Remote sensing technology has become a popular tool for crop classification, but it faces challenges in accurately identifying crops in areas with fragmented land plots and complex planting structures. To address this issue, we propose an improved method for crop identification in high-resolution remote sensing images, achieved by modifying the DeepLab V3+ semantic segmentation network. In this paper, the typical crop area in the Jianghuai watershed is taken as the experimental area, and Gaofen-2 satellite images with high spatial resolutions are used as the data source. Based on the original DeepLab V3+ model, CI and OSAVI vegetation indices are added to the input layers, and MobileNet V2 is used as the backbone network. Meanwhile, the upper sampling layer of the network is added, and the attention mechanism is added to the ASPP and the upper sampling layers. The accuracy verification of the identification results shows that the MIoU and PA of this model in the test set reach 85.63% and 95.30%, the IoU and F1_Score of wheat are 93.76% and 96.78%, and the IoU and F1_Score of rape are 74.24% and 85.51%, respectively. The identification accuracy of this model is significantly better than that of the original DeepLab V3+ model and other related models. The proposed method in this paper can accurately extract the distribution information of wheat and rape from high-resolution remote sensing images. This provides a new technical approach for the application of high-resolution remote sensing images in identifying wheat and rape.

This paper intends to clarify that the spatial and temporal evolutionary patterns of regional vegetation and their relationship with climate form a premise of ecological conservation and environmental governance, and play an important role in maintaining regional ecosystem balance and promoting sustainable development. Based on measured data collected from NDVI remote sensing products and meteorological stations, NDVI variation in Anhui Province from 2001 to 2019 was determined through trend analysis and measurement methods involving coefficient of variation and Hurst index; in addition, the response to climatic factors was also explored. It was concluded that, firstly, in terms of spatiotemporal analysis, the interannual variation of NDVI in Anhui Province showed an increasing trend with a rate of 0.024/10 a, while the monthly variation showed a weak bimodal pattern, with the highest value in August and the lowest value in January. Furthermore, NDVI in Anhui Province showed significant spatial heterogeneity, with high values concentrated in mountainous regions in southern Anhui and Dabie Mountain region, and low values concentrated in the hilly areas of Jianghuai and areas along the Yangtze River. At the same time, the overall spatial variation of NDVI showed an increasing trend, and the areas with extremely significant and significant improvement in vegetation coverage accounted for 54.69% of the total area of Anhui Province. Secondly, in terms of the analysis on variation characteristics, the variation of NDVI in Anhui Province was generally stable, with an average CV coefficient of variation of 0.089, which, however, was quite different in different regions; meanwhile, the future trend of NDVI variation in the study areas was mostly in a random manner. Thirdly, the response of NDVI in Anhui Province to climatic factors showed significant spatial heterogeneity. NDVI was found to be positively correlated with precipitation and negatively correlated with temperature; in general, the impact of precipitation on NDVI was greater than that of temperature. In the 19 years studied, NDVI in Anhui Province showed an increasing trend; and climate, topography and human activities led to heterogeneous spatial distribution of vegetation. Therefore, in the future, the evolutionary trend of vegetation will be relatively random, and NDVI will be more greatly affected by temperature, than by precipitation.

Monitoring the lake waterbody area in the Qinghai–Tibet Plateau (QTP) is significant in dealing with global climate change. The latest released Landsat-9 data, which has higher radiation resolution and can be complemented with other Landsat data to improve imaging temporal resolution, have great potential for applications in lake area extraction. However, no study is published on identifying waterbodies and lakes in large-scale plateau scenes based on Landsat-9 data. Therefore, we relied on the Google Earth Engine (GEE) platform and selected ten waterbody extraction algorithms to evaluate the quantitative evaluation of waterbody and lake area extraction results on the QTP and explore the usability of Landsat-9 images in the relationship between the extraction accuracy and the algorithm. The results show that the random forest (RF) algorithm performs best in all models. The overall accuracy of waterbody extraction is 95.84%, and the average lake waterbody area extraction error is 1.505%. Among the traditional threshold segmentation waterbody extraction algorithms, the overall accuracy of the NDWI waterbody extraction method is 89.89%, and the average error of lake waterbody area extraction is 3.501%, which is the highest performance model in this kind of algorithm. The linear regression coefficients of NDVI and reflectance of Landsat-8 and Landsat-9 data are close to 1, and R² is more significant than 0.91. At the same time, the overall accuracy difference of water extraction between the two data is not better than 1.1%. This study proves that Landsat-9 and Landsat-8 data have great consistency, which can be used for collaborative analysis to identify plateau waterbodies more efficiently. With the development of cloud computing technologies, such as Gee, more complex models, such as RF, can be selected to improve the extraction accuracy of the waterbody and lake area in large-scale research.

