MétaCan
Menu
Back to cohort
Record W7062254348

A Survey of Wildfire Spread Prediction and Risk Estimation Methodswith Machine Learning Techniques

2022· article· en· W7062254348 on OpenAlexaboutno aff

Bibliographic record

VenueScholarsArchive (Brigham Young University) · 2022
Typearticle
Languageen
FieldEngineering
TopicThermal Analysis in Power Transmission
Canadian institutionsnot available
Fundersnot available
KeywordsNatural disasterWork (physics)EstimationNatural (archaeology)Random forestNatural hazard
DOInot available

Abstract

fetched live from OpenAlex

Wildfires can be very dangerous and destructive. In 2021, states in the USA particularly affected by deadly and damaging wildfires include California, Oregon, Montana, Washington, and Arizona (statista.com, 2021). Worldwide, countries recently affected significantly by devastating wildfires include, but are not limited to, Algeria, Australia, Brazil, Canada, Greece, India, Spain, South Korea, and Turkey. Thus, two important research questions are “how to predict fire spread behaviours?” and “how to evaluate wildfire risks?”. To answer these questions, in this paper we conducted a survey of recent methods and approaches that are based on machine learning techniques. For the first research question, fire spread is an important element of fire behaviours. Based on our survey, fire spread models can be categorised into three groups: traditional physical models (based on physics), data-driven models (based on machine learning techniques), and hybrid models (that combine both physical models and machine learning techniques). Regarding the second research question, it is challenging to quantify fire risks, particularly the wildfire probability and the fire risk zone, because numerous factors are involved, including human factors and natural factors. In this paper, we surveyed existing wildfire research work that involved human and natural factors. Human factors, such as human presence and socioeconomic transformations, and natural factors, such as weather and geographic information, were usually selected and leveraged to predict wildfire probability. We surveyed related journal and conference articles published recently, organised them in two taxonomies (ontology trees) pertaining to each of the two research questions addressed, provided comprehensive discussions for both questions, and suggested several possible directions of future work. Among the most significant results obtained, we found out that (i) For the fire spread behaviour prediction problems, traditional physical models play an important role but can be improved with machine learning techniques. For example, machine learning techniques are commonly used to assist traditional physical modelling for more accurate results and less time consumptions; and (ii) For the risk estimation problems, machine learning is commonly and effectively used for modelling the connections between human and natural factors and wildfire burned areas as well as for quantifying fire risks.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.337
Threshold uncertainty score0.660

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.008
GPT teacher head0.199
Teacher spread0.192 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueScholarsArchive (Brigham Young University)Same topicThermal Analysis in Power TransmissionFrench-language works237,207