With the development of multisource satellite platforms and the deepening of remote sensing applications, the growing demand for high-spatial resolution and high-temporal resolution remote sensing images has aroused extensive interest in spatiotemporal fusion research. However, reducing the uncertainty of fusion results caused by sensor inconsistencies and input data preprocessing is one of the challenges in spatiotemporal fusion algorithms. Here, we propose a novel sensor bias correction method to correct the input data of the spatiotemporal fusion model through a machine learning technique learning the bias between different sensors. Taking the normalized difference vegetation index (NDVI) images with low-spatial resolution (MODIS) and high-spatial resolution (Landsat) as the basic data, we generated the neighborhood gray matrices from the MODIS image and established the image bias pairs of MODIS and Landsat. The light gradient boosting machine (LGBM) regression model was used for the nonlinear fitting of the bias pairs to correct MODIS NDVI images. For three different landscape areas with various spatial heterogeneities, the fusion of the bias-corrected MODIS NDVI and Landsat NDVI was conducted by using the spatiotemporal adaptive reflection fusion model (STARFM) and the flexible spatiotemporal data fusion method (FSDAF), respectively. The results show that the sensor bias correction method can enhance the spatially detailed information in the input data, significantly improve the accuracy and robustness of the spatiotemporal fusion technology, and extend the applicability of the spatiotemporal fusion models.

Identifying the changes in dryland functioning and the drivers of those changes are critical for global ecosystem conservation and sustainability. The arid and semi-arid regions of northern China (ASARNC) are located in a key area of the generally temperate desert of the Eurasian continent, where the ecological conditions have experienced noticeable changes in recent decades. However, it is unclear whether the ecosystem functioning (EF) in this region changed abruptly and how that change was affected by natural and anthropogenic factors. Here, we estimated monthly rain use efficiency (RUE) from MODIS NDVI time series data and investigated the timing and types of turning points (TPs) in EF by the Breaks For Additive Season and Trend (BFAST) family algorithms during 2000–2019. The linkages between the TPs, drought, the frequency of land cover change, and socioeconomic development were examined. The results show that 63.2% of the pixels in the ASARNC region underwent sudden EF changes, of which 26.64% were induced by drought events, while 55.67% were firmly associated with the wetting climate. Wet and dry events were not detected in 17.69% of the TPs, which might have been caused by human activities. TP types and occurrences correlate differently with land cover change frequency, population density, and GDP. The improved EF TP type was correlated with the continuous humid climate and a reduced population density, while the deteriorated EF type coincided with persistent drought and increasing population density. Our research furthers the understanding of how and why TPs of EF occur and provides fundamental data for the conservation, management, and better decision-making concerning dryland ecosystems in China.