Extreme heat prediction through deep learning and explainable AI
Open accessThe DOI matches its Crossref record; 26 of the 27 references it cites were found in a registry or an index; 3 of the 18 sources its claims cite were checked for support.
Abstract
Extreme heat waves are causing widespread concern for comprehensive studies on their ecological and societal implications. With the ongoing rise in global temperatures, precise forecasting of heatwaves becomes increasingly crucial for proactive planning and ensuring safety. This study investigates the efficacy of deep learning (DL) models, including Artificial Neural Network (ANN), Conolutional Neural Network (CNN) and Long-Short Term Memory (LSTM), using five years of meteorological data from Pakistan Meteorological Department (PMD), by integrating Explainable AI (XAI) techniques to enhance the interpretability of models. Although Weather forecasting has advanced in predicting sunshine, rain, clouds, and general weather patterns, the study of extreme heat, particularly using advanced computer models, remains largely unexplored, overlooking this gap risks significant disruptions in daily life. Our study addresses this gap by collecting five years of weather dataset and developing a comprehensive framework integrating DL and XAI models for extreme heat prediction. Key variables such as temperature, pressure, humidity, wind, and precipitation are examined. Our findings demonstrate that the LSTM model outperforms others with a lead time of 1–3 days and minimal error metrics, achieving an accuracy of 96.2%. Through the utilization of SHAP and LIME XAI methods, we elucidate the significance of humidity and maximum temperature in accurately predicting extreme heat events. Overall,…
Overview
CoChat Summary
## TL;DR
This paper proposes a deep learning framework for predicting extreme heat in Lahore using five years of PMD weather data (2018–2022) and then explains the predictions with SHAP and LIME. The LSTM model performed best, reaching 96.2% accuracy, and the XAI analysis identified humidity and maximum temperature as the most influential features.
## Key findings
- The study used 1,450 data instances from the XWeather dataset, split 80% for training and 20% for testing.
- Among ANN, CNN, and LSTM, the LSTM model was the most effective, with the highest accuracy of 96.2% and the lowest error metrics reported in the paper.
- A regional extreme-heat threshold was set at the 95th percentile of maximum temperature, corresponding to 41 °C, with a lead time of 1–3 days.
- SHAP and LIME both indicated that humidity and maximum temperature were the most influential variables for predicting extreme heat events.
## Methods
- The paper used a regional meteorological dataset (“XWeather”) for Lahore, Pakistan, collected from PMD over five years (2018–2022), with 12 parameters including pressure, humidity, temperature, precipitation, and wind variables.
- Preprocessing included handling missing values with column averages, label encoding for categorical variables such as wind direction, and min-max numerical scaling.
- Three deep learning models were trained and compared: ANN, CNN, and LSTM, using Python with Keras/TensorFlow; model performance was evaluated with accuracy, RMSE, MAE, and MSE, and SHAP/LIME were applied for interpretability.
## Limitations
- The paper states that future work should include data from desert regions like Al-Ahsa in Saudi Arabia, suggesting the current study is limited to Lahore and may not generalize to other climates.
- The paper also suggests that larger datasets and additional data sources such as satellite imagery and social media could improve performance, implying the current dataset and feature set are limited.
- Evident from the text: the study reports only one regional dataset and one city-level application, so broader external validation is not shown.
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 · 2 Not valid · 7 Not checked · 20 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Limited work on explainable AI: Even though XAI is increasingly being used to improve model interpretability, its applications in extreme heat prediction are limited [21–23, 25, 33, 34] .”
