Climate change and human activities significantly affect vegetation growth in terrestrial ecosystems. Here, data reconstruction was performed to obtain a time series of the normalized difference vegetation index (NDVI) for China (1982–2018) based on Savitzky–Golay filtered GIMMS NDVI3g and MOD13A2 datasets. Combining surface temperature and precipitation observations from more than 2000 meteorological stations in China, Theil–Sen trend analysis, Mann–Kendall significance tests, Pearson correlation analysis, and residual trend analysis were used to quantitatively analyze the long-term trends of vegetation changes and their sources of uncertainty. Significant spatial and temporal heterogeneity was observed in vegetation changes in the study area. From 1982 to 2018, the vegetation showed a gradually increasing trend, at a rate of 0.5%·10 a⁻¹, significantly improving (37.15%, p < 0.05) more than the significant degradation (7.46%, p < 0.05). Broadleaf (0.66) and coniferous forests (0.62) had higher NDVI, and farmland had the fastest rate of increase (1.02%/10 a⁻¹). Temperature significantly affected the vegetation growth in spring (R > 0; p < 0.05); however, the increase in summer temperatures significantly inhibited (R < 0; p < 0.05) the growth in North China (R_NDVI-tem = −0.379) and the Qinghai–Tibetan Plateau (R_NDVI-tem = −0.051). Climate change has highly promoted the growth of vegetation in the plain region of the Changjiang (Yangtze) River (3.24%), Northwest China (1.07%). Affected by human activities only, 49.89% of the vegetation showed an increasing trend, of which 22.91% increased significantly (p < 0.05) and 9.97% decreased significantly (p < 0.05). Emergency mitigation actions are required in Northeast China, Xinjiang, Northwest China, and the Qinghai–Tibetan Plateau. Therefore, monitoring vegetation changes is important for ecological environment construction and promoting regional ecological protection.

Understanding the response of vegetation to drought is of great significance to the biodiversity protection of terrestrial ecosystem. Based on the MOD13A2 NDVI, GOSIF, and SPEI data of the Yellow River Basin from 2001 to 2020, this paper used the methods of Theil–Sen median trend analysis, Mann–Kendall significance test, and Pearson correlation analysis to analyze whether the vegetation change trends monitored by MODIS and GOSIF are consistent and their sensitivity to meteorological drought. The results showed that NDVI and SIF increased significantly (p < 0.001) at the rate of 0.496 × 10⁻² and 0.345 × 10⁻², respectively. The significant improvement area of SIF (66.49%, p < 0.05) is higher than NDVI (50.7%, p < 0.05), and the spatial distribution trend of vegetation growth monitored by NDVI and SIF is consistent. The negative value of SPEI-12 accounts for 65.83%, with obvious periodic changes. The significant positive correlation areas of SIF-SPEI in spring, summer, and autumn (R > 0, p < 0.05) were 7.00%, 28.49%, and 2.28% respectively, which were higher than the significant positive correlation areas of NDVI-SPEI (spring: 1.79%; summer: 20.72%; autumn: 1.13%). SIF responded more strongly to SPEI in summer, and farmland SIF was significantly correlated with SPEI (0.3424, p < 0.01). The results indicate that SIF is more responsive to drought than NDVI. Analyzing the response of vegetation to meteorological drought can provide constructive reference for ecological protection.

The performance of deep neural networks depends on the accuracy of labeled samples, as they usually contain label noise. This study examines the semantic segmentation of remote sensing images that include label noise and proposes an anti-label-noise network framework, termed Labeled Noise Robust Network in Remote Sensing Image Semantic Segmentation (NRN-RSSEG), to combat label noise. The algorithm combines three main components: network, attention mechanism, and a noise-robust loss function. Three different noise rates (containing both symmetric and asymmetric noise) were simulated to test the noise resistance of the network. Validation was performed in the Vaihingen region of the ISPRS Vaihingen 2D semantic labeling dataset, and the performance of the network was evaluated by comparing the NRN-RSSEG with the original U-Net model. The results show that NRN-RSSEG maintains a high accuracy on both clean and noisy datasets. Specifically, NRN-RSSEG outperforms UNET in terms of PA, MPA, Kappa, Mean_F1, and FWIoU in the presence of noisy datasets, and as the noise rate increases, each performance of UNET shows a decreasing trend while the performance of NRN-RSSEG decreases slowly and some performances show an increasing trend. At a noise rate of 0.5, the PA (−6.14%), MPA (−4.27%) Kappa (−8.55%), Mean_F1 (−5.11%), and FWIOU (−9.75%) of UNET degrade faster; while the PA (−2.51%), Kappa (−3.33%), and FWIoU of NRN-RSSEG (−3.26) degraded more slowly, MPA (+1.41) and Mean_F1 (+2.69%) showed an increasing trend. Furthermore, comparing the proposed model with the baseline method, the results demonstrate that the proposed NRN-RSSEG anti-noise framework can effectively help the current segmentation model to overcome the adverse effects of noisy label training.