Data-driven chimney fire risk prediction using machine learning and point process tools

DOI10.1214/23-AOAS1752MaRDI QIDQ6138624zbMATH OpenOpenAlexFDO

Authors Changqing Lü, M. N. M. Van Lieshout, Maurits de Graaf, Paul Visscher

Publication date 16 January 2024

Published in The Annals of Applied Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2112.07257

zbMATH Keywords

variable importancepair correlation functionPoisson point process\(K\)-functionfire predictionlogistic regression estimationspatiotemporal point pattern

Mathematics Subject Classification ID

Applications of statistics (62Pxx)

Abstract: Chimney fires constitute one of the most commonly occurring fire types. Precise prediction and prompt prevention are crucial in reducing the harm they cause. In this paper, we develop a combined machine learning and statistical modeling process to predict chimney fires. Firstly, we use random forests and permutation importance techniques to identify the most informative explanatory variables. Secondly, we design a Poisson point process model and apply associated logistic regression estimation to estimate the parameters. Moreover, we validate the Poisson model assumption using second-order summary statistics and residuals. We implement the modeling process on data collected by the Twente Fire Brigade and obtain plausible predictions. Compared to similar studies, our approach has two advantages: i) with random forests, we can select explanatory variables non-parametrically considering variable dependence; ii) using logistic regression estimation, we can fit the statistical model efficiently by tuning it to focus on important regions and times of the fire data.

Cites work

• scientific article; zbMATH DE number 3746271 (Why is no real title available?)
• An Introduction to the Theory of Point Processes
• Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations (with discussion)
• Consistency and asymptotic normality of the maximum likelihood estimator in generalized linear models
• Convex and non-convex regularization methods for spatial point processes intensity estimation
• Enhancing the SPDE modeling of spatial point processes with INLA, applied to wildfires. Choosing the best mesh for each database
• Hierarchical modeling and analysis for spatial data
• Information criteria for inhomogeneous spatial point processes
• Logistic regression for spatial Gibbs point processes
• On the Second-Order and Orientation Analysis of Planar Stationary Point Processes
• Point process modeling of wildfire hazard in Los Angeles county, California
• Practical Maximum Pseudolikelihood for Spatial Point Patterns
• Quantification of annual wildfire risk; a spatio-temporal point process approach
• Quasi-Likelihood and Optimal Estimation, Correspondent Paper
• Random forests
• Residual Analysis for Spatial Point Processes (with Discussion)
• Spatiotemporal wildfire modeling through point processes with moderate and extreme marks
• Statistical Analysis of Financial Data in S-Plus
• Structured spatio-temporal shot-noise Cox point process models, with a view to modeling forest fires
• Survival ensembles
• Theory of Spatial Statistics
• Variable selection for inhomogeneous spatial point process models
• Variable selection for spatial Poisson point processes via a regularization method
• Who Invented the Delta Method?

This page was built for publication: Data-driven chimney fire risk prediction using machine learning and point process tools

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6138624)