§ Extreme heat prediction through deep learning and explainable AI > 2 Literature review Extreme heat prediction is critical for its serious effects, necessitating extensive global research using a variety of methodologies such as ML, DL, and statistical models. But interpreting and understanding the variables influencing these forecasts is a challenging task. Integrating XAI techniques has the potential to elucidate critical features in models, improve interpretability, and formulate proactive measures to mitigate heat wave effects. This section covers the latest research on the forecasting of extreme heatwaves in different parts of the world. In study [22] Sub-seasonal performance analyzed in Central Europe using linear and RF models, revealing accurate ECMWF forecasts with 1-6 weeks lead times. Local air temperature, 500 hPa soil temperature, and precipitation, were identified as the greatest predictors of summer anomalies and heat waves. The temperature data from 27 grid points are used in another study [23] to forecast the number of annual heatwave days in Iran. Ada-Boost Regression and Decision Tree (ABR-DT), a hybrid approach that combines traditional machine learning algorithms and hybrid methods, performs better than the other methods with a correlation coefficient of 0.860 and a mean absolute error of 6.929. The research [19] develops a climate change-resilient heatwave prediction model using machine learning methods like SVM, random forest, and artificial neural network, outperforming other models in Pakistan summer heatwave days. A climate change study on Trinidad and Tobago using Sen’s slope estimator and Mann-Kendall tests found significant increases in minimum and maximum temperatures over 30 years, with no significant changes in monthly rainfall. This suggests warmer winters and hotter summers [20]. The neural weather model, ExtNet [25], outperforms historical data in predicting heat events with lead time of 1 to 28 days in sub seasonal conditions. The next study [26] assesses the prediction of summer high temperatures in Western and Central Europe using statistical modeling and a machine learning model on the ERA5 dataset, with a 15-day lead time, concentrating on climate change and driving variables. The study [24] compares ANN and Gene Expression Programming (GEP) for temperature prediction in Tabuk, Saudi Arabia. GEP, using inputs like pressure, wind speed, humidity, and rainfall, proves more accurate and reliable for agricultural forecasting. However, in study [21] Convolutional Neural Network trained using 1000 years of climate model results, Planet Simulator, large-class under-sampling, and transfer learning, accurately anticipates long-lasting intense heat waves up to 15 days in advance. A real-time heatwave monitoring method [27] for the Indian subcontinent, utilizing machine learning to predict extreme heat indices two to three days in advance. The SWAT (Soil and Water Assessment Tool) model in [29] showed that climate change could increase extreme heat temperatures by 1–4 °C in the Gharesou Basin, affecting water availability. The QRF model, based on synoptic climate variables, outperforms classical random forest in Pakistan’s heatwave forecasting, predicting triggering and departure dates with 1–10 days lead times [30]. The LSTM neural networks [7] is utilized to predict heatwave maximum temperatures. Moreover, a data-driven solution [31] using Capsule Neural Networks (Caps Nets) for weather forecasting extremes, outperforming numerical models and demonstrating the power of deep learning methods. However, the study [32] explores climate change’s impact on the China-Pakistan Economic Corridor, revealing its vulnerability to heat waves from 1980 to 2016, with continuous activity in Pakistan’s southern, middle, and eastern regions. The study [18] employs Recurrent Neural Networks and LSTM models to estimate daily temperatures from BMKG in Bandung, with accuracy enhanced by pre-processing and optimization models. The study [28] forecasts temperature and geopotential approximately three to five days in advance using a full stacked neural network approach, specifically convolutional ResNet over the ERA5 dataset. The study [1] reveals a global concentration of heatwave research and health impacts, primarily in mid-latitude, high-income countries, with underrepresentation in areas like tropical and high-latitude areas, South America, Africa, Eastern Europe, Middle East, and Asia. It is anticipated that in the near future, South Asian regions and its neighbors would be extremely affected by HWs, which will have significant socioeconomic effects [32]. Limited work exists on regional datasets: In the field of extreme heat prediction, there has been relatively little focus on datasets specific to south Asian regions [7, 19, 27] despite this being a critical and emerging area of interest. The complexity of acquiring localized data often poses a significant barrier, which may explain the scarcity of such studies. To address this gap, we collected regional data from the PMD, preprocessed it, and named it the XWeather dataset. To the best of our knowledge, limited work has utilized local datasets in this context, highlighting the novelty and potential impact of our approach.
