View in EDS HTML Full Text PDF Full Text

Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model.

Saved in:
Bibliographic Details
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.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 194587007
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Du%2C+Pengfei%22">Du, Pengfei</searchLink><relatesTo>1,2,3,4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Luo%2C+Jing-Jia%22">Luo, Jing-Jia</searchLink><relatesTo>2,3,4,5</relatesTo> (AUTHOR)<i> jjluo@nuist.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lin%2C+Xianxuan%22">Lin, Xianxuan</searchLink><relatesTo>2,3,5</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Meng%2C+Fan%22">Meng, Fan</searchLink><relatesTo>2,3,4,5</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Jun2026, Vol. 18 Issue 11, p1786. 30p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Probabilistic+generative+models%22">Probabilistic generative models</searchLink><br /><searchLink fieldCode="DE" term="%22Forecasting%22">Forecasting</searchLink><br /><searchLink fieldCode="DE" term="%22Encoding%22">Encoding</searchLink><br /><searchLink fieldCode="DE" term="%22Emergency+management%22">Emergency management</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Tropical+cyclones%22">Tropical cyclones</searchLink><br /><searchLink fieldCode="DE" term="%22Measurement+uncertainty+%28Statistics%29%22">Measurement uncertainty (Statistics)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=194587007
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs18111786
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 30
        StartPage: 1786
    Subjects:
      – SubjectFull: Probabilistic generative models
        Type: general
      – SubjectFull: Forecasting
        Type: general
      – SubjectFull: Encoding
        Type: general
      – SubjectFull: Emergency management
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Tropical cyclones
        Type: general
      – SubjectFull: Measurement uncertainty (Statistics)
        Type: general
    Titles:
      – TitleFull: Probabilistic Forecast of Tropical Cyclone Precipitation Based on Diffusion Model.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Du, Pengfei
      – PersonEntity:
          Name:
            NameFull: Luo, Jing-Jia
      – PersonEntity:
          Name:
            NameFull: Lin, Xianxuan
      – PersonEntity:
          Name:
            NameFull: Meng, Fan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 06
              Text: Jun2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 18
            – Type: issue
              Value: 11
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1