Recent advances in explainable Machine Learning models for wildfire prediction
Climate change has caused increasingly frequent occurrences of forest fires around the world. Machine Learning (ML) and Artificial Intelligence models have emerged to predict both the onset of wildfires and evaluate the extent of damage a wildfire would cause. However, understanding what factors lea...
Saved in:
| Published in: | Applied computing and geosciences Vol. 27; p. 100266 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Ltd
01.09.2025
Elsevier |
| Subjects: | |
| ISSN: | 2590-1974, 2590-1974 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Climate change has caused increasingly frequent occurrences of forest fires around the world. Machine Learning (ML) and Artificial Intelligence models have emerged to predict both the onset of wildfires and evaluate the extent of damage a wildfire would cause. However, understanding what factors lead to generating models that exhibit optimal performance and providing insight into the importance of features on model outcomes is the subject of ongoing research. To help answer these questions, we propose a framework which adopts recent advances in methods for obtaining optimal models along with the application of SHAP (SHapley Additive exPlanations) values to obtain the most important features which affect the performance of wildfire prediction models. We use this framework as a classification task to predict the likelihood of wildfire occurrence based on environmental conditions, using a data set which represents instances of forest fires in Algerian, and as a regression task to predict the burned area once a wildfire has begun, using a data set from Portugal that recorded the area burned after a fire event. Insights provided by this framework allow us to assess the efficacy of specific ML models for wildfire prediction, ultimately making recommendations as to which ML models are more suited towards these challenging tasks.
[Display omitted]
•Machine learning model framework for wildfire forecasting and burned area estimation.•Shapley values show interactions between features that influence model predictions.•Adopting a new method to show contributions of hyper-parameters on model learning. |
|---|---|
| AbstractList | Climate change has caused increasingly frequent occurrences of forest fires around the world. Machine Learning (ML) and Artificial Intelligence models have emerged to predict both the onset of wildfires and evaluate the extent of damage a wildfire would cause. However, understanding what factors lead to generating models that exhibit optimal performance and providing insight into the importance of features on model outcomes is the subject of ongoing research. To help answer these questions, we propose a framework which adopts recent advances in methods for obtaining optimal models along with the application of SHAP (SHapley Additive exPlanations) values to obtain the most important features which affect the performance of wildfire prediction models. We use this framework as a classification task to predict the likelihood of wildfire occurrence based on environmental conditions, using a data set which represents instances of forest fires in Algerian, and as a regression task to predict the burned area once a wildfire has begun, using a data set from Portugal that recorded the area burned after a fire event. Insights provided by this framework allow us to assess the efficacy of specific ML models for wildfire prediction, ultimately making recommendations as to which ML models are more suited towards these challenging tasks. Climate change has caused increasingly frequent occurrences of forest fires around the world. Machine Learning (ML) and Artificial Intelligence models have emerged to predict both the onset of wildfires and evaluate the extent of damage a wildfire would cause. However, understanding what factors lead to generating models that exhibit optimal performance and providing insight into the importance of features on model outcomes is the subject of ongoing research. To help answer these questions, we propose a framework which adopts recent advances in methods for obtaining optimal models along with the application of SHAP (SHapley Additive exPlanations) values to obtain the most important features which affect the performance of wildfire prediction models. We use this framework as a classification task to predict the likelihood of wildfire occurrence based on environmental conditions, using a data set which represents instances of forest fires in Algerian, and as a regression task to predict the burned area once a wildfire has begun, using a data set from Portugal that recorded the area burned after a fire event. Insights provided by this framework allow us to assess the efficacy of specific ML models for wildfire prediction, ultimately making recommendations as to which ML models are more suited towards these challenging tasks. [Display omitted] •Machine learning model framework for wildfire forecasting and burned area estimation.