What the sources say
- Not matchedcites [21]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [22]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites [23]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Could not verifycites [25] I Lopez-Gomez, 2023, Global extreme heat forecasting using neural weather models, Artif Intell Earth Syst sourceExperimental — accuracy not yet measured
Section 5, “Model interpretation” (page unavailable), applies integrated gradients to interpret an extreme-heat forecasting model. It does not assess how widespread XAI applications are in extreme-heat prediction, so it cannot establish the claim that such applications are limited. Searches for explainability, interpretability, and feature attribution found no statement of that limitation. (LLM, conf=0.72)
- Could not verifycites [33] C O’Brien-Delpesh, 2022, Preserving fragile ecosystems from oil spills – an environmental sensitivity assessment of the east coast of Trinidad, Ocean Coastal Manag sourceExperimental — accuracy not yet measured
The Introduction and §3.2 discuss environmental sensitivity mapping for oil spills, while §3.3 describes models that predict diesel dispersion. Searches for explainable AI, model interpretability, and extreme heat prediction found no passage addressing whether XAI applications in extreme heat prediction are limited. (LLM, conf=0.76)
- Not matchedcites [34] A Perera, 2020, Recent climatic trends in Trinidad and Tobago, West Indies. Asia-Pac J Sci Technol.
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
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.
- Not matched
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“While much work has been done to integrate XAI with machine learning models [26, 37], there has been little research into applying XAI to DL models, particularly in the context of extreme heat prediction.”
§ Extreme heat prediction through deep learning and explainable AI > 2 Literature review Extreme heat prediction is critical for its serious effects, necessitating extensive global research using a variety of methodologies such as ML, DL, and statistical models. But interpreting and understanding the variables influencing these forecasts is a challenging task. Integrating XAI techniques has the potential to elucidate critical features in models, improve interpretability, and formulate proactive measures to mitigate heat wave effects. This section covers the latest research on the forecasting of extreme heatwaves in different parts of the world. In study [22] Sub-seasonal performance analyzed in Central Europe using linear and RF models, revealing accurate ECMWF forecasts with 1-6 weeks lead times. Local air temperature, 500 hPa soil temperature, and precipitation, were identified as the greatest predictors of summer anomalies and heat waves. The temperature data from 27 grid points are used in another study [23] to forecast the number of annual heatwave days in Iran. Ada-Boost Regression and Decision Tree (ABR-DT), a hybrid approach that combines traditional machine learning algorithms and hybrid methods, performs better than the other methods with a correlation coefficient of 0.860 and a mean absolute error of 6.929. The research [19] develops a climate change-resilient heatwave prediction model using machine learning methods like SVM, random forest, and artificial neural network, outperforming other models in Pakistan summer heatwave days. A climate change study on Trinidad and Tobago using Sen’s slope estimator and Mann-Kendall tests found significant increases in minimum and maximum temperatures over 30 years, with no significant changes in monthly rainfall. This suggests warmer winters and hotter summers [20]. The neural weather model, ExtNet [25], outperforms historical data in predicting heat events with lead time of 1 to 28 days in sub seasonal conditions. The next study [26] assesses the prediction of summer high temperatures in Western and Central Europe using statistical modeling and a machine learning model on the ERA5 dataset, with a 15-day lead time, concentrating on climate change and driving variables. The study [24] compares ANN and Gene Expression Programming (GEP) for temperature prediction in Tabuk, Saudi Arabia. GEP, using inputs like pressure, wind speed, humidity, and rainfall, proves more accurate and reliable for agricultural forecasting. However, in