Mesoscale spatiotemporal predictive models of daily human- and lightning-caused wildland fire occurrence in British Columbia

Nadeem, Khurram; Taylor, Stephen; Woolford, Douglas G.; Dean, C. B.

doi:10.1071/wf19058

Cited by 39 publications

(79 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictions of the number and location of fire starts in the upcoming day(s) are important for preparedness planning, that is, the acquisition of resources, including the relocation of mobile resources and readiness for expected fire activity. The origins of fire occurrence prediction (FOP) models go back almost 100 years (Nadeem et al 2020). FOP models typically use regression methods to relate the response variable (fire reports or hotspots) to weather, lightning, and other covariates for a geographic unit or as a spatial probability.…”

Section: Fire Occurrence Predictionmentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

Artiﬁcial intelligence has been applied in wildﬁre science and management since the 1990s, with early applications including neural networks and expert systems. Since then the ﬁeld has rapidly progressed congruently with the wide adoption of machine learning (ML) methods in the environmental sciences. Here, we present a scoping review of ML applications in wildﬁre science and management. Our overall objective is to improve awareness of ML methods among wildﬁre researchers and managers, as well as illustrate the diverse and challenging range of problems in wildﬁre science available to ML data scientists. To that end, we ﬁrst present an overview of popular ML approaches used in wildﬁre science to date, and then review the use of ML in wildﬁre science as broadly categorized into six problem domains, including: 1) fuels characterization, ﬁre detection, and mapping; 2) ﬁre weather and climate change; 3) ﬁre occurrence, susceptibility, and risk; 4) ﬁre behavior prediction; 5) ﬁre eﬀects; and 6) ﬁre management. Furthermore, we discuss the advantages and limitations of various ML approaches relating to data size, computational requirements, generalizability, and interpretability, as well as identify opportunities for future advances in the science and management of wildﬁres within a data science context. In total, we identfied 300 relevant publications up to the end of 2019, where the most frequently used ML methods across problem domains included random forests, MaxEnt, artiﬁcial neural networks, decision trees, support vector machines, and genetic algorithms. As such, there exists opportunities to apply more current ML methods — including deep learning and agent based learning — in the wildﬁre sciences, especially in instances involving very large multivariate datasets. We must recognize, however, that despite the ability of ML methods to learn on their own, expertise in wildﬁre science is necessary to ensure realistic modelling of ﬁre processes across multiple scales, while the complexity of some ML methods, such as deep learning, requires a dedicated and sophisticated knowledge of their application. Finally, we stress that the wildﬁre research and management communities play an active role in providing relevant, high quality, and freely available wildﬁre data for use by practitioners of ML methods.

show abstract

Section: Fire Occurrence Predictionmentioning

confidence: 99%

A review of machine learning applications in wildfire science and management

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Another metric that has also been used for FOP model evaluation (e.g. Vasconcelos et al 2001;Bar Massada et al 2013;Rodrigues and de la Riva 2014;Nadeem et al 2020) is area under the receiver operating characteristic curve (AUC-ROC) (Hanley and McNeil 1982). This is a threshold-independent metric that depends only on a model's ability to rank observations (i.e.…”

Section: A Reviewmentioning

confidence: 99%

“…A wellcalibrated FOP model produces predictions that represent the true probability of a fire occurrence. Sakr et al (2010Sakr et al ( , 2011 used customised metrics to assess the error in predicting the number of fires on a given day, whereas Nadeem et al (2020) used root-mean-squared error (RMSE) after aggregating the predictions either spatially or temporally.…”

Section: A Reviewmentioning

confidence: 99%

“…Vasconcelos et al 2001;Stojanova et al 2012;Bar Massada et al 2013;Rodrigues and de la Riva 2014). Vasconcelos et al (2001) also used a calibration plot to compare the observed probability of fire occurrence with their models' predictions, whereas Nadeem et al (2020) plotted observed and predicted counts.…”

Section: A Reviewmentioning

confidence: 99%

“…LASSO) logistic regression (e.g. Nadeem et al 2020), logistic generalised additive models (e.g. Brillinger et al 2003;Preisler et al 2004Preisler et al , 2011Vilar et al 2010;Woolford et al 2011Woolford et al , 2016Magnussen and Taylor 2012) and a variety of machine learning methods, including neural networks, support vector machines and random forests (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Guidelines for effective evaluation and comparison of wildland fire occurrence prediction models

Phelps

Woolford

2021

Int. J. Wildland Fire

Self Cite

View full text Add to dashboard Cite

Daily, fine-scale spatially explicit wildland fire occurrence prediction (FOP) models can inform fire management decisions. Many different data-driven modelling methods have been used for FOP. Several studies use multiple modelling methods to develop a set of candidate models for the same region, which are then compared against one another to choose a final model. We demonstrate that the methodologies often used for evaluating and comparing FOP models may lead to selecting a model that is ineffective for operational use. With an emphasis on spatially and temporally explicit FOP modelling for daily fire management operations, we outline and discuss several guidelines for evaluating and comparing data-driven FOP models, including choosing a testing dataset, choosing metrics for model evaluation, using temporal and spatial visualisations to assess model performance, recognising the variability in performance metrics, and collaborating with end users to ensure models meet their operational needs. A case study for human-caused FOP in a provincial fire control zone in the Lac La Biche region of Alberta, Canada, using data from 1996 to 2016 demonstrates the importance of following the suggested guidelines. Our findings indicate that many machine learning FOP models in the historical literature are not well suited for fire management operations.

show abstract

Canadian contributions to environmetrics

et al. 2022

Self Cite

View full text Add to dashboard Cite

This article focuses on the importance of collaboration in statistics by Canadian researchers and highlights the contributions that Canadian statisticians have made to many research areas in environmetrics. We provide a discussion about different vehicles that have been developed for collaboration by Canadians in the environmetrics context as well as specific scientific areas that are focused on environmetrics research in Canada including climate science, forestry, and fisheries, which are areas of importance for natural resources in Canada.Résumé: Cet article souligne l'ampleur de la collaboration entre les scientifiques canadiens dans le domaine de la statistique et présente un survol des travaux réalisés par des spécialistes du sujet sur un ensemble de thèmes liés aux sciences de l'environnement. Les auteurs relatent différents moyens par lesquels cette collaboration s'est incarnée et a permis aux Canadiennes et Canadiens de contribuer à l'environnemétrie et à divers domaines connexes, notamment les sciences du climat, la foresterie et les pêches, dont l'importance est capitale pour la gestion des ressources naturelles du pays.

show abstract

Mesoscale spatiotemporal predictive models of daily human- and lightning-caused wildland fire occurrence in British Columbia

Cited by 39 publications

References 45 publications

A review of machine learning applications in wildfire science and management

A review of machine learning applications in wildfire science and management

Guidelines for effective evaluation and comparison of wildland fire occurrence prediction models

Canadian contributions to environmetrics

Contact Info

Product

Resources

About