A5069355688- Rangeland Management and Livestock Ecology
- Forest, Soil, and Plant Ecology in China
- Remote Sensing in Agriculture
- Remote Sensing and LiDAR Applications
- Geological Studies and Exploration
- Impact of Light on Environment and Health
- Urban Transport and Accessibility
- Land Use and Ecosystem Services
- Species Distribution and Climate Change
- Remote Sensing and Land Use
- Environmental Changes in China
- Fire effects on ecosystems
- Ecology and Vegetation Dynamics Studies
- Wildlife-Road Interactions and Conservation
- Climate change and permafrost
- Landslides and related hazards
- Plant and animal studies
- Tree Root and Stability Studies
- Night-time city culture
Chengdu University of Technology
2022-2023
University of Helsinki
2023
The Changtang Nature Reserve, located in the hinterland of Qinghai-Tibet Plateau, plays a crucial role researching ecological and environmental assessment on plateau. However, severe natural conditions Plateau have resulted absence meteorological observation stations within reserve, thereby leading to lack fundamental research data. Remote sensing technology presents an opportunity for monitoring Reserve. In this study, remote indices (RSEI) were utilized evaluate environment reserve from...
Forest fires are one of the significant disturbances in forest ecosystems. It is essential to extract burned areas rapidly and accurately formulate restoration strategies plan plans. In this work, we constructed decision trees used a combination differential normalized burn ratio (dNBR) index OTSU threshold method heavily mildly areas. The applicability was evaluated with three Muli County, Sichuan, China, concluded that extraction accuracy could reach 97.69% 96.37% for small area fires,...
Vegetation restoration is an essential approach to re-establish the ecological balance in subalpine areas. Changes vegetation cover represent, some extent, growth trends and are consequence of a complex different natural factors human activities. Microtopography influences by affecting amount heat moisture reaching ground, role that more pronounced However, little research concerned with characteristics dynamics microtopography types. The respective importance driving changes areas also not...
Evergreen broad-leaved forests with rich biodiversity play a key role in stabilizing global vegetation productivity and maintaining land carbon sinks. However, quantitative accurate classification results for humid, evergreen, (HEBF) semi-humid evergreen (SEBF) different significant differences species composition are lacking. Remote sensing technology brings the possibility of subtype classification. Taking mountainous distributed Sichuan Province as an example, this study proposed...
Convolutional neural networks (CNNs) have demonstrated their efficacy in remote sensing applications for mountain forest classification. However, two-dimensional convolutional (2D CNNs) require a significant manual involvement the visual interpretation to obtain continuous polygon label data. To reduce errors associated with and enhance classification efficiency, it is imperative explore alternative approaches. In this research, we introduce novel one-dimensional network (1D CNN) methodology...
The biogeography research of orchids through species distribution models (SDMs), a vital tool in the field, is critical to understanding fundamental geographic patterns and identifying conservation priorities. correspondence between occurrence environmental information crucial model's performance. However, ecological preferences unique different orchid species, such as their life forms, are often overlooked during modeling process. This oversight can introduce bias increase model...
Changes in the spatial expansion of urban built-up areas are great significance for analysis China’s urbanization process and economic development. Nighttime light data can be used to extract a large-scale long-time series. In this article, we introduced UNet model, semantic segmentation network, as base architecture, added attention channel modules encoder part improve boundary integrity consistency change feature map, constructed an area extraction model—CBAM_UNet. Also, model from 2012...
<p><strong>Abstract： </strong>Accurate spatial extent changes in urban built-up areas are essential for detecting urbanization, analyzing the drivers of development and impact urbanization on environment. In recent years, nighttime light images have been widely used extraction, but traditional extraction methods need to be improved terms accuracy automation. this experiment, a U-Net model was built trained with NPP-VIIRS MOD13A1 data...