Satellite remote sensing provides the changes information of Earth surface on large spatial scale in a long time series and has been widely used in ecology. However, the possible impact from human activities generally occurs on a smaller spatial scale and could be detected in a longer time, which requires the remote sensing data having the both higher spatial and temporal resolution. Meanwhile, the development of the spatiotemporal data fusion algorithm provides an opportunity for the requirements. In this paper, based on deep learning, we proposed a residual convolutional neural network (Res-CNN) model to improve the fusion result considerably with brand-new network architecture to fuse the NDVI retrievals from Landsat 8 and MODIS images. Experiments conducted in two different areas demonstrate improvements by comparing them with existing algorithms. The model performance was evaluated by a linear regression between predictions and observations and quantified by determination coefficients (R²), regressive ecoefficiency (slope). The two excellent models, ESTARFM and FSDAF, were compared with the new model on their performance. The results showed that the predicted NDVI had the higher exploitational on the variability in the Landsat-based NDVI with the R² of 0.768 and 0.807 at the urban and grassland sites. The predicted NDVI was well consistent with the observations with the slope of 1.01 and 0.989, and the R-RMSE of 95.76% and 93.58% at the urban and grassland sites respectively. This study demonstrated that the Res-CNN model developed in this paper exhibits higher accuracy and stronger robustness than the traditional models. This research is full implications because it not only provides a model on the spatio-temporal data fusion, but also can provide the data of a long time series for the management and utilization of agriculture and grassland ecosystems on the regional scale.

Desertification research plays a key role in the survival and development of all mankind. The Normalized Comprehensive Hotspots Index (NCH) is a comprehensive index that reveals the spatial distribution of research hotspots in a given research field based on the number of relevant scientific papers. This study uses Web Crawler technology to retrieve the full text of all Chinese journal articles spanning the 1980s-2018 in the Chinese Academic Journal full-text database (CAJ) from CNKI. Based on the 253,055 articles on desertification that were retrieved, we have constructed a research hotspot extraction model for desertification in China by means of the NCH Index. This model can reveal the spatial distribution and dynamic changes of research hotspots for desertification in China. This analysis shows the following: 1) The spatial distribution of research hotspots on desertification in China can be effectively described by the NCH Index, although its application in other fields still needs to be verified and optimized. 2) According to the NCH Index, the research hotspots for desertification are mainly distributed in the Agro-Pastoral Ecotone and grassland in Inner Mongolia, the desertification areas of Qaidam Basin in the Western Alpine Zone and the Oasis-Desert Ecotone in Xinjiang (including the extension of the central Tarim Basin to the foothills of the Kunlun Mountains, the sporadic areas around the Tianshan Mountains and the former hilly belt of the southern foothills of the Altai Mountains). Among these three, the Agro-Pastoral Ecotone in the middle and eastern part of Inner Mongolia includes the most prominent hotspots in the study of desertification. 3) Since the 1980s, the research hotspots for desertification in China have shown a general downward trend, with a significant decline in 219 counties (10.37% of the study area). This trend is dominated by the projects carried out since 2002. The governance of desertification in the eastern part of the Inner Mongolia-Greater Khingan Range still needs to be strengthened. The distribution of desertification climate types reflects the distribution of desertification in a given region to some extent. The Normalized Comprehensive Hotspots Index provides a new approach for researchers in different fields to analyze research progress.