study [21] Convolutional Neural Network trained using 1000 years of climate model results, Planet Simulator, large-class under-sampling, and transfer learning, accurately anticipates long-lasting intense heat waves up to 15 days in advance. A real-time heatwave monitoring method [27] for the Indian subcontinent, utilizing machine learning to predict extreme heat indices two to three days in advance. The SWAT (Soil and Water Assessment Tool) model in [29] showed that climate change could increase extreme heat temperatures by 1–4 °C in the Gharesou Basin, affecting water availability. The QRF model, based on synoptic climate variables, outperforms classical random forest in Pakistan’s heatwave forecasting, predicting triggering and departure dates with 1–10 days lead times [30]. The LSTM neural networks [7] is utilized to predict heatwave maximum temperatures. Moreover, a data-driven solution [31] using Capsule Neural Networks (Caps Nets) for weather forecasting extremes, outperforming numerical models and demonstrating the power of deep learning methods. However, the study [32] explores climate change’s impact on the China-Pakistan Economic Corridor, revealing its vulnerability to heat waves from 1980 to 2016, with continuous activity in Pakistan’s southern, middle, and eastern regions. The study [18] employs Recurrent Neural Networks and LSTM models to estimate daily temperatures from BMKG in Bandung, with accuracy enhanced by pre-processing and optimization models. The study [28] forecasts temperature and geopotential approximately three to five days in advance using a full stacked neural network approach, specifically convolutional ResNet over the ERA5 dataset. The study [1] reveals a global concentration of heatwave research and health impacts, primarily in mid-latitude, high-income countries, with underrepresentation in areas like tropical and high-latitude areas, South America, Africa, Eastern Europe, Middle East, and Asia. It is anticipated that in the near future, South Asian regions and its neighbors would be extremely affected by HWs, which will have significant socioeconomic effects [32]. Limited work exists on regional datasets: In the field of extreme heat prediction, there has been relatively little focus on datasets specific to south Asian regions [7, 19, 27] despite this being a critical and emerging area of interest. The complexity of acquiring localized data often poses a significant barrier, which may explain the scarcity of such studies. To address this gap, we collected regional data from the PMD, preprocessed it, and named it the XWeather dataset. To the best of our knowledge, limited work has utilized local datasets in this context, highlighting the novelty and potential impact of our approach.
What the sources say
- Supportedcites [26] C van Straaten, 2022, Using explainable machine learning forecasts to discover subseasonal drivers of high summer temperatures in Western and Central Europe, Monthly Weather Rev source
The citation is attached to the statement that XAI has been integrated with machine-learning models, not to the subsequent claim about a shortage of deep-learning research. The Introduction describes using explainability tools with a random-forest model to forecast high European temperatures, and the Explainability section specifies permutation importance and TreeSHAP (pages unavailable). (LLM, conf=0.89)
- Not checked — no full text of the sourcecites [37] ND Wimalagunarathna, 2024, Effect of endogenous and anthropogenic factors on the alkalinisation and salinisation of freshwater in United States by using explainable machine learning, Case Stud Chem Environ Eng source
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.
- Supported
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
“the XWeather dataset, collected from PMD, spans over five years from 2018 to 2022 and comprises twelve parameters, including date, pressure, humidity, minimum and maximum temperatures, precipitation, wind speed, and wind direction, recorded at 300 and 1200 UTC”
§ Extreme heat prediction through deep learning and explainable AI > 3 Proposed methodology > 3.1 Dataset details
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
“Parameters crucial for making predictions, such as maximum temperature and humidity at 1200 UTC, are highlighted in orange, whereas less significant parameters are marked in blue.”
