CoChat
Sign Up
Cited by 58Climate variability and modelsTraffic Prediction and Management TechniquesClimate Change and Health Impacts

Regional Heatwave Prediction Using Graph Neural Network and Weather Station Data

Open access
Li, Peiyuan, Yu, Yin, Huang, Daning, Wang, Zhi‐Hua, Sharma, Ashish·2023·Geophysical Research Letters
DOI 10.1029/2023gl103405
Open this paper in CoChat — free account

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.

Integrity signals

Registry

Crossref · 10.1029/2023gl103405

Cites

48 of 48 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Claims the paper makes

We couldn’t retrieve this paper’s full text, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Li et al. developed a spatiotemporal Graph Neural Network framework to predict heatwaves using meteorological data from 91 weather stations across the contiguous United States over 2006-2020.

    “[28] developed a spatiotemporal Graph Neural Network (GNN) framework to predict heatwaves using meteorological data from 91 weather stations across the contiguous United States (CONUS) over a 15-year period (2006-2020).”

    From Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs (2024) · cites this paper as [28]

  • DI-GNN outperforms baseline models, achieving significant improvements in balanced accuracy, recall, and precision, with high AUC and average precision scores, particularly in forecasting heatwave events at weather lead times.

    “Our empirical evaluations demonstrate that DI-GNN outperforms the baseline model of Li et al, achieving higher precision, recall, and balanced accuracy, particularly in forecasting HW events at weather lead times.”

    From Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs (2024) · cites this paper as [28]

  • The Li et al. model for heatwave prediction across 100 training epochs for the configuration Cin=10 and Cout=3 showed significant instability and low recall during training and validation phases.

    “Figure 2. Performance metrics of the Li et al. (2023) model for heatwave prediction across 100 training epochs for the configuration C in = 10 and C out = 3. The metrics displayed include: Loss, Accuracy, Recall, Precision, Balanced Accuracy, and F1 Score, highlighting significant instability and low recall during training and validation phases.”

    From Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs (2024) · cites this paper as [28]

  • Unlike heuristic methods, DI-GNN's EVT-based approach provides a principled and robust framework for forecasting extreme climate events.

    “Unlike heuristic methods, DI-GNN's EVT-based approach provides a principled and robust framework for forecasting extreme climate events [29, 28].”

    From Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs (2024) · cites this paper as [28]

  • The DI-GNN framework builds upon and addresses key gaps in the spatiotemporal GNN methodology established by Li et al. using statistical theory of distributions, introducing GPD-based insights into feature representation, adjacency matrix reweighting, and loss function design.

    “The DI-GNN framework builds upon and address key gaps in the spatiotemporal GNN methodology established by [28] using statistical theory of distributions, introducing the use of Generalized Pareto Distribution (GPD)-based insights into feature representation, adjacency matrix reweighting, and loss function design.”

    From Advancing Heatwave Forecasting via Distribution Informed-Graph Neural Networks (DI-GNNs): Integrating Extreme Value Theory with GNNs (2024) · cites this paper as [28]

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Li, P., Yu, Y., Huang, D., Wang, Z., & Sharma, A.
Affiliations
  • University of Illinois System (US)
  • Department of Aerospace Engineering Pennsylvania State University PA University Park USA
  • Pennsylvania State University (US)
  • Arizona State University (US)
  • Argonne National Laboratory (US)
Corresponding author
Li, Peiyuan
ORCID
Venue
Geophysical Research Letters
Publisher
American Geophysical Union (AGU)
Published
2023-04-04
Volume
50
Issue
7
ISSN
  • 0094-8276 (ISSN-L)
  • 1944-8007
DOI
10.1029/2023gl103405
OpenAlex
W4362627411
Cited by
57
References
48
Citations by year
2026: 20 · 2025: 19 · 2024: 13 · 2023: 5
FWCI
6.39
Type
journal article
Language
en
Open access
Licence
Locations
  • Geophysical Research Letters (publishedVersion, cc-by-nc)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders
  • National Science Foundation (139316, 2230772)
  • U.S. Department of Energy (DE‐AC02‐06CH11357)
Topics
  • Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models
  • Physical Sciences › Engineering › Building and Construction › Traffic Prediction and Management Techniques
  • Physical Sciences › Environmental Science › Health, Toxicology and Mutagenesis › Climate Change and Health Impacts
Keywords
heatwave prediction, graph neural networks, weather station data, spatiotemporal patterns, climate extremes, compound climate events, climate change preparedness, real-time early warning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review