This paper proposes a combined approach wherein the optical, near-infrared, and thermal infrared data from the Landsat 8 satellite and the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) global digital elevation model (GDEM) data are fused for soil moisture mapping under sparse sampling conditions, based on the Bayesian maximum entropy (BME) framework. The study was conducted in three stages. First, based on the maximum entropy principle of the information theory, a Lagrange multiplier was introduced to construct general knowledge, representing prior knowledge. Second, a principal component analysis (PCA) was conducted to extract three principal components from the multi-source data mentioned above, and an innovative and operable discrete probability method based on a fuzzy probability matrix was used to approximate the probability relationship. Thereafter, soft data were generated on the basis of the weight coefficients and coordinates of the soft data points. Finally, by combining the general knowledge with the prior information, hard data (HD), and soft data (SD), we completed the soil moisture mapping based on the Bayesian conditioning rule. To verify the feasibility of the combined approach, the ordinary kriging (OK) method was taken as a comparison. The results confirmed the superiority of the soil moisture map obtained using the BME framework. The map revealed more detailed information, and the accuracies of the quantitative indicators were higher compared with that for the OK method (the root mean squared error (RMSE) = 0.0423 cm³/cm³, mean absolute error (MAE) = 0.0399 cm³/cm³, and Pearson correlation coefficient (PCC) = 0.7846), while largely overcoming the overestimation issue in the range of low values and the underestimation issue in the range of high values. The proposed approach effectively fused inexpensive and easily available multi-source data with uncertainties and obtained a satisfactory mapping accuracy, thus demonstrating the potential of the BME framework for soil moisture mapping using multi-source data.

Vegetation classification has always been the focus of remote sensing applications, especially for tropical regions with fragmented terrain, cloudy and rainy climates, and dense vegetation. How to effectively classify vegetation in tropical regions by using multi-spectral remote sensing with high resolution and red-edge spectrum needs to be further verified. Based on the experiment in Wenchang, Hainan, China, which is located in the tropical monsoon region, and combined with the ZY-1 02D 2.5 m fused images in January, March, July, and August, this paper discusses whether NDVI and four red-edge vegetation indices (VIs), CIre, NDVIre, MCARI, and TCARI, can promote vegetation classification and reduce the saturation. The results show that the schemes with the highest classification accuracies in all phases are those in which the red-edge VIs are involved, which suggests that the red-edge VIs can effectively contribute to the classification of vegetation. The maximum accuracy of the single phase is 86%, and the combined accuracy of the four phases can be improved to 92%. It has also been found that CIre and NDVIre do not reach saturation as easily as NDVI and MCARI in July and August, and their ability to enhance the separability between different vegetation types is superior to that of TCARI. In general, red-edge VIs can effectively promote vegetation classification in tropical monsoon regions, and red-edge VIs, such as CIre and NDVIre, have an anti-saturation performance, which can slow down the confusion between different vegetation types due to saturation.

This paper proposes a combined approach comprising a set of methods for the high-precision mapping of soil moisture in a study area located in Jiangsu Province of China, based on the Chinese C-band synthetic aperture radar data of GF-3 and high spatial-resolution optical data of GF-1, in situ experimental datasets and background knowledge. The study was conducted in three stages: First, in the process of eliminating the effect of vegetation canopy, an empirical vegetation water content model and a water cloud model with localized parameters were developed to obtain the bare soil backscattering coefficient. Second, four commonly used models (advanced integral equation model (AIEM), look-up table (LUT) method, Oh model, and the Dubois model) were coupled to acquire nine soil moisture retrieval maps and algorithms. Finally, a simple and effective optimal solution method was proposed to select and combine the nine algorithms based on classification strategies devised using three types of background knowledge. A comprehensive evaluation was carried out on each soil moisture map in terms of the root-mean-square-error (RMSE), Pearson correlation coefficient (PCC), mean absolute error (MAE), and mean bias (bias). The results show that for the nine individual algorithms, the estimated model constructed using the AIEM (m_v1) was significantly more accurate than those constructed using the other models (RMSE = 0.0321 cm³/cm³, MAE = 0.0260 cm³/cm³, and PCC = 0.9115), followed by the Oh model (m_v5) and LUT inversion method under HH polarization (m_v2). Compared with the independent algorithms, the optimal solution methods have significant advantages; the soil moisture map obtained using the classification strategy based on the percentage content of clay was the most satisfactory (RMSE = 0.0271 cm³/cm³, MAE = 0.0225 cm³/cm³, and PCC = 0.9364). This combined method could not only effectively integrate the optical and radar satellite data but also couple a variety of commonly used inversion models, and at the same time, background knowledge was introduced into the optimal solution method. Thus, we provide a new method for the high-precision mapping of soil moisture in areas with a complex underlying surface.

