Scholarlink

This research addresses key challenges in spatial information mining, particularly related to the complexities and heterogeneity of geospatial data generated by diverse sensors and platforms. To enhance data collection and analysis, we introduce the Ground-Based Intelligent Multi-Parameter Environmental Health Remote Sensing Diagnostic Instrument (GB-EHRSDI). By leveraging Swin Transformer for cloud segmentation and PatchTST for time-series forecasting, we utilize edge computing to process multi-dimensional environmental data efficiently. This approach significantly improves the correlation analysis between cloud cover, rainfall, cloud motion, wind speed, and vertical cloud distribution, advancing weather prediction capabilities. Additionally, the GB-EHRSDI highlights the current limitations in Internet of Things (IoT)-based big data analysis techniques and underscores the need for future work to integrate more efficient data acquisition methods, IoT architecture, and Artificial Intelligence (AI) technologies to further enhance localized weather forecasting and environmental monitoring.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Spatiotemporal Analysis Methods Based on Ground-Based Intelligent Multi-parameter Environmental Health Remote Sensing Diagnostic Instrument

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Yu Zhang,
  • Chunxiang Cao,
  • Min Xu,
  • Shaohua Wang

摘要

This research addresses key challenges in spatial information mining, particularly related to the complexities and heterogeneity of geospatial data generated by diverse sensors and platforms. To enhance data collection and analysis, we introduce the Ground-Based Intelligent Multi-Parameter Environmental Health Remote Sensing Diagnostic Instrument (GB-EHRSDI). By leveraging Swin Transformer for cloud segmentation and PatchTST for time-series forecasting, we utilize edge computing to process multi-dimensional environmental data efficiently. This approach significantly improves the correlation analysis between cloud cover, rainfall, cloud motion, wind speed, and vertical cloud distribution, advancing weather prediction capabilities. Additionally, the GB-EHRSDI highlights the current limitations in Internet of Things (IoT)-based big data analysis techniques and underscores the need for future work to integrate more efficient data acquisition methods, IoT architecture, and Artificial Intelligence (AI) technologies to further enhance localized weather forecasting and environmental monitoring.