The DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index; 2 of the 16 sources its claims cite were checked for support.
Comparative analysis of machine learning approaches for heatwave event prediction in India
Open accessAbstract
Heatwaves, are identified as prolonged durations of unusually high temperatures, which pose significant threats to human health, animal health and agriculture. With the increasing frequency and intensity of heatwaves driven by climate change, accurate and early prediction of these extreme weather events is crucial for effective mitigation and adaptation. This research paper conducts a comparative analysis of various machine learning models for heatwave event classification using a time series dataset from a weather station in the equatorial region of India, specifically Chennai, Tamil Nadu. The study evaluates the performance of models including Random Forest, Convolutional Neural Networks, LightGBM, Long Short-Term Memory Networks, Transformer Networks, Support Vector Machines, Graph Neural Networks, Extreme Gradient Boosting and Autoencoders for Anomaly Detection in heatwave. The challenges posed by class imbalance and the limitations of traditional oversampling techniques are discussed, with insights into effective strategies for improving prediction accuracy. Accurate prediction of heatwaves enables mitigation plans to protect humans, animal and plants.
Overview
CoChat Summary
## TL;DR
This paper benchmarks nine machine learning approaches for heatwave event prediction using 2010–2023 weather-station data from Tambaram, Chennai, and finds that CNNs and boosting/ensemble methods perform best. It also argues that SMOTE is unsuitable for this time-series problem because it disrupts temporal structure, and that class weighting is a better imbalance-handling strategy.
## Key findings
- The dataset covers 14 years of weather observations from Tambaram, Chennai, Tamil Nadu, India and includes 20 meteorological parameters; the study uses a 7-day sliding window and reports an 80/20 train-test split with fivefold cross-validation.
- CNN achieved the best reported accuracy among the models, with precision 0.73, recall 0.61, F1-score 0.67, ROC AUC 0.9943, and accuracy 0.9892 (98.92%).
- Random Forest performed strongly with precision 0.80, recall 0.67, F1-score 0.73, ROC AUC 0.9956, and accuracy 0.9912.
- XGBoost, LightGBM, and Transformer Networks were also among the strongest models, each reported with precision 0.75, recall 0.50, F1-score 0.60, and ROC AUC around 0.993.
- LSTM performed poorly for heatwave detection, with precision, recall, and F1-score all 0.00 in one reported result set, despite accuracy 0.9824 and ROC AUC 0.9607.
- SVM and Autoencoders showed high recall but low precision: SVM had precision 0.12, recall 1.00, F1-score 0.22; Autoencoders had precision 0.07, recall 0.94, F1-score 0.13.
- GNN performed worst, with precision 0.00, recall 0.00, F1-score 0.00 and ROC AUC 0.4714.
## Methods
- Comparative benchmarking study of nine models: Random Forest, CNN, LightGBM, LSTM, Transformer, SVM, GNN, XGBoost, and Autoencoders for anomaly detection.
- Data came from a weather station in Tambaram, Chennai; missing values were interpolated, highly correlated features were removed, and feature selection used Pearson correlation plus RandomForestClassifier SelectFromModel.
- The main analysis used binary classification metrics: precision, recall, accuracy, ROC AUC, and F1-score; deep learning models used binary cross-entropy and Adam, while autoencoders used MSE loss.
## Limitations
- The paper states that traditional oversampling methods like SMOTE are not suitable for time series because they disrupt temporal dependencies; this is a limitation of the data structure and a motivation for the study’s alternative approach.
- It also states that CNNs require large training data and are computationally intensive, and that Transformers have high computational cost and need extensive hyperparameter tuning.
- Evident from the text: the study is based on a single weather-station dataset from one location (Tambaram/Chennai), so the findings may be limited in generalizability beyond this equatorial setting.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures









Verification
Claims the paper makes
1 Valid · 1 Not valid · 5 Not checked · 53 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“the prediction accuracy and heatwave projection greatly depend on the persistence of events in terms of temporal dependencies of the time series data.”
