DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data

Abstract

Abstract Heatwaves lead to catastrophic consequences on public health and the economy. Accurate and timely predictions of regional heatwaves can improve climate preparedness and foster decision‐making to alleviate the burdens due to climate change. In this paper, we propose a heatwave prediction algorithm based on a novel deep learning model, that is, Graph Neural Network (GNN). This new GNN framework can provide real time warnings of the sudden occurrence of regional heatwaves with high accuracy at lower costs of computation and data collection. In addition, its interpretable structure unravels the spatiotemporal patterns of regional heatwaves and helps to enrich our understanding of the general climate dynamics and the causal influences between locations. The proposed GNN framework can be applied for the detection and prediction of other extreme or compound climate events, which calls for future studies.

Authors:
ORCiD logo [1];  [2];  [2]; ORCiD logo [3]; ORCiD logo [4]
  1. Discovery Partners Institute University of Illinois System IL Chicago USA
  2. Department of Aerospace Engineering Pennsylvania State University PA University Park USA
  3. School of Sustainable Engineering and the Built Environment Arizona State University AZ Tempe USA
  4. Discovery Partners Institute University of Illinois System IL Chicago USA, Department of Atmospheric Sciences University of Illinois at Urbana‐Champaign IL Champaign USA, Environmental Science Division Argonne National Laboratory IL Lemont USA
Publication Date:
Research Org.:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Org.:
USDOE Office of Science (SC), Biological and Environmental Research (BER); National Science Foundation (NSF); The Walder Foundation
OSTI Identifier:
1968518
Alternate Identifier(s):
OSTI ID: 1971694; OSTI ID: 2329402
Grant/Contract Number:  
DE‐AC02‐06CH11357; AC02-06CH11357; 139316; 2230772
Resource Type:
Published Article
Journal Name:
Geophysical Research Letters
Additional Journal Information:
Journal Name: Geophysical Research Letters Journal Volume: 50 Journal Issue: 7; Journal ID: ISSN 0094-8276
Publisher:
American Geophysical Union (AGU)
Country of Publication:
United States
Language:
English
Subject:
54 ENVIRONMENTAL SCIENCES

Citation Formats

Li, Peiyuan, Yu, Yin, Huang, Daning, Wang, Zhi‐Hua, and Sharma, Ashish. Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data. United States: N. p., 2023. Web. doi:10.1029/2023GL103405.
Li, Peiyuan, Yu, Yin, Huang, Daning, Wang, Zhi‐Hua, & Sharma, Ashish. Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data. United States. https://doi.org/10.1029/2023GL103405
Li, Peiyuan, Yu, Yin, Huang, Daning, Wang, Zhi‐Hua, and Sharma, Ashish. Tue . "Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data". United States. https://doi.org/10.1029/2023GL103405.
@article{osti_1968518,
title = {Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data},
author = {Li, Peiyuan and Yu, Yin and Huang, Daning and Wang, Zhi‐Hua and Sharma, Ashish},
abstractNote = {Abstract Heatwaves lead to catastrophic consequences on public health and the economy. Accurate and timely predictions of regional heatwaves can improve climate preparedness and foster decision‐making to alleviate the burdens due to climate change. In this paper, we propose a heatwave prediction algorithm based on a novel deep learning model, that is, Graph Neural Network (GNN). This new GNN framework can provide real time warnings of the sudden occurrence of regional heatwaves with high accuracy at lower costs of computation and data collection. In addition, its interpretable structure unravels the spatiotemporal patterns of regional heatwaves and helps to enrich our understanding of the general climate dynamics and the causal influences between locations. The proposed GNN framework can be applied for the detection and prediction of other extreme or compound climate events, which calls for future studies.},
doi = {10.1029/2023GL103405},
journal = {Geophysical Research Letters},
number = 7,
volume = 50,
place = {United States},
year = {Tue Apr 04 00:00:00 EDT 2023},
month = {Tue Apr 04 00:00:00 EDT 2023}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1029/2023GL103405