•Shapley values show interactions between features that influence model predictions.•Adopting a new method to show contributions of hyper-parameters on model learning. |
| ArticleNumber | 100266 |
| Author | Woodford, Brendon J. Sengupta, Abira |
| Author_xml | – sequence: 1 givenname: Abira orcidid: 0000-0002-6867-3362 surname: Sengupta fullname: Sengupta, Abira email: sengupta.abira0609@gmail.com – sequence: 2 givenname: Brendon J. surname: Woodford fullname: Woodford, Brendon J. |
| BookMark | eNp9kNtKAzEQhoNU8NQn8CYv0JrTZncvvBDxUKgKotdhNpnUlDVbkqXq2xutiFdezfAz_8fwHZFJHCIScsrZnDOuz9ZzsLDKc8FEVRImtN4jh6Jq2Yy3tZr82Q_INOc1KzcV51XND8n9I1qMIwW3hWgx0xApvm96CBG6Hukd2JcQkS4RUgxxRV8Hh32mfkj0LfTOh4R0k9AFO4YhnpB9D33G6c88Js_XV0-Xt7Plw83i8mI5s1LrccZFeQna2ndaNgx8q5yQqLu6EYx7h413GirfcNX4WnotdddKxWsF2ipEJY_JYsd1A6zNJoVXSB9mgGC-gyGtDKQx2B4NStdgo4RqtVfAmw4rJZmQXCPXlmFhyR3LpiHnhP6Xx5n5MmzW5tuw-TJsdoZL63zXKjZwGzCZbAMWha4YsWP5I_zb_wRnTYX4 |
| Cites_doi | 10.1175/1520-0442(2004)017<2866:SDPICA>2.0.CO;2 10.1214/13-STS451 10.1109/ACCESS.2019.2957837 10.1016/j.ecoinf.2024.102598 10.1006/jcss.1997.1504 10.3390/rs13132513 10.1007/s11676-024-01717-7 10.1071/WF06002 10.1038/nclimate1633 10.5194/bg-13-3359-2016 10.1109/5254.708428 10.1029/2010RG000345 10.1080/01621459.1937.10503522 10.1016/j.aci.2018.08.003 10.1016/j.agwat.2019.105758 10.1071/WF18018 10.1007/s10346-015-0557-6 10.5558/tfc65258-4 10.1023/A:1010933404324 10.1029/2022GL099368 10.3389/frsen.2022.825190 10.32604/jai.2024.054314 10.1016/S1364-8152(01)00072-X 10.3390/rs16040715 10.1177/030913259101500205 10.1029/2008GL035333 10.1162/neco.2006.18.7.1678 10.1016/j.heliyon.2023.e18064 10.1016/j.jenvman.2008.07.005 10.3390/math9060691 10.1016/j.rse.2020.111702 |
| ContentType | Journal Article |
| Copyright | 2025 The Authors |
| Copyright_xml | – notice: 2025 The Authors |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.acags.2025.100266 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Open Access: DOAJ - Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Geology |
| EISSN | 2590-1974 |
| ExternalDocumentID | oai_doaj_org_article_e3d8e842496f4a18be54302316e16c0e 10_1016_j_acags_2025_100266 S2590197425000485 |
| GroupedDBID | 0R~ 6I. AAEDW AAFTH AALRI AAXUO AAYWO ACLIJ ACVFH ADCNI ADVLN AEUPX AFJKZ AFPUW AIGII AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ APXCP EBS FDB GROUPED_DOAJ M41 M~E OK1 ROL AAYXX CITATION |
| ID | FETCH-LOGICAL-c366t-12259a97fb6380af94d23e6b78201fde8fd6a5f8148f73f636b934174a6c4ee43 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001546503100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2590-1974 |
| IngestDate | Fri Oct 03 12:53:11 EDT 2025 Sat Nov 29 07:28:41 EST 2025 Sun Oct 19 01:40:14 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Explainable artificial intelligence Hyper-parameter optimisation SHAP values Forest fires Machine learning |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c366t-12259a97fb6380af94d23e6b78201fde8fd6a5f8148f73f636b934174a6c4ee43 |
| ORCID | 0000-0002-6867-3362 |
| OpenAccessLink | https://doaj.org/article/e3d8e842496f4a18be54302316e16c0e |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_e3d8e842496f4a18be54302316e16c0e crossref_primary_10_1016_j_acags_2025_100266 elsevier_sciencedirect_doi_10_1016_j_acags_2025_100266 |
| PublicationCentury | 2000 |
| PublicationDate | September 2025 2025-09-00 2025-09-01 |
| PublicationDateYYYYMMDD | 2025-09-01 |
