosting (XGBoost), and random forest regression (RFR) to improve the accuracy of soil moisture estimation. In addition to RS data, soil physical and hydraulic properties, meteorological variables, and topographical parameters were selected as inputs to the ML models for estimating the RZSM of sugarcane crops in Khuzestan, Iran. This study identified the temperature vegetation dryness index (TVDI) as a critical parameter for estimating RZSM in combination with the Sentinel-1 SAR data under high vegetation conditions. In both methods, the RFR algorithm outperformed, with similar performance, the XGBoost, SVR, and M5P algorithms in estimating soil surface moisture (R2 = 0.89, RMSE = 0.04 cm3cm−3). However, the accuracy of the RFR algorithm decreased with increasing depth for both the optical-thermal and combined SAR and optical-thermal RS data. This decrease was more pronounced in the combined approach, particularly for the root zone, where the RMSE reached approximately 0.073 cm3cm−3. Accordingly, the key findings demonstrated that the optical-thermal RS data outperformed the SAR RS data for retrieving RZSM in high-vegetated areas. However, combining TVDI with SAR data is a substantial improvement that opens a new path in radar-based RZSM estimation methods under high vegetation conditions.

Estimation of Soil Moisture during Different Growth Stages of Summer Maize under Various Water Conditions Using UAV Multispectral Data and Machine Learning

Accurate estimation of soil moisture content (SMC) is vital for effective farmland water management and informed irrigation decision-making. The utilization of unmanned aerial vehicle (UAV)-based remote sensing technology to monitor SMC offers advantages such as mobility, high timeliness, and high spatial resolution, thereby compensating for the limitations of in-situ observations and satellite remote sensing. However, previous research has primarily focused on SMC diagnostics for the entire crop growth period, often neglecting the development of targeted soil moisture modeling paradigms that account for the specific characteristics of the canopy and root zone at different growth stages. Furthermore, the variations in soil moisture status between fields, resulting from the hysteresis of water flow in irrigation channels at different levels, may influence the development of soil moisture modeling schemes, an area that has been seldom explored. In this study, SMC models based on UAV spectral information were constructed using Random Forest (RF) and Particle Swarm Optimization-Support Vector Machine (PSO-SVM) algorithms. The soil moisture modeling paradigms (i.e., input–output mapping) under different growth stages and soil moisture conditions of summer maize were systematically compared and discussed, along with the corresponding physical interpretability. Our results showed that (1) the SMC modeling schemes differ significantly across the various growth stages, with distinct input–output mappings recommended for the early (i.e., jointing, tasselling, and silking stages), middle (i.e., blister and milk stages), and late (i.e., maturing stage) periods. (2) these machine learning-based models performed best at the jointing stage, while subsequently, their accuracy generally exhibited a downward trend as the maize grew. (3) the RF model demonstrates superior robustness in estimating soil moisture status across different fields (moisture conditions), achieving optimal estimation accuracy in fields with overall higher SMC in line with the PSO-SVM model. (4) unlike the RF model’s robustness in spatial SMC diagnostics, the PSO-SVM model more reliably captured the temporal dynamics of SMC across different growth stages of summer maize. This study offers technical references for future modelers in UAV-based SMC modeling across various spatial and temporal conditions, addressing both the types of models as well as their input features.

Soil moisture inversion based on multiple drought indices and RBFNN: A case study of northern Hebei Province

Drought has a significant impact on crop growth and productivity, highlighting the critical need for precise and timely soil moisture estimation to mitigate agricultural losses. This study focuses on soil moisture retrieval in northern Hebei Province during July 2012, utilizing eight widely employed remote sensing drought indices derived from MODIS satellite data. These indices were cross-referenced with measured soil moisture levels for analysis. Based on their correlation coefficients, a composite remote sensing drought index set comprising six indices was identified. Furthermore, a radial basis function neural network (RBFNN) was employed to estimate soil relative humidity. The accuracy evaluation of the soil moisture estimation model, which integrates multiple remote sensing drought indices and the RBFNN, demonstrated clear superiority over models relying on single drought indices. The model achieved an average estimation accuracy of 87.54 % for soil relative humidity at a depth of 10 cm (SM10) and 87.36 % for a 20 cm depth (SM20). The root mean square errors (RMSE) for the test sets were 0.093 and 0.092, respectively. Validation results for July 2013 indicated that the inversion accurately reflected the actual soil moisture conditions, effectively capturing dynamic moisture changes. These results fully verify the reliability and practicability of the model. These findings introduce a novel approach to local agricultural soil moisture estimation, with significant implications for enhancing agricultural water resource management and decision-making processes.

Noncontact Soil Moisture Estimation Using Continuous Wave Radar and Deep Learning

Noncontact Soil Moisture Estimation Using Continuous Wave Radar and Deep Learning