Save / Share:

Works referenced in this record:

Extreme weather impacts of climate change: an attribution perspective
journal, June 2022

  • Clarke, Ben; Otto, Friederike; Stuart-Smith, Rupert
  • Environmental Research: Climate, Vol. 1, Issue 1
  • DOI: 10.1088/2752-5295/ac6e7d

Mega-heatwave temperatures due to combined soil desiccation and atmospheric heat accumulation
journal, April 2014

  • Miralles, Diego G.; Teuling, Adriaan J.; van Heerwaarden, Chiel C.
  • Nature Geoscience, Vol. 7, Issue 5
  • DOI: 10.1038/ngeo2141

Deadly Compound Heat Stress‐Flooding Hazard Across the Central United States
journal, August 2020

  • Zhang, Wei; Villarini, Gabriele
  • Geophysical Research Letters, Vol. 47, Issue 15
  • DOI: 10.1029/2020GL089185

Multi-objective optimization of urban environmental system design using machine learning
journal, June 2022


Forecasting Global Weather with Graph Neural Networks
preprint, January 2022


Trends in weather type frequencies across North America
journal, November 2018


The effect of heat waves on dairy cow mortality
journal, July 2015

  • Vitali, A.; Felici, A.; Esposito, S.
  • Journal of Dairy Science, Vol. 98, Issue 7
  • DOI: 10.3168/jds.2015-9331

Extended-range forecasting of Chinese summer surface air temperature and heat waves
journal, May 2017


2021 North American heatwave amplified by climate change-driven nonlinear interactions
journal, November 2022


Impact of heatwave on mortality under different heatwave definitions: A systematic review and meta-analysis
journal, April 2016


Evaluation of heat wave forecasts seamlessly across subseasonal timescales
journal, October 2018

  • Ford, Trent W.; Dirmeyer, Paul A.; Benson, David O.
  • npj Climate and Atmospheric Science, Vol. 1, Issue 1
  • DOI: 10.1038/s41612-018-0027-7

Severity of drought and heatwave crop losses tripled over the last five decades in Europe
journal, June 2021

  • Brás, Teresa Armada; Seixas, Júlia; Carvalhais, Nuno
  • Environmental Research Letters, Vol. 16, Issue 6
  • DOI: 10.1088/1748-9326/abf004

Spectral Networks and Locally Connected Networks on Graphs
preprint, January 2013


Deep Learning-Based Extreme Heatwave Forecast
journal, February 2022


Detecting the causal influence of thermal environments among climate regions in the United States
journal, November 2022


Prediction of heat waves using meteorological variables in diverse regions of Iran with advanced machine learning models
journal, October 2021

  • Asadollah, Seyed Babak Haji Seyed; Khan, Najeebullah; Sharafati, Ahmad
  • Stochastic Environmental Research and Risk Assessment, Vol. 36, Issue 7
  • DOI: 10.1007/s00477-021-02103-z

The architecture of complex weighted networks
journal, March 2004

  • Barrat, A.; Barthelemy, M.; Pastor-Satorras, R.
  • Proceedings of the National Academy of Sciences, Vol. 101, Issue 11
  • DOI: 10.1073/pnas.0400087101

High-resolution rainfall-runoff modeling using graph neural network
preprint, January 2021


A survey on missing data in machine learning
journal, October 2021


Node centrality in weighted networks: Generalizing degree and shortest paths
journal, July 2010


Detecting Causality in Complex Ecosystems
journal, September 2012


Heatwave and health impact research: A global review
journal, September 2018


Heat Waves in Florida: Climatology, Trends, and Related Precipitation Events
journal, March 2019

  • Cloutier-Bisbee, Shealynn R.; Raghavendra, Ajay; Milrad, Shawn M.
  • Journal of Applied Meteorology and Climatology, Vol. 58, Issue 3
  • DOI: 10.1175/JAMC-D-18-0165.1