| PublicationDate_xml | – month: 09 year: 2025 text: September 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied computing and geosciences |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Conover, Iman (b11) 1979 Farhad Mortezapour, Thinagaran, Norwati, Raihani (b18) 2024; 6 Hansen, Ruedy, Sato, Lo (b24) 2010; 48 Hearst, Dumais, Osuna, Platt, Scholkopf (b27) 1998; 13 Badhan, Shamsaei, Ebrahimian, Bebis, Lareau, Rowell (b4) 2024; 16 Breiman (b7) 2001; 45 Davies, Legg (b14) 2016; e2649 Shabbar, Skinner (b42) 2004; 17 Abid, Izeboudjen (b1) 2020 Raghunath, Kumar, Venkatesan, Singh, Mahesh, Singh (b40) 2022; 21 Freund, Schapire (b20) 1997; 55 Tharwat (b48) 2021; 17 Fan, Ma, Wu, Zhang, Yu, Zeng (b17) 2019; 225 Mell, Jenkins, Gould, Cheney (b36) 2007; 16 The European Space Agency (b49) 2021 Suthaharan (b46) 2015; no. 36 Goodchild (b23) 1991; 15 Hantson, Arneth, Harrison, Kelley, Prentice, Rabin, Archibald, Mouillot, Arnold, Artaxo, Bachelet, Ciais, Forrest, Friedlingstein, Hickler, Kaplan, Kloster, Knorr, Lasslop, Li, Mangeon, Melton, Meyn, Sitch, Spessa, van der Werf, Voulgarakis, Yue (b25) 2016; 13 Sullivan (b45) 2019 Chen, Guestrin (b10) 2016 Ke, Meng, Finley, Wang, Chen, Ma, Ye, Liu (b29) 2017; 30 Anon (b3) 1993 Hastie, Tibshirani, Friedman (b26) 2009 Tien Bui, Tuan, Klempe, Pradhan, Revhaug (b50) 2016; 13 Kondylatos, Prapas, Ronco, Papoutsis, Camps-Valls, Piles, Fernández-Torres, Carvalhais (b31) 2022; 49 Shrestha, Solomatine (b43) 2006; 18 Bhatt, Chouhan (b6) 2024; 35 Gibson, Danaher, Hehir, Collins (b22) 2020; 240 Jaafari, Pourghasemi (b28) 2019 Martínez, Vega-Garcia, Chuvieco (b35) 2009; 90 Cortez, Morais (b12) 2007 Dessler, Zhang, Yang (b16) 2008; 35 Naderpour, Rizeei, Ramezani (b37) 2021; 13 Akiba, Sano, Yanase, Ohta, Koyama (b2) 2019 Breiman, Friedman, Olshen, Stone (b8) 2017 Friedman (b21) 1937; 32 Oliveira, Torgo, Santos Costa (b38) 2021; 9 Zaidi (b53) 2023; 9 Tyukavina, Potapov, Hansen, Pickens, Stehman, Turubanova, Parker, Zalles, Lima, Kommareddy, Song, Wang, Harris (b51) 2022; 3 Liang, Zhang, Wang (b32) 2019; 7 Sarkar, Majhi, Pathak, Biswas, Mahapatra, Kumar, Bhatt, Kuniyal, Nautiyal (b41) 2024; 81 Dai (b13) 2013; 3 Taylor, Woolford, Dean, Martell (b47) 2013; 28 Khalil Alsmadi, Omar, Noah, Almarashdah (b30) 2009 Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel, Blondel, Prettenhofer, Weiss, Dubourg, Vanderplas, Passos, Cournapeau, Brucher, Perrot, Duchesnay (b39) 2011; 12 California Air Resources Board (b9) 2024 Lundberg, Lee (b34) 2017 Bergstra, Yamins, Cox (b5) 2013 de Bem, de Carvalho Júnior, Matricardi, Guimarães, Gomes (b15) 2018; 28 Finney, Grenfell, McHugh (b19) 2009; 55 Stocks, Lynham, Lawson, Alexander, Wagner, McAlpine, Dube (b44) 1989; 65 Watanabe, Bansal, Hutter (b52) 2023 Lopes, Cruz, Viegas (b33) 2002; 17 Hastie (10.1016/j.acags.2025.100266_b26) 2009 Davies (10.1016/j.acags.2025.100266_b14) 2016; e2649 Tyukavina (10.1016/j.acags.2025.100266_b51) 2022; 3 Stocks (10.1016/j.acags.2025.100266_b44) 1989; 65 Oliveira (10.1016/j.acags.2025.100266_b38) 2021; 9 Tharwat (10.1016/j.acags.2025.100266_b48) 2021; 17 Taylor (10.1016/j.acags.2025.100266_b47) 2013; 28 Sullivan (10.1016/j.acags.2025.100266_b45) 2019 Conover (10.1016/j.acags.2025.100266_b11) 1979 Finney (10.1016/j.acags.2025.100266_b19) 2009; 55 California Air Resources Board (10.1016/j.acags.2025.100266_b9) 2024 Breiman (10.1016/j.acags.2025.100266_b8) 2017 Bhatt (10.1016/j.acags.2025.100266_b6) 2024; 35 Shrestha (10.1016/j.acags.2025.100266_b43) 2006; 18 Akiba (10.1016/j.acags.2025.100266_b2) 2019 Naderpour (10.1016/j.acags.2025.100266_b37) 2021; 13 Sarkar (10.1016/j.acags.2025.100266_b41) 2024; 81 Khalil Alsmadi (10.1016/j.acags.2025.100266_b30) 2009 Martínez (10.1016/j.acags.2025.100266_b35) 2009; 90 Shabbar (10.1016/j.acags.2025.100266_b42) 2004; 17 Cortez (10.1016/j.acags.2025.100266_b12) 2007 Anon (10.1016/j.acags.2025.100266_b3) 1993 Fan (10.1016/j.acags.2025.100266_b17) 2019; 225 Ke (10.1016/j.acags.2025.100266_b29) 2017; 30 The European Space Agency (10.1016/j.acags.2025.100266_b49) 2021 Mell (10.1016/j.acags.2025.100266_b36) 2007; 16 Badhan (10.1016/j.acags.2025.100266_b4) 2024; 16 Tien Bui (10.1016/j.acags.2025.100266_b50) 2016; 13 Farhad Mortezapour (10.1016/j.acags.2025.100266_b18) 2024; 6 Bergstra (10.1016/j.acags.2025.100266_b5) 2013 Jaafari (10.1016/j.acags.2025.100266_b28) 2019 Goodchild (10.1016/j.acags.2025.100266_b23) 1991; 15 Pedregosa (10.1016/j.acags.2025.100266_b39) 2011; 12 Friedman (10.1016/j.acags.2025.100266_b21) 1937; 32 Liang (10.1016/j.acags.2025.100266_b32) 2019; 7 Hearst (10.1016/j.acags.2025.100266_b27) 1998; 13 Freund (10.1016/j.acags.2025.100266_b20) 1997; 55 Abid (10.1016/j.acags.2025.100266_b1) 2020 Zaidi (10.1016/j.acags.2025.100266_b53) 2023; 9 Hansen (10.1016/j.acags.2025.100266_b24) 2010; 48 de Bem (10.1016/j.acags.2025.100266_b15) 2018; 28 Breiman (10.1016/j.acags.2025.100266_b7) 2001; 45 Dai (10.1016/j.acags.2025.100266_b13) 2013; 3 Suthaharan (10.1016/j.acags.2025.100266_b46) 2015; no. 36 Hantson (10.1016/j.acags.2025.100266_b25) 2016; 13 Gibson (10.1016/j.acags.2025.100266_b22) 2020; 240 Kondylatos (10.1016/j.acags.2025.100266_b31) 2022; 49 Lundberg (10.1016/j.acags.2025.100266_b34) 2017 Watanabe (10.1016/j.acags.2025.100266_b52) 2023 Raghunath (10.1016/j.acags.2025.100266_b40) 2022; 21 Lopes (10.1016/j.acags.2025.100266_b33) 2002; 17 Dessler (10.1016/j.acags.2025.100266_b16) 2008; 35 Chen (10.1016/j.acags.2025.100266_b10) 2016 |