§ Comparative analysis of machine learning approaches for heatwave event prediction in India > Discussion > Reasons for higher predicting skills of the chosen models
What the sources say
- Not checked — no full text of the sourcecites [52] Bhoopathi, S., Kumar, N. & Pal, M. Evaluating the performances of SVR and XGBoost for short-range forecasting of heatwaves across different temperature zones of India. Appl. Comput. Geosci. 24, 100204. https://doi.org/10.1016/j.acags.2024.100204 (2024). source
- Not checked — no full text of the sourcecites [53] Velivelli, S., Satyanarayana, G. C. & Ali, M. M. Predicting daily maximum temperature over Andhra Pradesh using machine learning techniques. Theor. Appl. Climatol. 155, 8567–8585. https://doi.org/10.1007/s00704-024-05146-8 (2024). source
- Partly supportedcites [54] Qureshi, M. M. U. et al. Developing a seasonal-adjusted machine-learning-based hybrid time-series model to forecast heatwave warning. Sci. Rep. 15, 8699. https://doi.org/10.1038/s41598-025-93227-7 (2025). sourceExperimental — accuracy not yet measured
The Discussion says heatwave-warning forecasts require handling daily time-series data and that seasonal adjustment matters for forecasting. The Results compare model accuracy and lag-one error autocorrelation. Neither section establishes the claimed dependence of prediction accuracy or heatwave projections on the persistence of heatwave events. (LLM, conf=0.78)
- Not checked — no full text of the sourcecites [55] Brown, S. J. Future changes in heatwave severity, duration and frequency due to climate change for the most populous cities. Weather Clim. Extremes 30, 100278. https://doi.org/10.1016/j.wace.2020.100278 (2020). source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Earlier methods described in22–25 disrupt the temporal dependencies, making them unsuitable for predicting events based on sequential data.”
§ Comparative analysis of machine learning approaches for heatwave event prediction in India > Discussion > Reasons for higher predicting skills of the chosen models
What the sources say
- Not checked — no full text of the sourcecites [22] Singh, S. et al. Evaluation of CORDEX-South Asia regional climate models for heat wave simulations over India. Atmos. Res. 248, 105228 (2021). source
- Not checked — no full text of the sourcecites [23] Singh, S., Mall, R. K. & Singh, N. Changing spatio-temporal trends of heat wave and severe heat wave events over India: An emerging health hazard. Int. J. Climatol. 41, E1831–E1845 (2021). source
- Not checked — no full text of the sourcecites [24] Rohini, P., Rajeevan, M. & Mukhopadhay, P. Future projections of heat waves over India from CMIP5 models. Clim. Dyn. 53, 975–988 (2019). source
- Could not verifycites [25] Emmanuel, T. et al. A survey on missing data in machine learning. J. Big Data 8(1), 140. https://doi.org/10.1186/s40537-021-00516-9 (2021). sourceExperimental — accuracy not yet measured
The Missing data patterns section uses references 22–25 to describe patterns of missingness, and the References section identifies the corresponding works. Neither passage says those methods disrupt temporal dependencies or are unsuitable for predicting events from sequential data. Searches for temporal dependencies, time series, and sequential prediction found no passage establishing that claim. (LLM, conf=0.76)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“LSTM struggled in this task, with a precision, F1-score and recall of 0.00.”
§ Comparative analysis of machine learning approaches for heatwave event prediction in India > Methodology and implementation > Performance results of the models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“It had a low-test ROC AUC of 0.4714, indicating its ineffectiveness in the heatwave prediction task.”
§ Comparative analysis of machine learning approaches for heatwave event prediction in India > Methodology and implementation > Performance results of the models
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“While GNNs were found to be less effective for this specific task, the findings contribute valuable insights into the limitations and potential applications of graph-based models in meteorology.”
§ Comparative analysis of machine learning approaches for heatwave event prediction in India > Existing literature
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
20 more claims
Create a free account to see all 60 claims and to verify the 3 references still open.
- It may state two separate claims as one. 25
- Probably not a substantial claim. 12
Citations
Cites
Increasing trends in regional heatwaves
Perkins-Kirkpatrick, S. E., & Lewis, S. C. (2020) · Nature Communications · doi:10.1038/s41467-020-16970-7 · Cited by 1,912
A survey on missing data in machine learning
Emmanuel, T., Maupong, T., Mpoeleng, D., Semong, T., Mphago, B., & Tabona, O. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00516-9 · Cited by 1,067
Xu, Z., FitzGerald, G., Guo, Y., Jalaludin, B., & Tong, S. (2016) · Environment International · doi:10.1016/j.envint.2016.02.007 · Cited by 659
Could Machine Learning Break the Convection Parameterization Deadlock?