Pm2.5-Gnn
conference, November 2020

  • Wang, Shuo; Li, Yanran; Zhang, Jiang
  • Proceedings of the 28th International Conference on Advances in Geographic Information Systems
  • DOI: 10.1145/3397536.3422208

Detectable Increases in Sequential Flood‐Heatwave Events Across China During 1961–2018
journal, March 2021

  • Chen, Yang; Liao, Zhen; Shi, Yan
  • Geophysical Research Letters, Vol. 48, Issue 6
  • DOI: 10.1029/2021GL092549

Long-lead predictions of eastern United States hot days from Pacific sea surface temperatures
journal, March 2016

  • McKinnon, K. A.; Rhines, A.; Tingley, M. P.
  • Nature Geoscience, Vol. 9, Issue 5
  • DOI: 10.1038/ngeo2687

GraphCast: Learning skillful medium-range global weather forecasting
preprint, January 2022


Computation of extreme heat waves in climate models using a large deviation algorithm
journal, December 2017

  • Ragone, Francesco; Wouters, Jeroen; Bouchet, Freddy
  • Proceedings of the National Academy of Sciences, Vol. 115, Issue 1
  • DOI: 10.1073/pnas.1712645115

Land use change impacts on European heat and drought: remote land-atmosphere feedbacks mitigated locally by shallow groundwater
journal, April 2019

  • Zipper, Samuel C.; Keune, Jessica; Kollet, Stefan J.
  • Environmental Research Letters, Vol. 14, Issue 4
  • DOI: 10.1088/1748-9326/ab0db3

Graph Neural Networks for Improved El Niño Forecasting
preprint, January 2020


Introduction to Good (1952) Rational Decisions
book, January 1992


A Graph Neural Network with Spatio-Temporal Attention for Multi-Sources Time Series Data: An Application to Frost Forecast
journal, February 2022

  • Lira, Hernan; Martí, Luis; Sanchez-Pi, Nayat
  • Sensors, Vol. 22, Issue 4
  • DOI: 10.3390/s22041486

Dynamic synchronization of extreme heat in complex climate networks in the contiguous United States
journal, July 2021


Compound summer temperature and precipitation extremes over central Europe
journal, February 2017

  • Sedlmeier, Katrin; Feldmann, H.; Schädler, G.
  • Theoretical and Applied Climatology, Vol. 131, Issue 3-4
  • DOI: 10.1007/s00704-017-2061-5

Graph Attention Networks
preprint, January 2017


Increasing trends in regional heatwaves
journal, July 2020


First Street Foundation's 6th National Risk Assessment: Hazardous Heat
report, January 2022


Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques
journal, March 2022

  • Jose, Dinu Maria; Vincent, Amala Mary; Dwarakish, Gowdagere Siddaramaiah
  • Scientific Reports, Vol. 12, Issue 1
  • DOI: 10.1038/s41598-022-08786-w

Uncertainty in big data analytics: survey, opportunities, and challenges
journal, June 2019

  • Hariri, Reihaneh H.; Fredericks, Erik M.; Bowers, Kate M.
  • Journal of Big Data, Vol. 6, Issue 1
  • DOI: 10.1186/s40537-019-0206-3

The NCEP Climate Forecast System Version 2
journal, March 2014


Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
text, January 2016


The impact of anthropogenic land use and land cover change on regional climate extremes
journal, October 2017


Compound Hydrometeorological Extremes: Drivers, Mechanisms and Methods
journal, October 2021


Forecasting PM2.5 Concentration in India Using a Cluster Based Hybrid Graph Neural Network Approach
journal, August 2022

  • Ejurothu, Pavan Sai Santhosh; Mandal, Subhojit; Thakur, Mainak
  • Asia-Pacific Journal of Atmospheric Sciences
  • DOI: 10.1007/s13143-022-00291-4