Journal Article10.1088/1748-9326/ad1bde
Tropical cyclone intensity forecasting using model knowledge guided deep learning model
Chong Wang,Xiaofeng Li,Gang Zheng +2 more
5
TL;DR: The results show that the performance of the model-knowledge-guided approach can forecast TC intensity landfall better than the official subjective prediction and advanced deep learning methods in forecasting TC intensity by 4% to 22%.
read more
Abstract:
This paper developed a deep learning (DL) model for forecasting tropical cyclone (TC) intensity in the Northwest Pacifi c. A dataset containing 20,533 synchronized and collocated samples was assembled, which included ERA5 reanalysis data as well as satellite infrared imagery, covering the period from 1979 to 2021. The u-, v- and w-components of wind, sea surface temperature, infrared satellite imagery, and historical TC information were selected as the model inputs. Then, a tropical-cyclone-intensity-forecast-fusion (TCIF-fusion) model was developed, in which two special branches were designed to learn multi-factor information to forecast 24- hour TC intensity. Finally, heat maps capturing the model's insights are generated and applied to the original input data, creating an enhanced input set that results in more accurate forecasting. Employing this refi ned input, the heat maps (model knowledge, MK) were used to guide TCIF-fusion model modeling, and the model- knowledge-guided TCIF-fusion model achieved a 24-hour forecast error of 3.56 m/s for Northwest Paci fic TCs spanning 2020-2021. The results show that the performance of our method is signi ficantly better than the official subjective prediction and advanced deep learning methods in forecasting TC intensity by 4% to 22%. Moreover, in contrast to approaches by operational agencies, the model-knowledge-guided approach can forecast TC intensity landfall better.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
High-Resolution Tropical Cyclone Rainfall Detection From C-Band SAR Imagery With Deep Learning
Shanshan Mu,Xiaofeng Li,Haoyu Wang,Gang Zheng,Will Perrie,Chong Wang +5 more
Difference-Focusing Fusion Decision Method: An Ensemble Learning Framework and Its Application in Improving Deep Learning Sea-Land Segmentation for Waterline Extraction in Synthetic Aperture Radar Imagery
Gang Zheng,Yinfei Zhou,Bin Liu,Lizhang Zhou,Han Jiang,Yang Gao,Peng Chen +6 more
Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Model
Xinyu Wang,Kang Chen,Lei Liu,Tao Han,Bingfeng Li,Lei Bai +5 more
TL;DR: Multi-modal multi-scale causal autoregressive model (MSCAR) for global tropical cyclone intensity forecasting outperforms state-of-the-art methods using a newly developed dataset.
TCIP-Net: Quantifying Radial Structure Evolution for Tropical Cyclone Intensity Prediction
Wei Tian,Yuanyuan Chen,Ping Song,Haifeng Xu,Liguang Wu,Yonghong Zhang,Chunyi Xiang,Shifeng Hao +7 more
TL;DR: This study introduces TCIP-Net, a deep learning model that extracts convective structural information from satellite imagery to predict tropical cyclone intensity, achieving good performance and providing practical guidance for operational models.
Evaluation of precipitation forecasting methods and an advanced lightweight model
Nan Yang,Chong Wang,Xiaofeng Li +2 more
TL;DR: An advanced lightweight precipitation forecasting model (ALPF) based on CNN is proposed and experimental results demonstrate that ALPF can effectively forecast spatial-temporal features, maintaining CNN's feature extraction capabilities while avoiding error accumulation in RNN's propagation.
References
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Ramprasaath R. Selvaraju,Michael Cogswell,Abhishek Das,Ramakrishna Vedantam,Devi Parikh,Devi Parikh,Dhruv Batra,Dhruv Batra +7 more
TL;DR: Grad-CAM as mentioned in this paper uses the gradients of any target concept (e.g., a dog in a classification network or a sequence of words in captioning network) flowing into the final convolutional layer to produce a coarse localization map highlighting the important regions in the image for predicting the concept.
3.5K
The NCEP climate forecast system version 2
Suranjana Saha,Shrinivas Moorthi,Xingren Wu,Jiande Wang,Sudhir Nadiga,Patrick Tripp,David Behringer,Yu-Tai Hou,Hui Ya Chuang,M. Iredell,Michael Ek,Jesse Meng,Rongqian Yang,Malaquías Peña Mendez,Huug van den Dool,Qin Zhang,Wanqiu Wang,Mingyue Chen,Emily Becker +18 more
TL;DR: The second version of the NCEP Climate Forecast System (CFSv2) was made operational at the National Center for Environmental Prediction (NCEP) in 2011 as discussed by the authors.
An Overview of the China Meteorological Administration Tropical Cyclone Database
TL;DR: Wang et al. as mentioned in this paper summarized the characteristics and key technical details of the CMA TC database, which includes not only the best-track dataset but also TC-induced wind and precipitation data.
Coastal flooding by tropical cyclones and sea-level rise
TL;DR: In this article, the future impacts of climate change on landfalling tropical cyclones are unclear, but regardless of this uncertainty, flooding by hurricanes will increase as a result of accelerated sea-level rise.
Further improvements to the Statistical Hurricane Intensity Prediction Scheme (SHIPS)
TL;DR: In this article, a verification of the statistical hurricane intensity prediction scheme (SHIPS) for each year from 1997 to 2003 is described, including the addition of a method to account for the storm decay over land in 2000, the extension of the forecasts from 3 to 5 days in 2001, and the use of an operational global model for evaluation of the atmospheric predictors instead of a simple dry-adiabatic model beginning in 2001.