The Changtang Nature Reserve, located in the hinterland of the Qinghai-Tibet Plateau, plays a crucial role in researching ecological and environmental assessment on the plateau. However, the severe natural conditions in the Changtang Plateau have resulted in the absence of meteorological observation stations within the reserve, thereby leading to a lack of fundamental ecological and environmental research data. Remote sensing technology presents an opportunity for ecological monitoring in the Changtang Nature Reserve. In this study, remote sensing ecological indices (RSEI) were utilized to evaluate the ecological environment of the reserve from 2000 to 2020. The MODIS data reconstructed using the Savitzky-Golay filter on the Google Earth Engine (GEE) platform were employed. Principal component analysis was then conducted to construct the RSEI. The results reveal that the overall ecological environment quality in the Changtang Nature Reserve between 2000 and 2020 was relatively poor. Over the past two decades, the mean RSEI of the reserve exhibited a fluctuating trend of decrease and increase, indicating a deteriorating and subsequently improving ecological environment quality. Specifically, during the period of 2000–2010, the RSEI mean decreased from 0.3197 to 0.2269, suggesting degradation of the ecological environment, and the proportion of areas classified as fair and poor increased by 51.99%, while the proportion of areas classified as good and excellent decreased by 32.69%. However, from 2010 to 2020, it increased from 0.2269 to 0.3180, indicating an improvement in the ecological environment, and the proportion of areas classified as good and excellent increased by 6.11%, while the proportion of areas classified as fair and poor decreased by 2.91%. Spatially, the core zone demonstrated higher ecological environment quality compared to the experimental and buffer zones. The findings of this study provide comprehensive and accurate information about the ecological environment, which supports management, decision-making, and emergency response efforts in the Changtang Nature Reserve. Moreover, it offers a scientific basis for conservation and sustainable development strategies in the reserve. The quantitative assessment of the ecological environment dynamics contributes to the understanding of the reserve’s ecological dynamics and facilitates informed decision-making for effective conservation and management practices.

Forest fires are one of the significant disturbances in forest ecosystems. It is essential to extract burned areas rapidly and accurately to formulate forest restoration strategies and plan restoration plans. In this work, we constructed decision trees and used a combination of differential normalized burn ratio (dNBR) index and OTSU threshold method to extract the heavily and mildly burned areas. The applicability of this method was evaluated with three fires in Muli County, Sichuan, China, and we concluded that the extraction accuracy of this method could reach 97.69% and 96.37% for small area forest fires, while the extraction accuracy was lower for large area fires, only 89.32%. In addition, the remote sensing environment index (RSEI) was used to evaluate the ecological environment changes. It analyzed the change of the RSEI level through the transition matrix, and all three fires showed that the changes in RSEI were stronger for heavily burned areas than for mildly burned areas, after the forest fire the ecological environment (RSEI) was reduced from good to moderate. These results realized the quantitative evaluation and dynamic evaluation of the ecological environment condition, providing an essential basis for the restoration, decision making and management of the affected forests.

Convolutional neural networks (CNNs) have demonstrated their efficacy in remote sensing applications for mountain forest classification. However, two-dimensional convolutional neural networks (2D CNNs) require a significant manual involvement in the visual interpretation to obtain continuous polygon label data. To reduce the errors associated with manual visual interpretation and enhance classification efficiency, it is imperative to explore alternative approaches. In this research, we introduce a novel one-dimensional convolutional neural network (1D CNN) methodology that directly leverages field investigation data as labels for classifying mountain forest types based on multiple remote sensing data sources. The hyperparameters were optimised using an orthogonal table, and the model’s performance was evaluated on Mount Emei of Sichuan Province. Comparative assessments with traditional classification methods, namely, a random forest (RF) and a support vector machine (SVM), revealed superior results obtained by the proposed 1D CNN. Forest type classification using the 1D CNN achieved an impressive overall accuracy (OA) of 97.41% and a kappa coefficient (Kappa) of 0.9673, outperforming the U-Net (OA: 94.45%, Kappa: 0.9239), RF (OA: 88.99%, Kappa: 0.8488), and SVM (OA: 88.79%, Kappa: 0.8476). Moreover, the 1D CNN model was retrained using limited field investigation data from Mount Wawu in Sichuan Province and successfully classified forest types in that region, thereby demonstrating its spatial-scale transferability with an OA of 90.86% and a Kappa of 0.8879. These findings underscore the effectiveness of the proposed 1D CNN in utilising multiple remote sensing data sources for accurate mountain forest type classification. In summary, the introduced 1D CNN presents a novel, efficient, and reliable method for mountain forest type classification, offering substantial contributions to the field.

