It is currently difficult to acquire the clear-sky data with high spatial resolutions in spring and summer in the southern region of China, making it impossible to carry out timely and fine monitoring of sugarcane planting information. Thus, Fusui, a sugarcane producing county in Guangxi, was selected in this paper to analyze the NDVI characteristics and change rules during the whole growth period of sugarcane based on MODIS and HJ-1 CCD remote sensing data, which were fused into 30 m resolution NDVI time series data with high accuracy by using the spatial and temporal fusion model of multi-source remote sensing data ESTRAFM. In addition, the NDVI change rate and sample automatic training threshold were used to construct the sugarcane planting information identification model. The results showed that the fused images showed a high similarity with the observed images, indicating good fusion quality. Moreover, the correlation coefficients in the sugarcane planting area reached 0.953, and AD, AAD and SD were 0.033, 0.019 and 0.007, respectively. The NDVI change rate model was used to identify the sugarcane planting information in different time phases of 113 d, 129 d, 145 d, 193 d and 209 d in spring and summer, and the overall accuracy was 92.17%, 92.58%, 91.78%, 90.52% and 91.17%, respectively. The established model also achieved good results in 2017 with the overall accuracies are 88.44%, 87.79%, 89.79%, 88.34% for 113 d, 145 d, 193 d and 209 d.

Based on the vegetation ecological quality index retrieved by satellite remote sensing in the karst areas of Guangxi in 2000–2019, the status of the ecological restoration of the vegetation and the influencing factors of the ecological restoration potential of the vegetation were analyzed. Then, habitats with a similar ecological restoration potential were categorized and the maximum ecological restoration potential of the vegetation was estimated. Finally, realization and prediction models of the ecological restoration potential of the vegetation were constructed to evaluate the realization degree and provide predictions. The quality of the ecological restoration was good in the study region, and the vegetation ecological quality index showed a fluctuating increasing trend. In the study region, 96.25%, 92.92%, 97.14%, and 99.07% of the total area was shown to have good ecological quality of the vegetation in 2000–2004, 2005–2009, 2010–2014, and 2015–2019, respectively. Terrain, soil, vegetation types, and climatic conditions had significant impacts on the ecological restoration of the vegetation. With the increase in the soil sand content, the changes in the vegetation ecological quality indexes were significant at altitudes of 200 m, 400 m, and 800 m and slopes of 15°, 25°, and 35°. The ecological restoration potential was the highest for forests, peaking at 87.5, followed by shrubs and grasses (87.4), and farmland (85.4). The partial and multiple correlations of the temperature, precipitation, and vegetation ecological quality index were significant, and the climate driving zones were divided into the strong driving zone of temperature and precipitation, temperature-dominated driving zone, precipitation-dominated driving zone, weak driving zone of temperature and precipitation, and non-climate driving zone. There was a high realization of the ecological restoration potential of the vegetation. The vegetation ecological quality in 97.95% of the area was restored, of which regions classified as maintaining growth, having slow growth, and having rapid growth accounted for 79.73%, 18.09%, and 0.13%, respectively, indicating that projects of rocky desertification control and ecological poverty alleviation were well implemented. In the future, the ecological restoration potential of the vegetation is predicted to be mainly low and medium. The areas with low potential are predicted to be mainly distributed in the north and southeast of Hechi, the northwest of Baise, and the west of Chongzuo, where the vegetation ecological quality and ecological restoration of the vegetation are predicted to be good, thus the restoration gap is predicted to be small. The areas with medium potential are predicted to be mainly distributed in the south of Hechi, the south of Baise, and the north of Chongzuo, where the vegetation ecological quality was restored well but further restoration could be beneficial. This research can provide technical support for future evaluations of the ecological restoration of vegetation, as well as construction, in the karst areas in the future.