§ Extreme heat prediction through deep learning and explainable AI > 5 Results and discussions > 5.2 Interpretability of DL Model using SHAP and LIME models
plainstates an association- 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
“achieving an accuracy of 96.2%”
- Also stated in: § 4.6 LSTM model training · plain
“achieving an accuracy of 96.2%”
§ Extreme heat prediction through deep learning and explainable AI > Abstract Extreme heat waves are causing widespread concern for comprehensive studies on their ecological and societal implications. With the ongoing rise in global temperatures, precise forecasting of heatwaves becomes increasingly crucial for proactive planning and ensuring safety. This study investigates the efficacy of deep learning (DL) models, including Artificial Neural Network (ANN), Conolutional Neural Network (CNN) and Long-Short Term Memory (LSTM), using five years of meteorological data from Pakistan Meteorological Department (PMD), by integrating Explainable AI (XAI) techniques to enhance the interpretability of models. Although Weather forecasting has advanced in predicting sunshine, rain, clouds, and general weather patterns, the study of extreme heat, particularly using advanced computer models, remains largely unexplored, overlooking this gap risks significant disruptions in daily life. Our study addresses this gap by collecting five years of weather dataset and developing a comprehensive framework integrating DL and XAI models for extreme heat prediction. Key variables such as temperature, pressure, humidity, wind, and precipitation are examined. Our findings demonstrate that the LSTM model outperforms others with a lead time of 1–3 days and minimal error metrics, achieving an accuracy of 96.2%. Through the utilization of SHAP and LIME XAI methods, we elucidate the significance of humidity and maximum temperature in accurately predicting extreme heat events. Overall, this study emphasizes how important it is to investigate intricate DL models that integrate XAI for the prediction of extreme heat. Making these models understood allows us to identify important parameters, improving heatwave forecasting accuracy and guiding risk-reduction strategies.
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.
- Also stated in: § 4.6 LSTM model training · plain
7 more claims
Create a free account to see all 30 claims and every source verdict.
- Probably not a substantial claim. 6
- It may state two separate claims as one. 14
- The quote only partly states this claim. 4
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?
The cited source says what the claim attributes to it.
In the citing paper
“In the broader area of extreme heat forecasting, deep learning models have already been applied to predict extreme heat events from meteorological variables, and the reported results indicate that such data-driven approaches can achieve good predictive performance [22].”
From GPU-Accelerated Deep Learning for Heatwave Prediction and Urban Heat Risk Assessment (2026) · cites this paper as [22]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated major: it would touch a result — a value a result rests on, reported and recomputed p-values on opposite sides of the significance level, two passages that conflict with no sign which is right, or a cited work retracted before this paper was published.
In the paper
§ Extreme heat prediction through deep learning and explainable AI > 3 Proposed methodology > 3.2 Deep learning model development
“To optimize the model, we used a batch size of 32 during training over 50 epochs, balancing computational efficiency and model convergence.”
§ Extreme heat prediction through deep learning and explainable AI > 4 Experimentation > 4.4 ANN model training
“The training process was completed in 20 epochs, ensuring effective model convergence while balancing training time.”
Citations
Cites
Heatwave and health impact research: A global review
Campbell, S., Remenyi, T. A., White, C. J., & Johnston, F. H. (2018) · Health & Place · doi:10.1016/j.healthplace.2018.08.017 · Cited by 573 · cited 2×
“The study [1] reveals a global concentration of heatwave research and health impacts, primarily in mid-latitude, high-income countries, with underrepresentation in areas like tropical and high-latitude areas, South America, Africa, Eastern Europe, Middle East, and Asia.”
Changes in regional heatwave characteristics as a function of increasing global temperature
Perkins-Kirkpatrick, S. E., & Gibson, P. B. (2017) · Scientific Reports · doi:10.1038/s41598-017-12520-2 · Cited by 472 · cited 1×
“Extended heatwaves can cause far more havoc than a single, severe day’s temperature [3].”
Vimbi, V., Shaffi, N., & Mahmud, M. (2024) · Brain Informatics · doi:10.1186/s40708-024-00222-1 · Cited by 433 · cited 1×
“Since LIME is model agnostic, it can be used with any model and is primarily utilized as a local explainer [46,47].”
