Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Spatial Temporal Approach for High-Resolution Gridded Wind Forecasting across Southwest Western Australia

Fuling Chen, Kevin Vinsen, Arthur Filoche

Abstract

Accurate wind speed and direction forecasting is paramount across many sectors, spanning agriculture, renewable energy generation, and bushfire management. However, conventional forecasting models encounter significant challenges in precisely predicting wind conditions at high spatial resolutions for individual locations or small geographical areas (< 20 km2) and capturing medium to long-range temporal trends and comprehensive spatio-temporal patterns. This study focuses on a spatial temporal approach for high-resolution gridded wind forecasting at the height of 3 and 10 metres across large areas of the Southwest of Western Australia to overcome these challenges. The model utilises the data that covers a broad geographic area and harnesses a diverse array of meteorological factors, including terrain characteristics, air pressure, 10-metre wind forecasts from the European Centre for Medium-Range Weather Forecasts, and limited observation data from sparsely distributed weather stations (such as 3-metre wind profiles, humidity, and temperature), the model demonstrates promising advancements in wind forecasting accuracy and reliability across the entire region of interest. This paper shows the potential of our machine learning model for wind forecasts across various prediction horizons and spatial coverage. It can help facilitate more informed decision-making and enhance resilience across critical sectors.

Spatial Temporal Approach for High-Resolution Gridded Wind Forecasting across Southwest Western Australia

Abstract

Accurate wind speed and direction forecasting is paramount across many sectors, spanning agriculture, renewable energy generation, and bushfire management. However, conventional forecasting models encounter significant challenges in precisely predicting wind conditions at high spatial resolutions for individual locations or small geographical areas (< 20 km2) and capturing medium to long-range temporal trends and comprehensive spatio-temporal patterns. This study focuses on a spatial temporal approach for high-resolution gridded wind forecasting at the height of 3 and 10 metres across large areas of the Southwest of Western Australia to overcome these challenges. The model utilises the data that covers a broad geographic area and harnesses a diverse array of meteorological factors, including terrain characteristics, air pressure, 10-metre wind forecasts from the European Centre for Medium-Range Weather Forecasts, and limited observation data from sparsely distributed weather stations (such as 3-metre wind profiles, humidity, and temperature), the model demonstrates promising advancements in wind forecasting accuracy and reliability across the entire region of interest. This paper shows the potential of our machine learning model for wind forecasts across various prediction horizons and spatial coverage. It can help facilitate more informed decision-making and enhance resilience across critical sectors.
Paper Structure (24 sections, 4 equations, 18 figures, 3 tables)

This paper contains 24 sections, 4 equations, 18 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Motivations and Contributions
  4. The proposed model
  5. Our Study
  6. Data Description
  7. DPIRD observation data source
  8. ECMWF forecasting data source
  9. Terrain data source
  10. Add time features
  11. Experiments configuration
  12. Data resolution
  13. Training and testing data samples
  14. Loss function
  15. Performance metrics
  16. ...and 9 more sections

Figures (18)

  • Figure 1: Weather station locations in the southwest of Western Australia. The red square highlights the area used with 73 weather stations.
  • Figure 2: Input and output data samples
  • Figure 3: MAE and RMSE of $u_{10}$ and $v_{10}$ at the 7 labelled stations from Jan-2022 to Dec-2023
  • Figure 4: MAE and RMSE of $u_{10}$ and $v_{10}$ at the 7 labelled stations during the period of summer daytime from Jan-2022 to Dec-2023
  • Figure 5: MAE and RMSE of $u_{10}$ and $v_{10}$ at the 7 labelled stations during the period of summer nighttime from Jan-2022 to Dec-2023
  • ...and 13 more figures