Application and Prospects of Deep Learning in Extreme Disaster Weather Prediction

YANG Hao; SHOU Han-rui; LIU Ze-run; LIANG Zi-yi; LIU Rui; XU Li-ming; YANG Ming

doi:10.12263/newIT.2024.04.004

您当前的位置：

首页 >

文章列表页 >

Application and Prospects of Deep Learning in Extreme Disaster Weather Prediction

SURVEYS & TUTORIALS | 更新时间：2025-05-15

- Application and Prospects of Deep Learning in Extreme Disaster Weather Prediction
- New Generation of Information Technology Vol. 7, Issue 4, Pages: 16-24(2024)
- 作者机构：
  
  1.浙江省气象信息网络中心，浙江杭州 310051
  2.浙江仙鹤特种纸有限公司，浙江衢州 324022
- 作者简介：
- 基金信息：
- DOI：10.12263/newIT.2024.04.004
  CLC： TP183;X43
- Accepted：12 March 2025，
  
  Published：15 April 2024
- 稿件说明：
移动端阅览
杨浩, 寿涵锐, 刘泽润, 等. 深度学习在极端灾害性天气预测中的应用及展望[J]. 新一代信息技术, 2024, 7(4): 16-24

YANG Hao, SHOU Han-rui, LIU Ze-run, et al. Application and Prospects of Deep Learning in Extreme Disaster Weather Prediction[J]. New Generation of Information Technology, 2024, 7(4): 16-24
杨浩, 寿涵锐, 刘泽润, 等. 深度学习在极端灾害性天气预测中的应用及展望[J]. 新一代信息技术, 2024, 7(4): 16-24 DOI： 10.12263/newIT.2024.04.004.

YANG Hao, SHOU Han-rui, LIU Ze-run, et al. Application and Prospects of Deep Learning in Extreme Disaster Weather Prediction[J]. New Generation of Information Technology, 2024, 7(4): 16-24 DOI： 10.12263/newIT.2024.04.004.

摘要

极端灾害性天气的发生不仅对人类生存造成威胁还会对社会经济发展造成破坏，如何及时、精准地预测灾害性天气对防范和应对其带来的影响具有重要意义。深度学习近年来在气象预测领域中发挥了关键作用，本文从极端灾害性天气预测角度出发，探究了深度学习在该领域中的应用与进展。本文分别介绍了雷暴和台风预测领域中深度学习算法的发展以及相关模型的应用，并进一步基于代表性的深度学习算法介绍了其网络模型架构和损失函数等细节。最后，本文针对深度学习的发展趋势与极端灾害性天气的特点给出了对未来的展望。

Abstract

The occurrence of extreme disaster weather poses a threat to human survival and can significantly impact social and economic development. Timely and accurate prediction of such weather is crucial for mitigating and responding to its effects. In recent years

deep learning has played a key role in the field of meteorological forecasting. This paper explores the applications and advancements of deep learning in the prediction of extreme disaster weather. It introduces the development of deep learning algorithms in the prediction of thunderstorms and typhoons

along with the application of relevant models. Additionally

the paper details the architecture of representative deep learning models

including their network structures and loss functions. Finally

this paper offers insights into future trends of deep learning in light of its development trajectory and the characteristics of extreme disaster weather.

关键词

Keywords

references

EMANUEL K . Tropical cyclones [J ] . Annual Review of Earth and Planetary Sciences , 2003 , 31 ( 1 ): 75 - 104 .

Jr PINTO O , SABA M M F , PINTO I R C A , et al . Thunderstorm and lightning characteristics associated with sprites in Brazil [J ] . Geophysical Research Letters , 2004 , 31 ( 13 ): L13103 .

LÓPEZ-MORENO J I , GOYETTE S , VICENTE-SERRANO S M , et al . Effects of climate change on the intensity and frequency of heavy snowfall events in the Pyrenees [J ] . Climatic Change , 2011 , 105 ( 3 ): 489 - 508 .

BRUNNER M I , SLATER L , TALLAKSEN L M , et al . Challenges in modeling and predicting floods and droughts: A review [J ] . Wiley Interdisciplinary Reviews: Water , 2021 , 8 ( 3 ): e1520 .

FAN K , WANG H J . A new approach to forecasting typhoon frequency over the western north Pacific [J ] . Weather and Forecasting , 2009 , 24 ( 4 ): 974 - 986 .

MISHRA A K , DESAI V R . Drought forecasting using stochastic models [J ] . Stochastic Environmental Research and Risk Assessment , 2005 , 19 ( 5 ): 326 - 339 .

STANDER J H , DYSON L , ENGELBRECHT C . A snow forecasting decision tree for significant snowfall over the interior of South Africa: Review article [J ] . South African Journal of Science , 2016 , 112 ( 9/10 ): 29 - 38 .

秦予禛 , 刘怡欣 , 卿粼波 , 等 . 结合Transformer的多模态交叉步态识别 [J ] . 新一代信息技术 , 2023 ( 19 ): 1 - 7 .

JMOUR N , ZAYEN S , ABDELKRIM A . Convolutional neural networks for image classification [C ] // 2018 International Conference on Advanced Systems and Electric Technologies (IC_ASET) . Piscataway : IEEE , 2018 : 397 - 402 .

轩勃娜 , 李进 . 基于改进CNN的恶意软件分类方法 [J ] . 电子学报 , 2023 , 51 ( 5 ): 1187 - 1197 .

金天虎 , 陶砚蕴 , 李佐勇 . 基于超像素图像分割的暗通道先验去雾改进算法 [J ] . 电子学报 , 2023 , 51 ( 1 ): 146 - 159 .

HALL T , BROOKS H , DOSWELL C A . Precipitation forecasting using a neural network [J ] . American Meteorological Society , 1999 , 14 ( 3 ): 338 - 345 .

