Scholarlink

Time series prediction plays a crucial role in various fields, including finance, economics and weather forecast. Dynamic Mode Decomposition (DMD) has emerged as a powerful technique for analysing and forecasting time series data. By identifying dominant modes or patterns within a time series, DMD offers a data-driven approach to predict future behaviour. This project explores and validates the use of DMD in forecasting meteorological variables such as temperature, dew point, wind speed, precipitation, and sea level pressure.

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

Meteorological Variables Forecast Using Dynamic Mode Decomposition (DMD)

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Luís Miguel Teixeira,
  • Paulo Alexandre Cardoso Salgado,
  • Paulo Lopes dos Santos,
  • T-P Azevedo Perdicoúlis

摘要

Time series prediction plays a crucial role in various fields, including finance, economics and weather forecast. Dynamic Mode Decomposition (DMD) has emerged as a powerful technique for analysing and forecasting time series data. By identifying dominant modes or patterns within a time series, DMD offers a data-driven approach to predict future behaviour. This project explores and validates the use of DMD in forecasting meteorological variables such as temperature, dew point, wind speed, precipitation, and sea level pressure.