Predictability of Euro-Russian blocking in summer of 2010: EURO-RUSSIAN BLOCKING IN SUMMER 2010
Matsueda, M. (2011) · Geophysical Research Letters · doi:10.1029/2010gl046557 · Cited by 279 · cited 1×
“In 2010, there was an atmospheric blockage in Eastern Europe and Western Russia [5] that resulted in over a month of intense heat and 1500 tragic deaths.”
Interpretable and explainable AI (XAI) model for spatial drought prediction
Dikshit, A., & Pradhan, B. (2021) · Science of The Total Environment · doi:10.1016/j.scitotenv.2021.149797 · Cited by 272 · cited 1×
“After obtaining predictions from the LSTM model, we utilized XAI techniques to enhance the transparency of the black-box model. not show how individual predictors affect prediction capability due to the additive nature of this characteristic [48].”
Deep learning-based effective fine-grained weather forecasting model
Hewage, P., Trovati, M., Pereira, E., & Behera, A. (2021) · Pattern Analysis and Applications · doi:10.1007/s10044-020-00898-1 · Cited by 244 · cited 1×
“LSTM, a DL models have garnered attention for weather forecasting [13–16].”
Prediction of heat waves in Pakistan using quantile regression forests
Khan, N., Shahid, S., Juneng, L., Ahmed, K., Ismail, T., & Nawaz, N. (2019) · Atmospheric Research · doi:10.1016/j.atmosres.2019.01.024 · Cited by 118
Ukwaththa, J., Herath, S., & Meddage, D. P. P. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.110294 · Cited by 118 · cited 1×
“XAI models doesn’t affect the accuracies and computations of the ML or DL models on which it is used, but it helps in the decision-making process by providing insights into it [38].”
Short-Term Weather Forecasting Using Spatial Feature Attention Based LSTM Model
Suleman, M. A. R., & Shridevi, S. (2022) · IEEE Access · doi:10.1109/access.2022.3196381 · Cited by 97
Assessment of Climate Change Impact on the Gharesou River Basin Using SWAT Hydrological Model
Zahabiyoun, B., Goodarzi, M. R., Bavani, A. R. M., & Azamathulla, H. M. (2012) · CLEAN - Soil Air Water · doi:10.1002/clen.201100652 · Cited by 79 · cited 1×
“The SWAT (Soil and Water Assessment Tool) model in [29] showed that climate change could increase extreme heat temperatures by 1–4 °C in the Gharesou Basin, affecting water availability.”
Al-Bouwarthan, M., Quinn, M., Kriebel, D., & Wegman, D. H. (2020) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph17113775 · Cited by 76 · cited 1×
“This highlights the broader effects of heatwaves across different regions [12].”
Ullah, S., You, Q., Ullah, W., Hagan, D. F. T., Ali, A., Ali, G., Zhang, Y., Jan, M. A., Bhatti, A. S., & Xie, W. (2019) · Climate Dynamics · doi:10.1007/s00382-019-04934-7 · Cited by 72 · cited 2×
“It is anticipated that in the near future, South Asian regions and its neighbors would be extremely affected by HWs, which will have significant socioeconomic effects [32].”
Khan, N., Shahid, S., Ismail, T. B., & Behlil, F. (2021) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-020-01963-1 · Cited by 59 · cited 3×
“Limited work exists on regional datasets: In the field of extreme heat prediction, there has been relatively little focus on datasets specific to south Asian regions [7,19,27] despite this being a critical and emerging area of interest.”
Combining distribution‐based neural networks to predict weather forecast probabilities
Clare, M. C. A., Jamil, O., & Morcrette, C. J. (2021) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.4180 · Cited by 52
Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning
Ranasinghe, R. S. S., Kulasooriya, W. K. V. J. B., Perera, U. S., Ekanayake, I. U., Meddage, D. P. P., Mohotti, D., & Rathanayake, U. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.102503 · Cited by 51
van Straaten, C., Whan, K., Coumou, D., van den Hurk, B., & Schmeits, M. (2022) · Monthly Weather Review · doi:10.1175/mwr-d-21-0201.1 · Cited by 50
Heatwave Damage Prediction Using Random Forest Model in Korea
Park, M., Jung, D., Lee, S., & Park, S. (2020) · Applied Sciences · doi:10.3390/app10228237 · Cited by 46 · cited 1×
“As one of the main contributors to both natural and human disasters, heatwaves must be addressed, and preventive measures must be taken to lessen the damage [2].”
