Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model.
Saved in:
| Title: | Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model. |
|---|---|
| Authors: | Du, Pengfei1,2,3,4 (AUTHOR), Luo, Jing-Jia2,3,4,5 (AUTHOR) jjluo@nuist.edu.cn, Lin, Xianxuan2,3,5 (AUTHOR), Meng, Fan2,3,4,5 (AUTHOR) |
| Source: | Remote Sensing. Jun2026, Vol. 18 Issue 11, p1786. 30p. |
| Subjects: | Probabilistic generative models, Forecasting, Encoding, Emergency management, Deep learning, Tropical cyclones, Measurement uncertainty (Statistics) |
| Abstract: | Highlights: What are the main findings? This article introduces temporal constraints and a spatiotemporal-condition encoding mechanism (TCDF) in the diffusion framework, reducing the sensitivity of the model to initial conditions and achieving robust probability prediction. The article also highlights the superior performance of the proposed TCDF model across all lead times, ocean basins, and rainfall intensities, as demonstrated by improved deterministic accuracy, probabilistic metrics, and reduced false alarm rates. What are the implications of the main findings? The TCDF produces high-quality and reliable probabilistic forecasts, supporting improved TC risk assessment, early warning, and disaster preparedness for meteorological agencies. This study highlights the potential of diffusion models in quantifying the uncertainty of extreme weather, offering new insights for developing intelligent and robust meteorological forecasting systems. Predicting tropical cyclone (TC) precipitation is an important step in disaster prevention and mitigation. However, in the probability prediction of TC precipitation, traditional deep learning models are highly sensitive to initial conditions and can only provide deterministic forecasts, making it difficult to quantify uncertainty. In this study, we develop an AI-driven deep learning model based on diffusion models, incorporating historical data to reduce sensitivity to initial conditions and enhance precipitation distribution accuracy. Compared with traditional deep learning methods, this model outperforms other models in terms of the SSIM and PSNR for deterministic prediction of TC precipitation in 0–12 h. For probabilistic prediction, this model also achieves lower CRPS and Brier scores. Therefore, diffusion-based deep learning models not only show broad application prospects in TC-precipitation forecasting but also hold promise for providing probabilistic prediction methods for various disasters, enabling the widespread adoption of probabilistic forecasting across different prediction domains. [ABSTRACT FROM AUTHOR] |
| Copyright of Remote Sensing is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Highlights: What are the main findings? This article introduces temporal constraints and a spatiotemporal-condition encoding mechanism (TCDF) in the diffusion framework, reducing the sensitivity of the model to initial conditions and achieving robust probability prediction. The article also highlights the superior performance of the proposed TCDF model across all lead times, ocean basins, and rainfall intensities, as demonstrated by improved deterministic accuracy, probabilistic metrics, and reduced false alarm rates. What are the implications of the main findings? The TCDF produces high-quality and reliable probabilistic forecasts, supporting improved TC risk assessment, early warning, and disaster preparedness for meteorological agencies. This study highlights the potential of diffusion models in quantifying the uncertainty of extreme weather, offering new insights for developing intelligent and robust meteorological forecasting systems. Predicting tropical cyclone (TC) precipitation is an important step in disaster prevention and mitigation. However, in the probability prediction of TC precipitation, traditional deep learning models are highly sensitive to initial conditions and can only provide deterministic forecasts, making it difficult to quantify uncertainty. In this study, we develop an AI-driven deep learning model based on diffusion models, incorporating historical data to reduce sensitivity to initial conditions and enhance precipitation distribution accuracy. Compared with traditional deep learning methods, this model outperforms other models in terms of the SSIM and PSNR for deterministic prediction of TC precipitation in 0–12 h. For probabilistic prediction, this model also achieves lower CRPS and Brier scores. Therefore, diffusion-based deep learning models not only show broad application prospects in TC-precipitation forecasting but also hold promise for providing probabilistic prediction methods for various disasters, enabling the widespread adoption of probabilistic forecasting across different prediction domains. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 20724292 |
| DOI: | 10.3390/rs18111786 |
