Mahdipour et al. (2025) Improving thunderstorm prediction with neural networks using numerical weather and satellite data: a novel data fusion and validation approach

Identification

• Journal: Elsevier eBooks
• Year: 2025
• Date: 2025-12-13
• Authors: Hadi Mahdipour, Alireza Sharifi, Dariush Abbasi‐Moghadam
• DOI: 10.1016/b978-0-443-30204-6.00016-4

Research Groups

• Centre for Cleantech and Biomass Resource Efficiency Centre at the Agricultural University of Plovdiv, Plovdiv, Bulgaria
• Department of Geomatics and Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran
• Department of Electrical Engineering, Shahid Bahonar University of Kerman, Kerman, Iran

Short Summary

This paper introduces a novel data fusion and validation approach using neural networks, numerical weather, and satellite data to improve short-term thunderstorm prediction, aiming to enhance air traffic management and reduce weather-related delays.

Objective

• To develop and validate a novel data fusion approach utilizing neural networks, numerical weather prediction (NWP) models, and satellite data to improve the accuracy of short-term thunderstorm prediction.
• To enhance air traffic management (ATM) operations and reduce economic costs associated with weather-related delays by providing more accurate thunderstorm forecasts.

Study Configuration

• Spatial Scale: Regional (e.g., Europe, implied by context of air traffic management delays).
• Temporal Scale: Short-term forecasting (nowcasting) within a timeframe of 1 to 3 hours, and general severe weather forecasting.

Methodology and Data

• Models used: Neural networks, Numerical Weather Prediction (NWP) models.
• Data sources: Numerical weather data, satellite data, real-time data (including Doppler radars for nowcasting).

Main Results

• The provided text is an introduction and does not contain specific results. However, the paper's objective implies the development and validation of a novel data fusion approach that improves thunderstorm prediction accuracy.

Contributions

• Introduction of a novel data fusion and validation approach combining neural networks with numerical weather and satellite data for thunderstorm prediction.
• Advancement in accurate short-term thunderstorm forecasting, addressing a critical challenge for aviation safety and air traffic management efficiency.
• Potential for significant reduction in economic costs and disruptions caused by weather-related delays in air traffic.

Funding

• Not specified in the provided text.

Citation

@article{Mahdipour2025Improving,
  author = {Mahdipour, Hadi and Sharifi, Alireza and Abbasi‐Moghadam, Dariush},
  title = {Improving thunderstorm prediction with neural networks using numerical weather and satellite data: a novel data fusion and validation approach},
  journal = {Elsevier eBooks},
  year = {2025},
  doi = {10.1016/b978-0-443-30204-6.00016-4},
  url = {https://doi.org/10.1016/b978-0-443-30204-6.00016-4}
}