| References_xml | – volume: 28 start-page: 586 year: 2013 end-page: 615 ident: b47 article-title: Wildfire prediction to inform fire management: Statistical science challenges publication-title: Statist. Sci. – volume: 17 start-page: 168 year: 2021 end-page: 192 ident: b48 article-title: Classification assessment methods publication-title: Appl. Comput. Inform. – volume: 32 start-page: 675 year: 1937 end-page: 701 ident: b21 article-title: The use of ranks to avoid the assumption of normality implicit in the analysis of variance publication-title: J. Amer. Statist. Assoc. – volume: 9 year: 2021 ident: b38 article-title: Evaluation procedures for forecasting with spatiotemporal data publication-title: Mathematics – volume: 55 start-page: 119 year: 1997 end-page: 139 ident: b20 article-title: A decision-theoretic generalization of on-line learning and an application to boosting publication-title: J. Comput. System Sci. – volume: 15 start-page: 194 year: 1991 end-page: 200 ident: b23 article-title: Geographic information systems publication-title: Prog. Hum. Geogr. – volume: 12 start-page: 2825 year: 2011 end-page: 2830 ident: b39 article-title: Scikit-learn: Machine learning in Python publication-title: J. Mach. Learn. Res. – year: 1979 ident: b11 article-title: Multiple-comparisons procedures. Informal report – start-page: 607 year: 2019 end-page: 619 ident: b28 article-title: 28 - factors influencing regional-scale wildfire probability in Iran: An application of random forest and support vector machine publication-title: Spatial Modeling in GIS and R for Earth and Environmental Sciences – volume: 18 start-page: 1678 year: 2006 end-page: 1710 ident: b43 article-title: Experiments with AdaBoost.RT, an improved boosting scheme for regression publication-title: Neural Comput. – volume: 3 year: 2022 ident: b51 article-title: Global trends of forest loss due to fire from 2001 to 2019 publication-title: Front. Remote. Sens. – volume: 28 start-page: 35 year: 2018 end-page: 45 ident: b15 article-title: Predicting wildfire vulnerability using logistic regression and artificial neural networks: a case study in Brazil publication-title: Int. J. Wildland Fire – start-page: 48 year: 1993 ident: b3 article-title: Fire Weather Index System Tables for New Zealand – volume: 6 start-page: 301 year: 2024 end-page: 360 ident: b18 article-title: A comprehensive overview and comparative analysis on deep learning models publication-title: J. Artif. Intell. – start-page: 785 year: 2016 end-page: –794 ident: b10 article-title: XGBoost: A scalable tree boosting system publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – start-page: 2623 year: 2019 end-page: 2631 ident: b2 article-title: Optuna: A next-generation hyperparameter optimization framework publication-title: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining – volume: 13 year: 2021 ident: b37 article-title: Forest fire risk prediction: A spatial deep neural network-based framework publication-title: Remote. Sens. – volume: e2649 year: 2016 ident: b14 article-title: Regional variation in fire weather controls the reported occurrence of Scottish wildfires publication-title: Peer J – start-page: 4389 year: 2023 end-page: 4396 ident: b52 article-title: PED-ANOVA: Efficiently quantifying hyperparameter importance in arbitrary subspaces publication-title: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence – start-page: 363 year: 2020 end-page: 370 ident: b1 article-title: Predicting forest fire in Algeria using data mining techniques: Case study of the decision tree algorithm publication-title: Advanced Intelligent Systems for Sustainable Development (AI2SD’2019) Volume 4-Advanced Intelligent Systems for Applied Computing Sciences – volume: 9 year: 2023 ident: b53 article-title: Predicting wildfires in Algerian forests using machine learning models publication-title: Heliyon – volume: 35 year: 2008 ident: b16 article-title: Water-vapor climate feedback inferred from climate fluctuations, 