Global extreme heat forecasting using neural weather models
Lopez-Gomez, I., McGovern, A., Agrawal, S., & Hickey, J. (2023) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-22-0035.1 · Cited by 41 · cited 2×
“…AI: Even though XAI is increasingly being used to improve model interpretability, its applications in extreme heat prediction are limited [21–23, 25, 33, Limited work on deep learning with XAI: DL models are complex [35], [36] and frequently known as ”black boxes” making it difficult to…”
Perera, U. A. K. K., Coralage, D. T. S., Ekanayake, I. U., Alawatugoda, J., & Meddage, D. P. P. (2024) · Results in Engineering · doi:10.1016/j.rineng.2024.101920 · Cited by 39
Azamathulla, H. M., Rathnayake, U., & Shatnawi, A. (2018) · Applied Water Science · doi:10.1007/s13201-018-0831-6 · Cited by 33
Global Warming in Pakistan and Its Impact on Public Health as Viewed Through a Health Equity Lens
Somani, R. K. (2023) · International Journal of Social Determinants of Health and Health Services · doi:10.1177/27551938231154467 · Cited by 25 · cited 1×
“In this paradigm, Pakistan find itself more a victim than a catalyst of these climate changes [9].”
Projection of climate variables by general circulation and deep learning model for Lahore, Pakistan
Nguyen, D., Ashraf, S., Le, M.-T., Trung, L. Q., & Ali, M. (2023) · Ecological Informatics · doi:10.1016/j.ecoinf.2023.102077 · Cited by 19 · cited 1×
“Serious concerns regarding the 21st century arise from global changes in weather patterns [8].”
Mardian, J., Champagne, C. M., Bonsal, B. R., & van den Berg, A. A. (2023) · Journal of Hydrometeorology · doi:10.1175/jhm-d-23-0036.1 · Cited by 19 · cited 1×
“Deep SHAP computes the SHAP values for each component using the compositional nature of neural networks to provide estimates of SHAP insights for the entire network [42,43].”
O'Brien-Delpesh, C., Sinanan, N., Martin, H., & Chadee, A. (2022) · Ocean & Coastal Management · doi:10.1016/j.ocecoaman.2022.106374 · Cited by 17
Spatial-Temporal Seasonal Variability of Extreme Precipitation under Warming Climate in Pakistan
Abbas, S., Waseem, M., Yaseen, M., Latif, Y., Leta, M. K., Khan, T. H., & Muhammad, S. (2023) · Atmosphere · doi:10.3390/atmos14020210 · Cited by 17 · cited 1×
“However, during the past three decades, Pakistan has seen an increase in severe weather events [10] comparable to the vulnerabilities found in coastal Ecosystems especially vulnerable to oil spills and human activities, like mangroves and leatherback turtle nesting sites along Trinidad’s east coast…”
Wimalagunarathna, N. D., Dharmarathne, G., Ekanayake, I. U., Rathanayake, U., Alwatugoda, J., & Meddage, D. P. P. (2024) · Case Studies in Chemical and Environmental Engineering · doi:10.1016/j.cscee.2024.100919 · Cited by 8 · cited 1×
“Deep SHAP computes the SHAP values for each component using the compositional nature of neural networks to provide estimates of SHAP insights for the entire network [42,43].”
