Shichang Liu

Accurate and timely mapping of paddy rice is essential for agricultural management, food security, and climate-resilient policy. However, high-precision mapping remains challenging in subtropical monsoon regions due to persistent cloud cover, long revisit intervals, and striping noise, which compromise satellite data quality and availability. To address these limitations, a rice mapping framework suitable for different geographical environments was developed based on a random forest (RF) by combining time-series harmonic analysis (HANTS) with Sentinel-1 and Sentinel-2 multi-source data. To address these limitations, a rice mapping classification algorithm for different geographical environments was developed by combining Harmonic Analysis of Time Series (HANTS) with Sentinel-1/2 multi-source data. The research obtained annual maps of single-season and double-season rice in the research area from 2019 to 2024, with a spatial resolution of 10 m. The results indicated that the Sentinel-1, Sentinel-2, GEE, and HANTS algorithm can effectively support the yearly mapping of single- and double-season paddy rice in Anhui Province, China. The resultant paddy rice map has a high accuracy with overall accuracies exceeding 92% and Kappa coefficients above 0.84. HANTS effectively captures key phenological features of paddy rice, and it can especially enhance the discrimination between single- and double-season rice; compared to existing rice mapping products, the proposed approach reduces classification errors by an average of 3.92% in six major rice-producing cities, each with cultivation areas exceeding 1 million hectares; spatial correlation analysis indicates substantial heterogeneity in rice cultivation patterns across northern, central, and southern Anhui, associated with both biophysical and anthropogenic factors. These results indicate that integrating phenological data with machine learning can enhance the accuracy of long-term, high-resolution crop monitoring, and annual rice maps will offer valuable support for food security assessment, water resource management, and policy planning.

Coastal wetlands play an important carbon sequestration role in China’s “carbon peaking” and “carbon neutrality” goals. Monitoring aboveground biomass (AGB) is crucial for wetland management. Satellite remote sensing enables efficient retrieval of AGB. However, a variety of statistical models can be used for biomass inversion, depending on factors such as the vegetation type and inversion method. In this study, Landsat 8 Operational Land Imager (OLI) images were preprocessed in the study area through radiation calibration and atmospheric correction for modeling. In terms of model selection, 13 different models, including the univariate regression model, multiple regression model, and machine learning regression model, were compared in terms of their accuracy in estimating the biomass of various wetland vegetation types under their respective optimal parameters. The findings revealed that: (1) the regression models varied across vegetation types, with the accuracy of the biomass estimates decreasing in the order of Scirpus spp. > Spartina alterniflora > Phragmites australis; (2) overall modeling, without distinguishing vegetation types, addressed the challenges of limited samples availability and sampling difficulty. Among them, the random forest regression model outperformed the others in estimating wet and dry AGB with R² values of 0.806 and 0.839, respectively. (3) Comparatively, individual modeling of vegetation types can better reflect the biomass of each wetland vegetation type, especially the dry AGB of Scirpus spp., whose R² and RMSE values increased by 0.248 and 11.470 g/m², respectively. This study evaluates the impact of coastal saltmarsh vegetation types on biomass estimation, providing insights into biomass dynamics and valuable support for wetland conservation and restoration, with potential contributions to global habitat assessment models and international policies like the 30x30 Conservation Agenda.