Soil moisture content (SMC) plays an essential role in geoscience research. The SMC can be retrieved using an artificial neural network (ANN) based on remote sensing data. The quantity and quality of samples for ANN training and testing are two critical factors that affect the SMC retrieving results. This study focused on sample optimization in both quantity and quality. On the one hand, a sparse sample exploitation (SSE) method was developed to solve the problem of sample scarcity, resultant from cloud obstruction in optical images and the malfunction of in situ SMC-measuring instruments. With this method, data typically excluded in conventional approaches can be adequately employed. On the other hand, apart from the basic input parameters commonly discussed in previous studies, a couple of new parameters were optimized to improve the feature description. The Sentinel-1 SAR and Landsat-8 images were adopted to retrieve SMC in the study area in eastern Austria. By the SSE method, the number of available samples increased from 264 to 635 for ANN training and testing, and the retrieval accuracy could be markedly improved. Furthermore, the optimized parameters also improve the inversion effect, and the elevation was the most influential input parameter.

Soil moisture (SM) estimates are essential for drought monitoring, hydrological modeling, and climate resilience planning applications. While satellite and model-derived SM products effectively capture SM dynamics, their coarse spatial resolutions (~10–36 km) hinder their ability to represent SM variability in heterogeneous landscapes influenced by local factors. This study proposes a novel downscaling framework that employs an Artificial Neural Network (ANN) on a cloud-computing platform to improve the spatial resolution and representation of multi-source SM datasets. A data analysis was conducted by integrating Google Earth Engine (GEE) with the computing capabilities of the python language through Google Colab. The framework downscaled Soil Moisture Active Passive (SMAP), European Centre for Medium-Range Weather Forecasts Reanalysis 5th Generation (ERA5-Land), and Famine Early Warning Systems Network Land Data Assimilation System (FLDAS) at 500 m for Kenya, East Africa. This was achieved by leveraging ten input variables comprising elevation, slope, surface albedo, vegetation, soil texture, land surface temperatures (day and night), evapotranspiration, and geolocations. The coarse SM datasets exhibited spatiotemporal consistency, with a standard deviation below 0.15 m³/m³, capturing over 95% of the variability in the original data. Validation against in situ SM data at the station confirmed the framework’s reliability, achieving an average UbRMSE of less than 0.04 m³/m³ and a correlation coefficient (r) over 0.52 for each downscaled dataset. Overall, the framework improved significantly in r values from 0.48 to 0.64 for SMAP, 0.47 to 0.63 for ERA5-Land, and 0.60 to 0.69 for FLDAS. Moreover, the performance of FLDAS and its downscaled version across all climate zone is consistent. Despite the uncertainties among the datasets, the framework effectively improved the representation of SM variability spatiotemporally. These results demonstrate the framework’s potential as a reliable tool for enhancing SM applications, particularly in regions with complex environmental conditions.

High-spatiotemporal-resolution and accurate soil moisture (SM) data are crucial for investigating climate, hydrology, and agriculture. Existing SM products do not yet meet the demands for high spatiotemporal resolution. The objective is to develop and evaluate a retrieval framework to derive SM estimates with high spatial (100 m) and temporal (<3 days) resolution that can be used on a national scale in China. Therefore, this study integrates multi-source data, including optical remote sensing (RS) data from Sentinel-2 and Landsat-7/8/9, synthetic aperture radar (SAR) data from Sentinel-1, and auxiliary data. Four machine learning and deep learning algorithms are applied, including Random Forest Regression (RFR), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM) networks, and Ensemble Learning (EL). The integrated framework (IF) considers three feature scenarios (SC1: optical RS + auxiliary data, SC2: SAR + auxiliary data, SC3: optical RS + SAR + auxiliary data), encompassing a total of 33 features. The results are as follows: (1) The correlation coefficients (r) between auxiliary data (such as sand fraction, r = −0.48; silt fraction, r = 0.47; and evapotranspiration, r = −0.42), SAR features (such as the backscatter coefficients for VV-pol (${\sigma }_{vv}^0$), r = 0.47), and optical RS features (such as Shortwave Infrared Band 2 (SWIR2) reflectance data from Sentinel-2 and Landsat-7/8/9, r = −0.39) with observed SM are significant. This indicates that multi-source data can provide complementary information for SM monitoring. (2) Compared to XGBoost and LSTM, RFR and EL demonstrate superior overall performance and are the preferred models for SM prediction. Their R² for the training and test sets exceed 0.969 and 0.743, respectively, and their ubRMSE are below 0.022 and 0.063 m³/m³, respectively. (3) The SM prediction accuracy is highest for the scenario of optical + SAR + auxiliary data, followed by SAR + auxiliary data, and finally optical + auxiliary data. (4) With an increasing Normalized Difference Vegetation Index (NDVI) and SM values, the trained models exhibit a general decrease in prediction performance and accuracy. (5) In 2021 and 2022, without considering cloud cover, the IF theoretically achieved an SM revisit time of 1–3 days across 95.01% and 96.53% of China’s area, respectively. However, SC1 was able to achieve a revisit time of 1–3 days over 60.73% of China’s area in 2021 and 69.36% in 2022, while the area covered by SC2 and SC3 at this revisit time accounted for less than 1% of China’s total area. This study validates the effectiveness of combining multi-source RS data with auxiliary data in large-scale SM monitoring and provides new methods for improving SM retrieval accuracy and spatiotemporal coverage.