2003–2008 publication-title: Geophys. Res. Lett. – volume: 16 start-page: 1 year: 2007 end-page: 22 ident: b36 article-title: A physics based approach to modeling grassland fires publication-title: Int. J. Wildland Fire – year: 2009 ident: b26 publication-title: The Elements of Statistical Learning Data Mining, Inference, and Prediction – volume: 81 year: 2024 ident: b41 article-title: Ensembling machine learning models to identify forest fire-susceptible zones in Northeast India publication-title: Ecol. Inform. – volume: 7 start-page: 176746 year: 2019 end-page: 176755 ident: b32 article-title: A neural network model for wildfire scale prediction using meteorological factors publication-title: IEEE Access – volume: 65 start-page: 258 year: 1989 end-page: 265 ident: b44 article-title: The Canadian forest fire danger rating system: An overview publication-title: For. Chron. – start-page: 4768 year: 2017 end-page: 4777 ident: b34 article-title: A unified approach to interpreting model predictions publication-title: Proceedings of the 31st International Conference on Neural Information Processing Systems – volume: 48 year: 2010 ident: b24 article-title: Global surface temperature change publication-title: Rev. Geophys. – volume: 17 start-page: 2866 year: 2004 end-page: 2880 ident: b42 article-title: Summer drought patterns in Canada and the relationship to global sea surface temperatures publication-title: J. Clim. – volume: 16 year: 2024 ident: b4 article-title: Deep learning approach to improve spatial resolution of GOES-17 wildfire boundaries using VIIRS satellite data publication-title: Remote. Sens. – volume: 13 start-page: 361 year: 2016 end-page: 378 ident: b50 article-title: Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree publication-title: Landslides – volume: 55 start-page: 249 year: 2009 end-page: 255 ident: b19 article-title: Modeling containment of large wildfires using generalized linear mixed-model analysis publication-title: For. Sci. – volume: 17 start-page: 269 year: 2002 end-page: 285 ident: b33 article-title: - an integrated software system for the numerical simulation of fire spread on complex topography publication-title: Environ. Model. Softw. – volume: 30 start-page: 3146 year: 2017 end-page: 3154 ident: b29 article-title: LightGBM: A highly efficient gradient boosting decision tree publication-title: Adv. Neural Inf. Process. Syst. – volume: 21 start-page: 1295 year: 2022 end-page: 1322 ident: b40 article-title: XGBoost regression classifier (XRC) model for cyber attack detection and classification using inception V4 publication-title: J. Web Eng. – volume: no. 36 year: 2015 ident: b46 publication-title: Machine Learning Models and Algorithms for Big Data Classification: Thinking with Examples for Effective Learning – year: 2024 ident: b9 – volume: 225 year: 2019 ident: b17 article-title: Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data publication-title: Agricult. Water. Manag. – volume: 3 start-page: 52 year: 2013 end-page: 58 ident: b13 article-title: Increasing drought under global warming in observations and models publication-title: Nat. Clim. Chang. – start-page: 1 year: 2019 end-page: 8 ident: b45 article-title: Physical modelling of wildland fires publication-title: Encyclopedia of Wildfires and Wildland-Urban Interface (WUI) Fires – volume: 35 start-page: 67 year: 2024 ident: b6 article-title: An enhanced method for predicting and analysing forest fires using an attention-based CNN model publication-title: J. For. Res. – year: 2017 ident: b8 article-title: Classification and Regression Trees – year: 2007 ident: b12 article-title: A data mining approach to predict forest fires using meteorological data – volume: 45 start-page: 5 year: 2001 end-page: 32 ident: b7 article-title: Random forests publication-title: Mach. Learn. – volume: 13 start-page: 18 year: 1998 end-page: 28 ident: b27 article-title: Support vector machines publication-title: IEEE Intell. Syst. Appl. – start-page: I year: 2013 end-page: 115–I–123 ident: b5 article-title: Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures publication-title: Proceedings of the 30th International Conference on International Conference on Machine Learning - Volume 28 – volume: 49 year: 2022 ident: b31 article-title: Wildfire danger prediction and understanding with deep learning publication-title: Geophys. Res. Lett. – start-page: 296 year: 2009 end-page: 299 ident: b30 article-title: Performance comparison of multi-layer