Gentine, P., Pritchard, M., Rasp, S., Reinaudi, G., & Yacalis, G. (2018) · Geophysical Research Letters · doi:10.1029/2018gl078202 · Cited by 497 · cited 1×
“Early and accurate predictions of heatwaves play a vital role in mitigating their adverse effects 12 .”
The Excess Heat Factor: A Metric for Heatwave Intensity and Its Use in Classifying Heatwave Severity
Nairn, J., & Fawcett, R. (2014) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph120100227 · Cited by 472
Causal network reconstruction from time series: From theoretical assumptions to practical estimation
Runge, J. (2018) · Chaos: An Interdisciplinary Journal of Nonlinear Science · doi:10.1063/1.5025050 · Cited by 422 · cited 1×
“Predicting heatwaves using time series weather data presents several challenges, primarily due to high class imbalance 17,18 .”
Heatwave classification over Europe and the Mediterranean region
Stefanon, M., D’Andrea, F., & Drobinski, P. (2012) · Environmental Research Letters · doi:10.1088/1748-9326/7/1/014023 · Cited by 347
Weyn, J. A., Durran, D. R., & Caruana, R. (2019) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2019ms001705 · Cited by 347
Moist heat stress extremes in India enhanced by irrigation
Mishra, V., Ambika, A. K., Asoka, A., Aadhar, S., Buzan, J., Kumar, R., & Huber, M. (2020) · Nature Geoscience · doi:10.1038/s41561-020-00650-8 · Cited by 250
Long term climatology and trends of heat waves over India during the recent 50 years (1961-2010)
PAI, D. S., NAIR, S., & RAMANATHAN, A. N. (2013) · MAUSAM · doi:10.54302/mausam.v64i4.742 · Cited by 233
Cited by
Yang, G., Shan, Y., Zhang, Z., et al. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms262311475 · Cited by 6
Mashrafi, M. J., Alif, H. A., Biswas, A., Majumder, N., Romit, F. A., & Alam, I. U. (2025) · International Conference on Communication and Electronics Systems (ICCES) · doi:10.1109/icces67310.2025.11337026 · Cited by 4
Petrou, I., Kassomenos, P. A., & Kyriazis, N. (2025) · Atmosphere · doi:10.3390/atmos16091093 · Cited by 8
Ashford, A., Ayaz, F., Shakir, M. Z., Ramzan, N., Gebreslasie, M. T., Viriri, S., Ndzi, D. L., Dickinson, N., Spencer, L. H., Lynch, M., et al. (2026) · Forecasting · doi:10.3390/forecast8040063
Ansari, W. A., & Dandekar, O. (2026) · Vidhyayana · doi:10.58213/qgvyek92
Metadata
- Authors
- V, R. C., Johnvictor, A. C., & N, P. S.
- Affiliations
- Vellore Institute of Technology University (IN)
- Corresponding author
- Johnvictor, Anita Christaline
- Venue
- Scientific Reports
- Published
- 2025-07-01
- Volume
- 15
- Issue
- 1
- Pages
- 22431-22431
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC12216918
- OpenAlex
- W4411851800
- Cited by
- 9
- References
- 51
- Citations by year
- 2026: 6 · 2025: 3
- FWCI
- 3.58
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Scientific Reports (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Vellore Institute of Technology, Chennai
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models
- Physical Sciences › Environmental Science › Health, Toxicology and Mutagenesis › Climate Change and Health Impacts
- Keywords
- heatwave prediction, extreme weather events, time series forecasting, class imbalance, oversampling, random forest, convolutional neural networks, long short-term memory networks, transformer models, graph neural networks, extreme gradient boosting, autoencoder, anomaly detection, Chennai
- MeSH terms
- Machine Learning, Humans, India, Neural Networks, Computer, Extreme Heat, Climate Change, Support Vector Machine
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Comparative analysis of machine learning approaches for heatwave event prediction in India. https://app.cochat.ai/papers/10.1038/s41598-025-04634-9
- The paper
- V, R. C., Johnvictor, A. C., & N, P. S. (2025). Comparative analysis of machine learning approaches for heatwave event prediction in India. Scientific Reports. https://doi.org/10.1038/s41598-025-04634-9
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.