Hetao Irrigation District is one of the most important grain and oil production bases in China. The spatial and temporal evolution of the cropping structure over the years can provide the basic data for the yield of farmland and the amount of water for irrigation in the future adjustment of agricultural structures. In this study, the errors from the different sensors were calibrated to calculate the normalized difference vegetation index (NDVI) of the irrigation area for the whole year using Landsat-5 and Landsat-8 remote sensing images. The MODIS NDVI data was also used to interpolate the missing areas. The MODIS NDVI data was interpolated and S-G filtered for the missing areas of the image. The spectral and texture features were also calculated after that. The samples were then augmented to obtain 13004 samples with a uniform distribution. The deep learning of the multilayer perceptron (MLP) neural network was constructed to adjust the MLP model for the actual planting and climatic conditions. The model was then migrated each year to obtain the planting structure from 2000 to 2021. Finally, a systematic analysis was made of the multi-year spatial and temporal changes. The results showed that the overall classification accuracy reached 89% in 2021, and the Kappa coefficient was 0.87. Overall, the classification accuracy was ranked in descending order as follows: wheat, maize, alfalfa, vegetables, sunflower (melons), and rice. Specifically, the accuracies of the rice and melons were lower at 0.86 and 0.88, respectively, in terms of the user’s accuracy indexes. All accuracies were higher than 90% in the main crops of maize, wheat, and alfalfa. The relative error of the area in each year was less than 8%, compared with the statistical planting area. The smaller relative error was found in the sunflower, corn and wheat, whereas, the larger one was vegetables and melons (5% to 8%). A comparison of the MLP classification revealed that there was a relatively high consistency of the spatial distribution. Meanwhile, the contiguous planting area was distributed in the form of plots. The planting area of sunflower and maize showed an upward trend between 2000-2021, whereas, the planting area of wheat shrunk considerably. The sunflower was distributed mainly in the eastern region in 2015-2021, maize growing areas are mainly distributed in the central and western regions, but in 2010 scattered distribution, no contiguous planting area. The wheat planted area accounted for a relatively large proportion of the total in 2000-2010, mainly in the northwestern region and eastern part of the irrigation area, and then shrunk considerably in 2010. The evolution of sunflower acreage occurred more during the study period, followed by maize, all of which was mainly transferred from the wheat. The high classification accuracy and migration of the improved model can provide a strong reference for agricultural management and rational resource utilization in the Hetao Irrigation District of Inner Mongolia.

Fractional vegetation cover (FVC) has been one of the most widely utilized indicators to assess the vegetation growth status for the better ecological environment. The spatiotemporal evolution of FVC and its relationship with the climate change can also be crucial to promote the ecological civilization and the sustainable development in agriculture and animal husbandry. However, the large-scale and long-term FVC research is often required to deal with the massive image data, leading to the significant challenges on research advancement. The Google Earth Engine (GEE) platform can be expected to offer the new and effective solutions. In this study, a perfect tradeoff was gained between the rich data sources and powerful processing using GEE platform. A dimidiate pixel model (DPM) was employed to produce the FVC under the different types of land cover in Inner Mongolia, northern China. The Sen's slope estimator and Pearson correlation coefficient were then used to identify the temporal and spatial change of FVC and its correlation with the climate factors. Initially, the FVC annual time series were collected from 1982 to 2021 using the NOAA AVHRR NDVI data within GEE. Subsequently, Sen's slope estimation and the Mann-Kendall test were conducted to analyze the significant trends of FVC over the four decades. Finally, Pearson correlation coefficients were calculated between FVC and climate factors. The significance tests were carried out to reveal the relationship between FVC and climate change. Additionally, the spatial distribution maps were obtained to depict the spatial pattern of the correlations in the significant correlated regions. The results showed that: 1) There was the significant band pattern in the spatial distribution of the average FVC, with the gradual increase from the west to the northeast. A large difference of FVC was also found in different types of land cover. Generally, the FVC was >0.1-0.2 in 18.7% of the region. The proportions of FVC >0.5-0.6 and >0.7-0.8 were both close to 15%. There were the relatively small proportions of 0-0.1 and >0.8-0.9, particularly without the proportions of >0.9-1.0. The rest intervals were about 10%. 2) The FVC decreased significantly in the desert area of western Inner Mongolia, accounting for 13.1%. There was no significant trend of FVC in the mountains and grasslands of the middle, where the area was accounted for 38.2%. A very significant upward trend was found in the FVC of croplands, forests and part of grasslands in the south, east and northeast, accounting for 38.3% of the total. 3) There were the significantly different correlations between FVC and meteorological factors in the different types of land cover. The FVC of grassland was significantly or extremely significantly positive correlated with the annual precipitation, while the FVC of croplands was significantly or extremely significantly positive correlated with annual average temperature, and the FVC in some areas of forests was significantly negative correlated with annual precipitation, as well as the FVC in some barren was significantly negative correlated with annual average temperature. A 40-year-long time series of annual FVC were successfully constructed using NOAA AVHRR NDVI data on the GEE platform. The robust processing and analysis capabilities of platform were better balanced to identify the trends of FVC in the various land cover types, together with the correlation with climate change. These findings can provide some significant implications to guide the ecological environment protection for the sustainable development in Inner Mongolia of China.