Research works printed but not linked: 8
- S Sajjad, 2015, The long-term variability in minimum and maximum temperature trends and heat island of Lahore city, Pakistan. Sci Int., 27, 1321
- A Perera, 2020, Recent climatic trends in Trinidad and Tobago, West Indies. Asia-Pac J Sci Technol., 25, 1
- C O’Brien-Delpesh, 2022, Preserving fragile ecosystems from oil spills – an environmental sensitivity assessment of the east coast of Trinidad, Ocean Coastal Manag, 230, 106374, 10.1016/j.ocecoaman.2022.106374 · DOI · Paper page
- A Perera, 2020, Recent climatic trends in Trinidad and Tobago, West Indies. Asia-Pac J Sci Technol., 25, 1
- RSS Ranasinghe, 2024, Eco-friendly mix design of slag-ash-based geopolymer concrete using explainable deep learning, Results Eng, 23, 102503, 10.1016/j.rineng.2024.102503 · DOI · Paper page
- ND Wimalagunarathna, 2024, Effect of endogenous and anthropogenic factors on the alkalinisation and salinisation of freshwater in United States by using explainable machine learning, Case Stud Chem Environ Eng, 10, 100919, 10.1016/j.cscee.2024.100919 · DOI · Paper page
- UAKK Perera, 2024, A new frontier in streamflow modeling in ungauged basins with sparse data: a modified generative adversarial network with explainable AI, Results Eng, 21, 101920, 10.1016/j.rineng.2024.101920 · DOI · Paper page
- A Dikshit, 2021, Interpretable and explainable AI (XAI) model for spatial drought prediction, Sci Total Environ, 801, 149797, 10.1016/j.scitotenv.2021.149797 · DOI · Paper page
Cited by
Im, C., Kim, W., & Kim, H. (2025) · Bioengineering · doi:10.3390/bioengineering12111276 · Cited by 11
From Black Box to Insight: Explainable AI for Extreme Event Preparedness
Vu, K., Özer, İ. S., Lai, P., Wu, Z., Munasinghe, T., & Wei, J. (2025) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata66926.2025.11401078 · 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
“Solar and longwave radiation were reported in five studies [28,29,46,47,49], and precipitation-related variables, including rainfall, snow cover, and sea ice in five studies [35,37,42,45,50].”
InfluentialGPU-Accelerated Deep Learning for Heatwave Prediction and Urban Heat Risk Assessment
Alihodžić, A. (2026) · arXiv · doi:10.48550/arxiv.2605.16435
“In the broader area of extreme heat forecasting, deep learning models have already been applied to predict extreme heat events from meteorological variables, and the reported results indicate that such data-driven approaches can achieve good predictive performance [22].”
Easton-Calabria, L., & Patel, K. (2026) · Climate Risk Management · doi:10.1016/j.crm.2026.100827 · Cited by 1
Metadata
- Authors
- Shafiq, F., Zafar, A., Ghani Khan, M. U., Iqbal, S., Albesher, A. S., & Asghar, M. N.
- Affiliations
- University of Engineering and Technology Lahore (PK)
- King Faisal University (SA)
- Corresponding author
- Iqbal, Sajid
- Venue
- PLoS ONE
- Publisher
- Public Library of Science (PLoS)
- Published
- 2025-03-20
- Volume
- 20
- Issue
- 3
- Pages
- e0316367
- ISSN
- 1932-6203 (ISSN-L)
- PMC
- PMC11925282
- OpenAlex
- W4408659870
- Cited by
- 8
- References
- 27
- Citations by year
- 2026: 6 · 2025: 2
- FWCI
- 2.20
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- PLoS ONE (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Deanship of Scientific Research, King Faisal University (GrantA468)
- Topics
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations
- Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models
- Keywords
- heatwave prediction, explainable AI, SHAP, lime, LSTM, artificial neural networks, convolutional neural networks, meteorological observations, humidity, maximum temperature
- MeSH terms
- Deep Learning, Forecasting, Humans, Pakistan, Weather, Neural Networks, Computer, Extreme Heat
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
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.