Zhao-Liang Li’s research while affiliated with Chinese Academy of Agricultural Sciences and other places

Water use efficiency (WUE), as an important metric for ecosystem resilience, has been identified to play a significant role in the coupling of carbon and water cycles. The farming–pastoral ecotone of Northern China (FPENC), which is highly susceptible to drought due to water scarcity, has long been recognized as an ecologically fragile zone. The ecological restoration projects in China have mitigated land degradation and maintain the sustainability of dryland. However, the process of greening in drylands has the potential to impact water availability. A comprehensive analysis of the WUE in the FPENC can help to understand the carbon absorption and water consumption. Using gross primary production (GPP) and evapotranspiration (ET) data from a MODerate resolution Imaging Spectroradiometer (MODIS), alongside biophysical variables data and land cover information, the spatio-temporal variations in WUE from 2003 to 2022 were examined. Additionally, its driving force and the ecosystem resilience were also revealed. Results indicated that the annual mean of WUE fluctuated between 0.52 and 2.60 gC kgH2O⁻¹, showing a non-significant decreasing trend across the FPENC. Notably, the annual averaged WUE underwent a significant decline before 2012 (p < 0.05), and then showed a slight increased trend (p = 0.14) during the year afterward (i.e., 2013–2022). In terms of climatic controls, temperature (Temp) and soil volumetric water content (VSWC) dominantly affected WUE from 2003 to 2012; VPD (vapor pressure deficit), VSWC, and Temp showed comprehensive controls from 2013 to 2022. The findings suggest that a wetter atmosphere and increased soil moisture contribute to the decline in WUE. In total, 59.2% of FPENC was shown to be non-resilient, as grassland occupy the majority of the area, located in Mu Us Sandy land and Horqin Sand Land. These results underscore the importance of climatic factors in the regulation WUE over FPENC and highlight the necessity for focused research on WUE responses to climate change, particularly extreme events like droughts, in the future.

Effective monitoring and management of potato late blight (PLB) is essential for sustainable agriculture. This study describes a methodology to improve PLB identification on a large scale. The method combines unsupervised and supervised machine learning algorithms. To improve the monitoring accuracy of the PLB regression model, the study used the K-Means algorithm in conjunction with morphological operations to identify potato growth areas. Input data consisted of monthly NDVI from Sentinel-2 and VH bands from Sentinel-1 (covering the year 2021). The identification results were validated on 221 field survey samples with an F1 score of 0.95. To monitor disease severity, we compared seven machine learning models: CART decision trees (CART), Gradient Tree Boosting (GTB), Random Forest (RF), single optical data Random Forest Time series model (TS–RF), single radar data Random Forest Time series model (STS–RF), multi-source data Gradient Tree Boosting Time series model (MSTS–GTB), and multi-source data Random Forest Time series model (MSTS–RF). The MSTS–RF model was the best performer, with a validation RMSE of 20.50 and an R² of 0.71. The input data for the MSTS–RF model consisted of spectral indices (NDVI, NDWI, NDBI, etc.), radar features (VH-band and VV-band), texture features, and Sentinel-2 bands synthesized as a monthly time series from May to September 2021. The feature importance analysis highlights key features for disease identification: the NIR band (B8) for Sentinel-2, DVI, SAVI, and the VH band for Sentinel-1. Notably, the blue band data (458–523 nm) were critical during the month of May. These features are related to vegetation health and soil moisture are critical for early detection. This study presents for the first time a large-scale map of PLB distribution in China with an accuracy of 10 m and an RMSE of 26.52. The map provides valuable decision support for agricultural disease management, demonstrating the effectiveness and practical potential of the proposed method for large-scale monitoring.