Scholarlink

In the natural environment, the terrain and atmospheric environments have the most intense mutual influence and the greatest impact on human activities. This paper focuses on their interaction, using deep learning algorithms to explore the evolutionary laws of environmental elements in historical data and predict future changes under interactive influence. A neural network model is adopted to solve the problem of slow calculation of existing complex models for terrain-atmosphere interaction, which cannot meet the needs of real-time simulation. The trained model can quickly generate environmental prediction data to accelerate calculations. Covering 50 terrain and 17 atmospheric environmental data items, the study selects wind speed, precipitation, soil temperature, and moisture as research objects. Through theoretical, correlation, and autocorrelation analyses, strongly related elements are identified to predict future environmental changes, finally establishing a mutual influence model.

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

Research on the Interactive Influence between Terrain and Atmospheric Based on Deep Learning

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Xiaoyu Qu,
  • Yitong Ding,
  • Kaihang Xu,
  • Yongjie Qi

摘要

In the natural environment, the terrain and atmospheric environments have the most intense mutual influence and the greatest impact on human activities. This paper focuses on their interaction, using deep learning algorithms to explore the evolutionary laws of environmental elements in historical data and predict future changes under interactive influence. A neural network model is adopted to solve the problem of slow calculation of existing complex models for terrain-atmosphere interaction, which cannot meet the needs of real-time simulation. The trained model can quickly generate environmental prediction data to accelerate calculations. Covering 50 terrain and 17 atmospheric environmental data items, the study selects wind speed, precipitation, soil temperature, and moisture as research objects. Through theoretical, correlation, and autocorrelation analyses, strongly related elements are identified to predict future environmental changes, finally establishing a mutual influence model.