Evergreen broad-leaved forests with rich biodiversity play a key role in stabilizing global vegetation productivity and maintaining land carbon sinks. However, quantitative and accurate classification results for humid, evergreen, broad-leaved forests (HEBF) and semi-humid evergreen broad-leaved forests (SEBF) with different vegetation productivity and significant differences in species composition are lacking. Remote sensing technology brings the possibility of vegetation subtype classification. Taking the mountainous evergreen broad-leaved forests distributed in Sichuan Province as an example, this study proposed a hierarchy-based classifier combined with environmental variables to quantitatively classify the two vegetation subtypes with different ecological characteristics but similar image features. Additionally, we applied Sun–Canopy–Sensor and C parameter(SCS + C) topographic correction to preprocess the images, effectively correcting the radiometric distortion and enhancing the accuracy of vegetation classification. Finally, achieving an overall accuracy (OA) of 87.91% and a Kappa coefficient of 0.76, which is higher than that of directly using the classifier to classify the two vegetation subtypes. The study revealed the widespread distribution of evergreen broad-leaved forests in Sichuan, with a clear boundary between the distribution areas of HEBF and SEBF. The HEBF in the east is located in the basin and the low marginal mountains; the SEBF is located in the southwest dry valley. The methods employed in this study offer an effective approach to vegetation classification in mountainous areas. The findings can provide guidance for ecological engineering construction, ecological protection, and agricultural and livestock development.

Vegetation restoration is an essential approach to re-establish the ecological balance in subalpine areas. Changes in vegetation cover represent, to some extent, vegetation growth trends and are the consequence of a complex of different natural factors and human activities. Microtopography influences vegetation growth by affecting the amount of heat and moisture reaching the ground, a role that is more pronounced in subalpine areas. However, little research is concerned with the characteristics and dynamics of vegetation restoration in different microtopography types. The respective importance of the factors driving vegetation changes in subalpine areas is also not clear yet. We used linear regression and the Hurst exponent to analyze the trends in vegetation restoration and sustainability in different microtopography types since 2000, based on Fractional Vegetation Cover (FVC) and identified potential driving factors of vegetation change and their importance by using Geographical Detector. The results show that: (1) The FVC in the region under study has shown an up-trend since 2000, and the rate of increase is 0.26/year (P = 0.028). It would be going from improvement to degradation, continuous decrease or continuous significant decrease in 47.48% of the region, in the future. (2) The mean FVC is in the following order: lower slope (cool), lower slope, lower slope (warm), valley, upper slope (warm), upper slope, valley (narrow), upper slope (cool), cliff, mountain/divide, peak/ridge (warm), peak/ridge, peak/ridge (cool). The lower slope is the microtopographic type with the best vegetation cover, and ridge peak is the most difficult to be afforested. (3) The main factors affecting vegetation restoration in subalpine areas are aspect, microtopographic type, and soil taxonomy great groups. The interaction between multiple factors has a much stronger effect on vegetation cover than single factors, with the effect of temperatures and aspects having the most significant impact on the vegetation cover changes. Natural factors have a greater impact on vegetation restoration than human factors in the study area. The results of this research can contribute a better understanding of the influence of different drivers on the change of vegetation cover, and provide appropriate references and recommendations for vegetation restoration and sustainable development in typical logging areas in subalpine areas.

Changes in the spatial expansion of urban built-up areas are of great significance for the analysis of China’s urbanization process and economic development. Nighttime light data can be used to extract urban built-up areas in a large-scale and long-time series. In this article, we introduced the UNet model, a semantic segmentation network, as a base architecture, added spatial attention and channel attention modules to the encoder part to improve the boundary integrity and semantic consistency of the change feature map, and constructed an urban built-up area extraction model—CBAM_UNet. Also, we used this model to extract urban built-up areas from 2012 to 2021 and analyzed the spatial and temporal expansion of China’s urban built-up areas in terms of expansion speed, expansion intensity, expansion direction, and gravity center migration. In the last decade, the distribution pattern of urban built-up areas in China has gradually changed from “center” to “periphery-networked” distribution pattern. It reveals a trend from agglomeration to the dispersion of urban built-up areas in China. It provides a reference for China’s urban process and its economic development.