perceptron (back propagation, delta rule and perceptron) algorithms in neural networks publication-title: 2009 IEEE International Advance Computing Conference – year: 2021 ident: b49 article-title: New long-term dataset to analyse global fire trends – volume: 90 start-page: 1241 year: 2009 end-page: 1252 ident: b35 article-title: Human-caused wildfire risk rating for prevention planning in Spain publication-title: J. Environ. Manag. – volume: 240 year: 2020 ident: b22 article-title: A remote sensing approach to mapping fire severity in south-eastern Australia using sentinel 2 and random forest publication-title: Remote Sens. Environ. – volume: 13 start-page: 3359 year: 2016 end-page: 3375 ident: b25 article-title: The status and challenge of global fire modelling publication-title: Biogeosciences – start-page: 607 year: 2019 ident: 10.1016/j.acags.2025.100266_b28 article-title: 28 - factors influencing regional-scale wildfire probability in Iran: An application of random forest and support vector machine – start-page: 785 year: 2016 ident: 10.1016/j.acags.2025.100266_b10 article-title: XGBoost: A scalable tree boosting system – volume: 17 start-page: 2866 issue: 14 year: 2004 ident: 10.1016/j.acags.2025.100266_b42 article-title: Summer drought patterns in Canada and the relationship to global sea surface temperatures publication-title: J. Clim. doi: 10.1175/1520-0442(2004)017<2866:SDPICA>2.0.CO;2 – volume: 28 start-page: 586 issue: 4 year: 2013 ident: 10.1016/j.acags.2025.100266_b47 article-title: Wildfire prediction to inform fire management: Statistical science challenges publication-title: Statist. Sci. doi: 10.1214/13-STS451 – volume: 7 start-page: 176746 year: 2019 ident: 10.1016/j.acags.2025.100266_b32 article-title: A neural network model for wildfire scale prediction using meteorological factors publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2957837 – volume: 81 year: 2024 ident: 10.1016/j.acags.2025.100266_b41 article-title: Ensembling machine learning models to identify forest fire-susceptible zones in Northeast India publication-title: Ecol. Inform. doi: 10.1016/j.ecoinf.2024.102598 – year: 2024 ident: 10.1016/j.acags.2025.100266_b9 – start-page: 48 year: 1993 ident: 10.1016/j.acags.2025.100266_b3 – volume: 55 start-page: 119 issue: 1 year: 1997 ident: 10.1016/j.acags.2025.100266_b20 article-title: A decision-theoretic generalization of on-line learning and an application to boosting publication-title: J. Comput. System Sci. doi: 10.1006/jcss.1997.1504 – volume: 13 issue: 13 year: 2021 ident: 10.1016/j.acags.2025.100266_b37 article-title: Forest fire risk prediction: A spatial deep neural network-based framework publication-title: Remote. Sens. doi: 10.3390/rs13132513 – start-page: I year: 2013 ident: 10.1016/j.acags.2025.100266_b5 article-title: Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures – start-page: 4768 year: 2017 ident: 10.1016/j.acags.2025.100266_b34 article-title: A unified approach to interpreting model predictions – volume: 21 start-page: 1295 issue: 4 year: 2022 ident: 10.1016/j.acags.2025.100266_b40 article-title: XGBoost regression classifier (XRC) model for cyber attack detection and classification using inception V4 publication-title: J. Web Eng. – volume: 55 start-page: 249 issue: 3 year: 2009 ident: 10.1016/j.acags.2025.100266_b19 article-title: Modeling containment of large wildfires using generalized linear mixed-model analysis publication-title: For. Sci. – year: 2007 ident: 10.1016/j.acags.2025.100266_b12 – start-page: 2623 year: 2019 ident: 10.1016/j.acags.2025.100266_b2 article-title: Optuna: A next-generation hyperparameter optimization framework – volume: 35 start-page: 67 issue: 1 year: 2024 ident: 10.1016/j.acags.2025.100266_b6 article-title: An enhanced method for predicting and analysing forest fires using an attention-based CNN model publication-title: J. For. Res. doi: 10.1007/s11676-024-01717-7 – volume: 16 start-page: 1 issue: 1 year: 2007 ident: 10.1016/j.acags.2025.100266_b36 article-title: A physics based approach to modeling grassland fires publication-title: Int. J. Wildland Fire doi: 10.1071/WF06002 – volume: 30 start-page: 3146 year: 2017 ident: 10.1016/j.acags.2025.100266_b29 article-title: LightGBM: A highly efficient gradient boosting decision tree publication-title: Adv. Neural Inf. Process. Syst. – year: 2021 ident: 10.1016/j.acags.2025.100266_b49 – volume: 3 start-page: 52 issue: 1 year: 2013 ident: 10.1016/j.acags.2025.100266_b13 article-title: