MétaCan
Menu
Back to cohort

Wildfire Occurrence Prediction Using Time Series Classification: A Comparative Study

2021· article· en· W4206068237 on OpenAlexaffabout
Ryan Laube, Howard J. Hamilton

Bibliographic record

Venue2021 IEEE International Conference on Big Data (Big Data) · 2021
Typearticle
Languageen
FieldEnvironmental Science
TopicFire effects on ecosystems
Canadian institutionsUniversity of Regina
Fundersnot available
KeywordsComputer scienceArtificial intelligenceTraining (meteorology)Residual neural networkMachine learningTraining setMultivariate statisticsClass (philosophy)Hidden Markov modelTime seriesPattern recognition (psychology)Deep learningMeteorologyGeography

Abstract

fetched live from OpenAlex

We compare the effectiveness of four machine learning models at predicting wildfire occurrence from multivariate time series containing hourly weather data, vegetation data, and fire occurrence data. Strategies to improve performance on highly imbalanced datasets are investigated, including adapting KNN and HMM to consider cost effectiveness. Two different training regimes are compared: the imbalanced training regime varies the class imbalance in the training and testing datasets together, and the balanced training regime keeps the imbalance ratio 50:50 for every training dataset. FCN and ResNet outperform KNN and HMM across all class imbalances tested. We tested the methods on the SaskFire dataset, which is an extensive, new dataset describing wildfires in Saskatchewan, Canada. The two models that performed best on highly imbalanced datasets are FCN and ResNet trained with the imbalanced training regime. On our dataset with a non-fire to fire class imbalance of 99:1, FCN and ResNet have precisions of 0.190 and 0.250, respectively, and recalls of 0.800.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.013
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.024
Threshold uncertainty score0.048

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.013
Meta-epidemiology (narrow)0.0020.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0050.003
Science and technology studies0.0010.000
Scholarly communication0.0020.003
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.365
GPT teacher head0.366
Teacher spread0.002 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
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

Citations4
Published2021
Admission routes2
Has abstractyes

Explore more

Same venue2021 IEEE International Conference on Big Data (Big Data)Same topicFire effects on ecosystemsFrench-language works237,207