Vegetation dynamics in arid and semi-arid regions have an important impact on carbon cycle, water cycle, and energy exchange at local, regional, and global scales. Therefore, it is of great significance for scientists to grasp the changes of vegetation cover in arid and semi-arid regions timely and accurately. Based on this, the applicability of ESTARFM model in the complex terrain area of arid and semi-arid Xinjiang was explored using Landsat and MODIS data fusion, and the overall change characteristics of vegetation cover (FVC) and the distribution and change patterns of different terrains in the study area in the past 15 years were analyzed by combining the dimidiate pixel model, unary linear regression and digital elevation model. The results show that: (1) the NDVI data fused by ESTARFM Model has high consistency with the real NDVI data, and it can be used for subsequent FVC estimation. (2) From 2006 to 2020, the inter FVC was at a high level as a whole, and the average annual FVC showed a weak increasing trend in fluctuation; there are obvious differences in spatial distribution, which is characterized by high distribution in the north and low in the south. (3) The improved area of vegetation cover in the study area is greater than the degraded area, accounting for 52.3% and 47.7% respectively; (4) In the elevation range of 2000 to 3500 m, the FVC showed a slight degradation trend on 25° to 45° slopes and south and southeast slopes, and the rest showed a slight improvement trend. ESTARFM-based model enables monitoring of vegetation cover changes in complex terrain areas of the arid and semi-arid regions in Xinjiang over a long time series. The overall FVC level in the study area is high, and there both are serious degradation and improvement phenomena.

Forest biomass estimation is an important parameter for calculating forest carbon storage, which is of great significance for formulating carbon-neutral strategies and forest resource management measures. We aimed at solving the problems of low estimation accuracy of forest biomass with complex canopy structure and high canopy density, and large differences in the estimation results of the same estimation model under complex forest conditions. The Huangfu Mountain Forest Farm in Chuzhou City was used as the research area. As predictors, we used Gaofen-1(GF-1) and Gaofen(GF-6) satellite high-resolution imaging satellite data, combined with digital elevation model (DEM) and forest resource data. Multiple stepwise regression, BP neural network and random forest estimation models were used to construct a natural subtropical secondary forest biomass estimation model with complex canopy structure and high canopy closure. We extracted image information as modeling factors, established multiple stepwise regression models of different tree types with a single data source and a comprehensive data source and determined the optimal modeling factors. On this basis, the BP neural network and random forest biomass estimation model were established for Pinus massoniana, Pinus elliottii, Quercus acutissima and mixed forests, with the coefficient of determination n (R²) and root mean square error (RMSE) as the judgment indices. The results show that the random forest model had the best biomass estimation effect among different forest types. The R² of Quercus acutissima was the highest, reaching 0.926, but the RMSE was 11.658 t/hm². The R² values of Pinus massoniana and mixed forest were 0.912 and 0.904, respectively. The RMSE reached 10.521 t/hm² and 6.765 t/hm², respectively; the worst result was the estimation result of Pinus elliottii, with an R² of 0.879 and an RMSE of 14.721 t/hm². The estimation result of the BP neural network was second only to that of the random forest model in the four forest types. From high precision to low precision, the order was Quercus acutissima, Pinus massoniana, mixed forest and Pinus elliottii, with R²s of 0.897, 0.877, 0.825 and 0.753 and RMSEs of 17.899 t/hm², 10.168 t/hm², 18.641 t/hm² and 20.419 t/hm², respectively. In this experiment, the worst biomass estimation performance was seen for multiple stepwise regression, which ranked the species in the order of Quercus acutissima, Pinus massoniana, mixed forest and Pinus elliottii, with R²s of 0.658, 0.622, 0.528 and 0.379 and RMSEs of 29.807 t/hm², 16.291 t/hm², 28.011 t/hm² and 23.101 t/hm², respectively. In conclusion, GF-1 and GF-6 combined with data and a random forest algorithm can obtain the most accurate results in estimating the forest biomass of complex tree species. The random forest estimation model had a good performance in biomass estimation of primary secondary forest. High-resolution satellite data have great application potential in the field of forest parameter inversion.

The monitoring of lake waterbody area in the Qinghai Tibet Plateau (QTP) is of great significance to deal with global climate change. As the latest generation of Landsat series satellites, Landsat-9 data not only have higher radiometric resolution, but also cooperate with other Landsat satellites to greatly improve the temporal resolution. It has great application potential in lake waterbody area monitoring. In order to explore the performance of different algorithms for extracting waterbody and lake waterbody area in Landsat-9 data under large-scale QTP regions, this study relies on Google Earth Engine (GEE) platform and selects 10 waterbody extraction algorithms as the basis to realize the quantitative evaluation of QTP lake waterbody area extraction results. The results show that the Random Forest (RF) algorithm performs best in all models. The overall accuracy of waterbody extraction is 95.84%, and the average error of lake waterbody area extraction is 1.505%. Among the traditional threshold segmentation waterbody extraction algorithms, the overall accuracy of the NDWI waterbody extraction method is 89.89%, and the average error of lake waterbody area extraction is 3.501%, which is the highest performance model in this kind of algorithms. This study proves that Landsat-9 data can effectively classify QTP waterbodies. With the development of cloud computing technologies such as Gee, more complex models such as RF can be selected to improve the extraction accuracy of water body and Lake area in large-scale research.