LI X , DU Z , SONG G . A method of rainfall runoff forecasting based on deep convolution neural networks [C ] // 2018 Sixth International Conference on Advanced Cloud and Big Data (CBD) . IEEE , 2018 : 304 - 310 .

QIU M H , ZHAO P L , ZHANG K , et al . A short-term rainfall prediction model using multi-task convolutional neural networks [C ] // 2017 IEEE International Conference on Data Mining(ICDM) . Piscataway : IEEE , 2017 : 395 - 404 .

CHEN J , YAN M , QURESHI M R H , et al . Estimating the visibility in foggy weather based on meteorological and video data: A Recurrent Neural Network approach [J ] . IET Signal Processing , 2023 , 17 ( 1 ): e12164 .

BOJESOMO A , ALMARZOUQI H , LIATSIS P . A novel transformer network with shifted window cross-attention for spatiotemporal weather forecasting [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2023 , 17 : 45 - 55 .

CHEN S C , SHU T , ZHAO H , et al . MASK-CNN-Transformer for real-time multi-label weather recognition [J ] . Knowledge-Based Systems , 2023 , 278 : 110881 .

MORGENSTERN D , STUCKE I , MAYR G J , et al . Thunderstorm environments in Europe [J ] . Weather and Climate Dynamics , 2023 , 4 ( 2 ): 489 - 509 .

LEINONEN J , HAMANN U , SIDERIS I V , et al . Thunderstorm nowcasting with deep learning: A multi-hazard data fusion model [J ] . Geophysical Research Letters , 2023 , 50 ( 8 ): e2022GL101626 .

GUASTAVINO S , PIANA M , TIZZI M , et al . Prediction of severe thunderstorm events with ensemble deep learning and radar data [J ] . Scientific Reports , 2022 , 12 ( 1 ): 20049 .

MÜLLER R , BARLEBEN A , HAUSSLER S , et al . A novel approach for the global detection and nowcasting of deep convection and thunderstorms [J ] . Remote Sensing , 2022 , 14 ( 14 ): 3372 .

ESSA Y , HUNT H G P , GIJBEN M , et al . Deep learning prediction of thunderstorm severity using remote sensing weather data [J ] . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 2022 , 15 : 4004 - 4013 .

KAMANGIR H , COLLINS W , TISSOT P , et al . A deep-learning model to predict thunderstorms within 400 km 2 South Texas domains [J ] . Meteorological Applications , 2020 , 27 ( 2 ): e1905 .

LI Y , LI H F , LI X T , et al . On deep learning models for detection of thunderstorm gale [J ] . Journal of Internet Technology , 2020 , 21 ( 4 ): 909 - 917 .

YANG X , XING H Y , XU W , et al . 3DAEFA-based thunderstorm prediction system with higher performance [J ] . IEEE Sensors Journal , 2022 , 22 ( 23 ): 22865 - 22884 .

ORTLAND S M , PAVOLONIS M J , CINTINEO J L . The development and initial capabilities of ThunderCast, a deep learning model for thunderstorm nowcasting in the United States [J ] . Artificial Intelligence for the Earth Systems , 2023 , 2 ( 4 ): e230044 .

GLOROT X , BENGIO Y . Understanding the difficulty of training deep feedforward neural networks [C ] // Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics . JMLR Workshop and Conference Proceedings , 2010 : 249 - 256 .

RANFTL R , BOCHKOVSKIY A , KOLTUN V . Vision transformers for dense prediction [C ] // 2021 IEEE/CVF International Conference on Computer Vision (ICCV) . Piscataway : IEEE , 2021 : 12159 - 12168 .

REN J , XU N , CUI Y N . Typhoon track prediction based on deep learning [J ] . Applied Sciences , 2022 , 12 ( 16 ): 8028 .

FENG Z H , LV S , SUN Y , et al . Skillful seasonal prediction of typhoon track density using deep learning [J ] . Remote Sensing , 2023 , 15 ( 7 ): 1797 .

RÜTTGERS M , LEE S , JEON S , et al . Prediction of a typhoon track using a generative adversarial network and satellite images [J ] . Scientific Reports , 2019 , 9 ( 1 ): 6057 .

HUANG C , BAI C , CHAN S X , et al . MGTCF: Multi-generator tropical cyclone forecasting with heterogeneous meteorological data [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2023 , 37 ( 4 ): 5096 - 5104 .

XU W W , KARTHIK B , ANDREW A , et al . Deep learning experiments for tropical cyclone intensity forecasts [J ] . Weather and Forecasting , 2021 , 36 ( 4 ): 1453 - 1470 .

JIANG W J , ZHANG D Q , HU G , et al . Transformer-based tropical cyclone track and intensity forecasting [J ] . Journal of Wind Engineering and Industrial Aerodynamics , 2023 , 238 : 105440 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Explainable Information Combined Deep Learning to Rank Algorithm

Predictive Study of Breast Cancer Pathological Images Based on DenseNet201

Application and Prospect of Deep Learning Technology in Medical Image Analysis

Study on the Recognition of Maize Leaf Disease Based on Deep Learning with Small Sample Size

Study of the Joint Framework for Real-World Super-Resolution-Semantic Segmentation

Related Author

ZHOU Ming-xing

GAO Ming-ze

HAN Yang

CHEN Guang-xin

GUO Jin-xing

SUN Yue

MIAO Zhuang

FU Li-yao

Related Institution

Datagrand CO., Ltd.

Hongqi Hospital Affiliated with Mudanjiang Medical University

Basic Medical College of Mudanjiang Medical University

Medical Imaging College of Mudanjiang Medical University

Chongqing Communication Design Institute Co., Ltd

⁰