Fragile karst areas of Guangxi are the key areas of vegetation protection and restoration work of the government. It is of great significance to study the effects of meteorological disasters on vegetation change for disaster prevention and reduction and ecological protection in the karst areas. The Normalized Differential Vegetation Index (NDVI), as a tool for monitoring vegetation growth, has a strong responsiveness to vegetation and can qualitatively and quantitatively evaluate the vegetation cover and its growth vitality. Therefore, in this study, we analyzed the trend of vegetation change and the impacts of multiple meteorological hazards, such as drought, torrential rainfall, high temperature, and low temperature, on the vegetation of the karst region in Guangxi by using the linear trend method, GIS spatial analysis, and correlation analysis, using the MODIS NDVI and temperature and precipitation information from 2000 to 2020 in the karst region of Guangxi. The results show that: (1) NDVI increased significantly in the karst areas, and 32.2% of the areas had significant improvement in vegetation. The improvement was the most obvious mainly in the central part of the study area, while the vegetation degradation trend was obvious in partial scattered areas in northeast and southwest. (2) On the interannual scale, NDVI was negatively correlated with some meteorological disaster indexes, such as relative humidity index, the number of drought days, the amount of extremely heavy rainstorm, the amount of heavy rainstorm, the number of days with high temperature of ≥35 °C, the number of days with high temperature of 35–37 °C, the number of days with high temperature of ≥37 °C, the minimum temperature, and the effective accumulated temperature of ≤0 °C. The obvious negative effect area of drought on vegetation was mainly concentrated in the middle of the study area, and that of rainfall was mainly distributed in the southwest, northeast and northwest; that of high temperature was mainly distributed in the northwest and northeast, and that of low temperature was mainly concentrated in the southwest and north. (3) On the multi-year monthly scale, the responses of NDVI to drought, high temperature and low temperature disaster indexes had a lag effect, but had no lag effect on rainfall disaster indexes. The lag time of vegetation to drought was 1 month, and the lag time to high temperature and low temperature was 3 months.

Multi-view real-life images taken by eco-meteorological observation stations can provide high-throughput visible light (RGB) image data for vegetation monitoring, but at present, there are few research reports on the vegetation monitoring effect of multi-view images and its difference from satellite remote sensing monitoring. In this study, with the underlying surface mixed with karst bare rock and vegetation as the research object, the far-view images and near-view images of 4 eco-meteorological stations were used to compare the segmentation effect of machine learning segmentation algorithm on images from far and near views, analyze the vegetation growth characteristics of visible images from far and near views, and investigate the differences between multi-view images and satellite remote sensing monitoring. The results showed that: (1) machine learning algorithm was suitable for green vegetation segmentation of multi-view images. The segmentation accuracy of machine learning algorithm for a near view image was higher than that for a far view image, with an accuracy rate of over 85%. Images captured under weak light conditions could obtain higher vegetation segmentation accuracy, and the proportion of bare rocks had no obvious influence on image segmentation accuracy. (2) The interannual variation trends of vegetation presented by different RGB vegetation indexes varied greatly, and the interannual variation difference of vegetation from a far view was greater than that from a near view. NDYI and RGBVI showed good consistency in vegetation changes from far and near views, and could also better show the interannual differences of vegetation. From the perspective of intra-year variation, various RGB vegetation indexes showed seasonal changes in different degrees. The vegetation in karst areas grew well from April to October, and the RGB vegetation indexes reached the peaks from May to June at most stations. The seasonal distribution of vegetation indexes were more obvious from a far view. (3) There was significant difference in the correlation between ground-based multi-view RGB vegetation indexes and NDVI of different satellites. The correlation with FY3D NDVI was weaker than that with MODIS NDVI. Most RGB vegetation indexes from a far view had a good correlation with MODIS NDVI, and the indexes with significant differences (P < 0.05) accounted for 70.5%. The correlation of most RGB vegetation indexes with FY3D NDVI and MODIS NDVI from a far view was better than that from a near view, and there was a significant difference in the RGB indexes with the highest correlation with NDVI of the 2 satellites from both far and near views in different stations. The machine learning algorithm combined with NLM filtering optimization had great advantages in multi-view image segmentation. Different RGB vegetation indices had different responses to vegetation growth changes, which may be related to the band composition of vegetation index and vegetation morphology and location. The image shooting mode of satellite was closer to the far-view Angle, so the correlation and fitting degree between satellite NDVI and far-view NDVI were higher. The research results provided theoretical basis and technical support for improving the ability of multi-view remote sensing monitoring of vegetation growth in karst ecological station.