Increasing drought under global warming in observations and models publication-title: Nat. Clim. Chang. doi: 10.1038/nclimate1633 – volume: 13 start-page: 3359 issue: 11 year: 2016 ident: 10.1016/j.acags.2025.100266_b25 article-title: The status and challenge of global fire modelling publication-title: Biogeosciences doi: 10.5194/bg-13-3359-2016 – volume: 13 start-page: 18 issue: 4 year: 1998 ident: 10.1016/j.acags.2025.100266_b27 article-title: Support vector machines publication-title: IEEE Intell. Syst. Appl. doi: 10.1109/5254.708428 – volume: 48 issue: 4 year: 2010 ident: 10.1016/j.acags.2025.100266_b24 article-title: Global surface temperature change publication-title: Rev. Geophys. doi: 10.1029/2010RG000345 – start-page: 1 year: 2019 ident: 10.1016/j.acags.2025.100266_b45 article-title: Physical modelling of wildland fires – volume: 32 start-page: 675 issue: 200 year: 1937 ident: 10.1016/j.acags.2025.100266_b21 article-title: The use of ranks to avoid the assumption of normality implicit in the analysis of variance publication-title: J. Amer. Statist. Assoc. doi: 10.1080/01621459.1937.10503522 – volume: 17 start-page: 168 issue: 1 year: 2021 ident: 10.1016/j.acags.2025.100266_b48 article-title: Classification assessment methods publication-title: Appl. Comput. Inform. doi: 10.1016/j.aci.2018.08.003 – volume: 225 year: 2019 ident: 10.1016/j.acags.2025.100266_b17 article-title: Light Gradient Boosting Machine: An efficient soft computing model for estimating daily reference evapotranspiration with local and external meteorological data publication-title: Agricult. Water. Manag. doi: 10.1016/j.agwat.2019.105758 – volume: 28 start-page: 35 issue: 1 year: 2018 ident: 10.1016/j.acags.2025.100266_b15 article-title: Predicting wildfire vulnerability using logistic regression and artificial neural networks: a case study in Brazil publication-title: Int. J. Wildland Fire doi: 10.1071/WF18018 – volume: 12 start-page: 2825 year: 2011 ident: 10.1016/j.acags.2025.100266_b39 article-title: Scikit-learn: Machine learning in Python publication-title: J. Mach. Learn. Res. – volume: 13 start-page: 361 year: 2016 ident: 10.1016/j.acags.2025.100266_b50 article-title: Spatial prediction models for shallow landslide hazards: a comparative assessment of the efficacy of support vector machines, artificial neural networks, kernel logistic regression, and logistic model tree publication-title: Landslides doi: 10.1007/s10346-015-0557-6 – volume: 65 start-page: 258 issue: 4 year: 1989 ident: 10.1016/j.acags.2025.100266_b44 article-title: The Canadian forest fire danger rating system: An overview publication-title: For. Chron. doi: 10.5558/tfc65258-4 – volume: 45 start-page: 5 year: 2001 ident: 10.1016/j.acags.2025.100266_b7 article-title: Random forests publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – volume: 49 issue: 17 year: 2022 ident: 10.1016/j.acags.2025.100266_b31 article-title: Wildfire danger prediction and understanding with deep learning publication-title: Geophys. Res. Lett. doi: 10.1029/2022GL099368 – volume: 3 year: 2022 ident: 10.1016/j.acags.2025.100266_b51 article-title: Global trends of forest loss due to fire from 2001 to 2019 publication-title: Front. Remote. Sens. doi: 10.3389/frsen.2022.825190 – start-page: 296 year: 2009 ident: 10.1016/j.acags.2025.100266_b30 article-title: Performance comparison of multi-layer perceptron (back propagation, delta rule and perceptron) algorithms in neural networks – year: 2017 ident: 10.1016/j.acags.2025.100266_b8 – volume: 6 start-page: 301 issue: 1 year: 2024 ident: 10.1016/j.acags.2025.100266_b18 article-title: A comprehensive overview and comparative analysis on deep learning models publication-title: J. Artif. Intell. doi: 10.32604/jai.2024.054314 – year: 2009 ident: 10.1016/j.acags.2025.100266_b26 – volume: 17 start-page: 269 issue: 3 year: 2002 ident: 10.1016/j.acags.2025.100266_b33 article-title: FireStation - an integrated software system for the numerical simulation of fire spread on complex topography publication-title: Environ. Model. Softw. doi: 10.1016/S1364-8152(01)00072-X – volume: no. 36 year: 2015 ident: 10.1016/j.acags.2025.100266_b46 – volume: 16 issue: 4 year: 2024 ident: 10.1016/j.acags.2025.100266_b4 article-title: Deep learning approach to improve spatial resolution of GOES-17 wildfire boundaries using VIIRS satellite data publication-title: Remote. Sens. doi: 10.3390/rs16040715 – volume: 15 start-page: 194 issue: 2 year: 1991 ident: 