Skip to main content

Dataset / Hurricane Dataset for Deep-Hurricane-Tracker model

Have a question about this item?

Item information. View source record on contributor's website.

Title
Hurricane Dataset for Deep-Hurricane-Tracker model
Creator
Kim, Sookyung
Date Created and/or Issued
2018-09
Contributing Institution
UC San Diego, Library, Research Data Curation Program
Collection
Lawrence Livermore National Laboratory (LLNL) Open Data Initiative
Rights Information
Under copyright
Constraint(s) on Use: This work is protected by the U.S. Copyright Law (Title 17, U.S.C.). Use of this work beyond that allowed by "fair use" or any license applied to this work requires written permission of the copyright holder(s). Responsibility for obtaining permissions and any use and distribution of this work rests exclusively with the user and not the UC San Diego Library. Inquiries can be made to the UC San Diego Library program having custody of the work.
Use: This work is available from the UC San Diego Library. This digital copy of the work is intended to support research, teaching, and private study.
Rights Holder and Contact
Lawrence Livermore National Laboratory
Description
We use 20-year-long records from 1996 to 2015 of Community Atmospheric Model v5 (CAM5) dataset. It contains snapshots of the global atmospheric states for every three hours (1 timestep = 3 hours). Each snapshot contains multiple physical variables among which we use the six most important climate variables to define hurricane from scientific literature, such as PSL (Sea level pressure), U850 (Zonal wind), V850 (Meridional wind), PRECT (Precipitation), TS (Surface temperature), QREFHT (Reference high humidity) by order. From global scaled CAM5 reanalysis data, we only used data for the region around the Northern hemisphere which is 180 degree to 340 degree longitude and 0 degree to 60 degree latitude. For the purpose of training proposed tracking model, we fixed time length as 10 (which is 30 hours long). The input image size is 128 times 257 pixels with around 0.50 degree (around 50.0 km) resolution. Basically, the file contains multiple spatio-temporal hurricane data (video) channeled by 6 climate variables with time length 10. All climate variables are normalized between 0 and 1 accordingly (each channel has max value as 1 and min value as 0).
Earth System Grid Federation (ESGF) Project and Task used for working with this data: 40128 / SCW1480-ESGF.
Research Data Curation Program, UC San Diego, La Jolla, 92093-0175 (https://lib.ucsd.edu/rdcp)
Kim, Sookyung (2020). Hurricane Dataset for Deep-Hurricane-Tracker model. In Lawrence Livermore National Laboratory (LLNL) Open Data Initiative. UC San Diego Library Digital Collections. https://doi.org/10.6075/J0862DZ8
Is Supplement To: Kim, Sookyung, et al. "Deep-hurricane-tracker: Tracking and forecasting extreme climate events." 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 2019. https://doi.org/10.1109/WACV.2019.00192 References: Byna, Surendra, et al. "Teca: Petascale pattern recognition for climate science." International Conference on Computer Analysis of Images and Patterns. Springer, Cham, 2015. https://doi.org/10.1007/978-3-319-23117-4_37 Meehl, Gerald A., et al. "Climate change projections in CESM1 (CAM5) compared to CCSM4." Journal of Climate 26.17 (2013): 6287-6308." https://doi.org/10.1175/JCLI-D-12-00572.1
The format of dataset is numpy array. The Source of data is from https://www.earthsystemgrid.org/dataset/ucar.cgd.ccsm4.cam5.1.amip.1d.002.html The details of input data, “hurricane_image_train.npy” and “hurricane_image_test.npy”, are as follows. shape: (3408, 10, 128, 257, 6) Axis; Description; Size 0; Number of hurricane videos; 87837 1; Time; 10 (=30 hours) 2; Width; 128 (= 64 degree = 6400 km) 3; Height; 257(= 128.5 degree = 12850 km) 4; Climate variables; 6 (by order: ['PSL','U850','V850','PRECT','TS','QREFHT'] ) As ground truth hurricane location in Input data, we used the corresponding TECA (*Byna, Surendra, et al. "Teca: Petascale pattern recognition for climate science." International Conference on Computer Analysis of Images and Patterns. Springer, Cham, 2015.: https://link.springer.com/chapter/10.1007/978-3-319-23117-4_37*) labels. The TECA labels contain spatial coordinate (latitude, longitude) of each hurricane and the diameter of hurricane-force winds. We synthesize the ground-truth density maps as the same size with input data based on Gaussian mixtures. The details of input data, “hurricane_label_train.npy” and “hurricane_label_test.npy”, are as follows. shape: (3408, 10, 128, 257, 1) Axis; Description; Size 0; Number of hurricane heatmap; 87837 1; Time; 10 (=30 hours) 2; Width; 128 (= 64 degree = 6400 km) 3; Height; 257(= 128.5 degree = 12850 km) 4; Climate variables; 1 (Pixel-level probability that hurricane exists on that location: value between 0~1)
Type
Dataset
Language
English
Subject
Climate change
Neural networks
Scientific machine learning
Artificial intelligence (AI)
Climate AI
Climate science
Northern Hemisphere
Place
Northern Hemisphere

About the collections in Calisphere

Learn more about the collections in Calisphere. View our statement on digital primary resources.

Copyright, permissions, and use

If you're wondering about permissions and what you can do with this item, a good starting point is the "rights information" on this page. See our terms of use for more tips.

Share your story

Has Calisphere helped you advance your research, complete a project, or find something meaningful? We'd love to hear about it; please send us a message.

Explore related content on Calisphere: