A5030269700- Hydrology and Watershed Management Studies
- Flood Risk Assessment and Management
- Remote-Sensing Image Classification
- Water Resources and Management
- Urban Heat Island Mitigation
- Advanced Image Fusion Techniques
- Face and Expression Recognition
- Remote Sensing and Land Use
- Neural Networks and Applications
China University of Petroleum, East China
2022-2024
Qingdao National Laboratory for Marine Science and Technology
2023
Deep learning methods have shown great advantages in hyperspectral image (HSI) classification tasks. In particular, convolutional neural network (CNN)-based for HSI made progress. However, it is difficult CNN to process long-range spatial and spectral information. Recently, a novel deep model called transformer has demonstrated its potential replace various tasks with amazing performance. this letter, multi-scale spectral-spatial dual-transformer (MS3DT) proposed deeply consider the features...
Abstract. High-resolution and multitemporal impervious surface maps on large scales are crucial for environmental socioeconomic studies. However, recently available of the Lancang-Mekong basin were limited at 30-m resolution with considerably low accuracy. Hence, development up-to-date, accurate, 10-m is urgently needed. In this article, a machine learning framework demonstrated by fusing Sentinel-1 Synthetic Aperture Radar images Sentinel-2 Multispectral Sensor to map study annual dynamics...