10.1016/j.acags.2025.100266_b23 article-title: Geographic information systems publication-title: Prog. Hum. Geogr. doi: 10.1177/030913259101500205 – volume: 35 issue: 20 year: 2008 ident: 10.1016/j.acags.2025.100266_b16 article-title: Water-vapor climate feedback inferred from climate fluctuations, 2003–2008 publication-title: Geophys. Res. Lett. doi: 10.1029/2008GL035333 – start-page: 363 year: 2020 ident: 10.1016/j.acags.2025.100266_b1 article-title: Predicting forest fire in Algeria using data mining techniques: Case study of the decision tree algorithm – volume: 18 start-page: 1678 issue: 7 year: 2006 ident: 10.1016/j.acags.2025.100266_b43 article-title: Experiments with AdaBoost.RT, an improved boosting scheme for regression publication-title: Neural Comput. doi: 10.1162/neco.2006.18.7.1678 – volume: 9 issue: 7 year: 2023 ident: 10.1016/j.acags.2025.100266_b53 article-title: Predicting wildfires in Algerian forests using machine learning models publication-title: Heliyon doi: 10.1016/j.heliyon.2023.e18064 – volume: 90 start-page: 1241 issue: 2 year: 2009 ident: 10.1016/j.acags.2025.100266_b35 article-title: Human-caused wildfire risk rating for prevention planning in Spain publication-title: J. Environ. Manag. doi: 10.1016/j.jenvman.2008.07.005 – volume: e2649 issue: 4 year: 2016 ident: 10.1016/j.acags.2025.100266_b14 article-title: Regional variation in fire weather controls the reported occurrence of Scottish wildfires publication-title: Peer J – year: 1979 ident: 10.1016/j.acags.2025.100266_b11 – start-page: 4389 year: 2023 ident: 10.1016/j.acags.2025.100266_b52 article-title: PED-ANOVA: Efficiently quantifying hyperparameter importance in arbitrary subspaces – volume: 9 issue: 6 year: 2021 ident: 10.1016/j.acags.2025.100266_b38 article-title: Evaluation procedures for forecasting with spatiotemporal data publication-title: Mathematics doi: 10.3390/math9060691 – volume: 240 year: 2020 ident: 10.1016/j.acags.2025.100266_b22 article-title: A remote sensing approach to mapping fire severity in south-eastern Australia using sentinel 2 and random forest publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2020.111702 |
| SSID | ssj0002511571 |
| Score | 2.3090072 |
| Snippet | Climate change has caused increasingly frequent occurrences of forest fires around the world. Machine Learning (ML) and Artificial Intelligence models have... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Index Database Publisher |
| StartPage | 100266 |
| SubjectTerms | Explainable artificial intelligence Forest fires Hyper-parameter optimisation Machine learning SHAP values |
| Title | Recent advances in explainable Machine Learning models for wildfire prediction |
| URI | https://dx.doi.org/10.1016/j.acags.2025.100266 https://doaj.org/article/e3d8e842496f4a18be54302316e16c0e |
| Volume | 27 |
| WOSCitedRecordID | wos001546503100002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: Directory of Open Access Journals customDbUrl: eissn: 2590-1974 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511571 issn: 2590-1974 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2590-1974 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511571 issn: 2590-1974 databaseCode: M~E dateStart: 20190101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV09T8MwELUQAokF8SnKlzwwEhHHju2MgFoYaMUAUjfLju2qCIWqLQgWfjtnJ4FMsLBkiCI7ehf7vVPO7xA6S732RuYy0bmwwVSbJFIakRTcWpv5krg0HhS-E6ORHI-L-06rr1ATVtsD18BdOGqlkwyyBO6ZJtK4nIVGN4Q7wsvUhd0XVE8nmQp7cBDOuSCtzVAs6NKlngSD7iyPvqPRF_GHiqJjf4eROiwz2EKbjTzEl_VrbaMVV-2g9ZvYfvdjF41A5QFL4ObP_QJPK-zeZ8_NESg8jKWRDjeuqRMcG90sMChTDKLYetjg8Gwefs6EgOyhx0H_4fo2aToiJCXlfJkQWH2FLoQ3sGxS7QtmM-q4CaZ3xFsnveU69xJyHC-o55SbAmhKMM1L5hyj-2i1eqncAcKaW6p1CWxNCROZ0cBmBfCZZJDipV700HkLjprVxheqrQh7UhFLFbBUNZY9dBUA_H40uFbHGxBL1cRS_RXLHuIt_KoRADWxw1DT32Y__I_Zj9BGGLIuIDtGq8v5qztBa-XbcrqYn8bvC67Dz_4XY2nT_Q |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Recent+advances+in+explainable+Machine+Learning+models+for+wildfire+prediction&rft.jtitle=Applied+computing+and+geosciences&rft.au=Abira+Sengupta&rft.au=Brendon+J.+Woodford&rft.date=2025-09-01&rft.pub=Elsevier&rft.eissn=2590-1974&rft.volume=27&rft.spage=100266&rft_id=info:doi/10.1016%2Fj.acags.2025.100266&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_e3d8e842496f4a18be54302316e16c0e |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2590-1974&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2590-1974&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2590-1974&client=summon |