Soil moisture can represent one of the most indispensable environmental variables during crop production in modern agriculture. Accurate and real-time monitoring of soil moisture content can directly dominate every stage of crop growth, development, and final maturation. Water and fertilizer practices can be effectively integrated to significantly enhance crop yield and product quality. Precious water resources can be conserved to alleviate the increasingly severe climate challenges in agricultural systems. It is often required to precisely implement on-demand irrigation schedules. However, conventional manual sampling and single-point sensor measurements cannot effectively capture the continuous spatiotemporal variations in soil moisture in the large-scale fields. This study aimed to systematically explore the significant, often overlooked impact of dynamic vegetation growth and development on soil moisture inversion within time-series analysis using improved change detection methods. Subtle variations in the radar backscattering coefficient were also selected to reliably infer soil moisture content beneath the surface. The surface roughness and vegetation cover were assumed over a much longer period at a gradual scale, compared with soil moisture, which fluctuated more frequently in response to irrigation, precipitation, and evaporation. Thus, the main fluctuations in the radar backscattering intensity were primarily attributed to soil moisture content rather than minor alterations in surface roughness or seasonal vegetation over long-term continuous observations. In practice, targeted corrections were applied to the radar backscattering coefficient and the soil moisture values under different surface cover conditions using a flexible piecewise function, according to real-time vegetation coverage data. Temporal dynamics were also estimated to effectively account for the interfering effects of vegetation. A composite vegetation index, NDEVI (Normalized Difference Enhanced Vegetation Index) was derived from the precise fitting of NDVI (Normalized Difference Vegetation Index) and EVI (Enhanced Vegetation Index) data. The accuracy and reliability of vegetation influence correction were significantly enhanced in soil moisture inversion, compared with single-vegetation-index correction. Abnormal events with sudden variations in the surface soil roughness were accurately identified using the DBSCAN clustering. The long-term time series of soil moisture data were divided into multiple intervals by invariant time series patterns. The experimental results showed that: 1) The radar backscattering coefficient and soil moisture content exhibited a steady upward trend as vegetation density increased gradually. Consequently, the segmentation function with fractional vegetation coverage effectively mitigated the adverse interference caused by varying vegetation. 2) The composite vegetation index after precise fitting effectively captured complex vegetation dynamics, compared with the single vegetation index. Correlation analysis between field-measured and inversion soil moisture demonstrated that the NDEVI vegetation correction significantly improved the overall performance of the model. Specifically, the coefficient of determination (R²) between measured and retrieved soil moisture values increased from 0.624 to 0.725, while the root mean square error (RMSE) decreased from 4.751% to 4.062% after the NDEVI correction. The improved change detection method outperformed the original conventional approach. The NDEVI correction effectively minimized the negative influence of vegetation dynamics in the change detection applications. Thereby, dependable, robust and accurate soil moisture was estimated after NDVI corrections. 3) The better performance was achieved in the soil moisture inversion over the invariant time segments. In contrast, serious variations in surface roughness over time severely compromised the accuracy of soil moisture content estimation using conventional approaches. Vegetation and surface roughness effects were effectively mitigated with change detection methods in vegetated agricultural areas, as these two factors severely interfered with detection accuracy by masking crucial soil-related signals. The practical value of change detection techniques was significantly enhanced to reduce the interference. Specifically, the retrieval accuracy was substantially enhanced, where the R² reached 0.892 within the invariant time series T3, and the RMSE was 2.503%, compared with conventional long time series approaches. The field experiments were fully validated to accurately monitor the soil moisture in real time. Meanwhile, the findings can provide a solid and reliable theoretical reference for time-series soil moisture inversion in complex agricultural environments, particularly for the water resource allocation and precision irrigation in efficient, eco-friendly and sustainable agriculture worldwide.

Optical remote sensing imagery can serve as a crucial data source in numerous fields. However, the susceptibility to weather conditions (like clouds and rain) can render the cloud contamination, leading to the significant influence on optical images. The image quality can be required to restore the spectral information in cloud-contaminated regions. In this study, the spectral information was reconstructed in the cloud-contaminated regions using an object-oriented approach. Synthetic aperture radar (SAR) data was integrated with the radar signals and land cover information, in order to serve as the constraints for the reconstruction. The distance matrix was calculated on the SAR images, and then transplant onto the optical images for the replacement. The pixel-level matching accuracy was enhanced to maximize the retention of spectral information from the original images. A solid foundation was provided for the accurate extraction of subsequent land surface information. The performance was also evaluated to verify the improved model. The comparative experiments were conducted with the traditional pixel replacement, weighted linear regression, and curvature-driven. Visual inspection was carried out over various scenes. The results revealed that the superior quality was achieved in the imagery reconstruction in the thick cloud areas and cloud shadows. Particularly, the consistency was maintained among various land cover pixels in the reconstructed areas by the object-oriented method. The boundaries and areas were accurately delineated in the various types of fine-grained land cover. Quantitative analysis was conducted to validate using some metrics, such as correlation coefficient, root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM). The spectral characteristic curves of the pixels were reconstructed to closely match those of the reference images, with the correlation coefficients exceeding 0.99. Notably, significant improvement was observed in the spectral curve recovery of vegetation pixels with the enhanced relative to the rest. The radar vegetation indices were optimized to employ an object-oriented matching mechanism during pixel reconstruction. The traditional pixel replacement model was optimized effectively. Furthermore, the band reflectance was closely resembled that of the reference images. Among the five bands of cloud-contaminated images after reconstruction, the highest correlation coefficients were observed with Band 2 and Band 3 reaching 0.925 and 0.922, respectively, and RMSE values of 0.009 and 0.007, respectively. The reconstructed images shared the minimal quality loss and high similarity to the reference images, with the highest PSNR and SSIM values across all bands. Specifically, the structural similarity values of the reconstructed Band 2 and Band 3 images were 0.902 and 0.910, respectively, with the PSNR values reaching 31.978 and 33.173, respectively. The superior image quality was obtained similar to reference images, which was consistence with spectral characteristics. The experimental results were used to the qualitatively and quantitatively validated the effectiveness of the reconstruction. The object-oriented approach can be expected to reconstruct the spectral information in the cloud-contaminated regions. The remotely sensed images were consistently produced with the higher spectral reconstruction accuracy in the different types of land cover and spectral bands. However, the replacing pixel spectral information was relied primarily on from single-image data. Some limitations was matched the effectiveness between cloudy and cloud-free regions, when reconstructing the large-scale, thick cloud areas in single remote sensing images. Additionally, the global searching can fail to the optimal reconstruction for the locally contaminated cloud pixels. Therefore, further investigation is required to determine the optimal local search range for the pixel matching using different extents of cloud contamination.