MétaCan
Menu
← Back to cohort

Разработка предложений по совершенствованию системы прогнозирования лесопожарных рисков на территории Красноярского края с использованием искусственных нейронных сетей

2025· article· ru· W7117486645 on OpenAlexaboutno aff
С.А. Жук, Д.Ю. Сидоренко, Д.В. Боровинский

Bibliographic record

VenueСибирский пожарно-спасательный вестник. · 2025
Typearticle
Languageru
FieldEnvironmental Science
TopicFire effects on ecosystems
Canadian institutionsnot available
Fundersnot available
KeywordsArtificial neural networkFeedforward neural networkScale (ratio)Feed forwardEstimationFire detection

Abstract

fetched live from OpenAlex

В статье рассматривается применение искусственных нейронных сетей (ИНС) для повышения точности прогнозирования лесопожарных рисков в Красноярском крае. В условиях увеличения частоты и масштабов лесных пожаров, обусловленных климатическими изменениями, традиционные методы прогнозирования демонстрируют ограниченную эффективность. Предложена многослойная нейронная сеть с архитектурой прямого распространения, обученная на данных за 2018–2023 годы, включающих метеорологические, лесопатологические и пространственно-временные параметры. Результаты исследования показали, что разработанная модель обеспечивает более высокую точность прогнозирования по сравнению с классическими методами (метод Нестерова, канадская система CFFDRS): снижение ошибки оценки площади возгораний в 1,8–2,3 раза и повышение точности предсказания сроков возникновения пожаров на 27–35%. Особое внимание уделено анализу влияния экстремальных погодных условий на динамику пожаров, что позволило выявить нелинейные взаимосвязи между факторами. Практическая значимость работы подтверждена апробацией модели на данных Сибирского федерального округа, где достигнуто сокращение времени реагирования на 30–40%. Перспективы дальнейших исследований включают интеграцию спутникового мониторинга, применение архитектур глубокого обучения (LSTM, GRU) и разработку геоинформационной системы поддержки принятия решений. The article explores the use of artificial neural networks (ANNs) to enhance the accuracy of forest fire risk forecasting in Krasnoyarsk Krai. Given the increasing frequency and scale of wildfires due to climate change, traditional prediction methods show limited effectiveness. A feedforward multilayer neural network was developed, trained on 2018–2023 data encompassing meteorological, forest pathology, and spatiotemporal parameters. The results demonstrate that the proposed model outperforms classical methods (Nesterov’s method, Canadian CFFDRS system), reducing fire area estimation errors by 1.8–2.3 times and improving fire occurrence timing prediction by 27–35%. Special emphasis is placed on analyzing the impact of extreme weather conditions on fire dynamics, revealing nonlinear relationships between factors. The practical relevance of the study is confirmed by testing the model on data from the Siberian Federal District, achieving a 30–40% reduction in response time. Future research directions include integrating satellite monitoring, applying deep learning architectures (LSTM, GRU), and developing a GIS-based decision support system.

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)0.004
metaresearch head score (Gemma)0.012
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: none
Teacher disagreement score0.052
Threshold uncertainty score0.173

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.012
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0030.003
Science and technology studies0.0040.005
Scholarly communication0.0160.009
Open science0.0020.004
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0520.020

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 head0.003
GPT teacher head0.211
Teacher spread0.208 · 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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueСибирский пожарно-спасательный вестник.→Same topicFire effects on ecosystems→French-language works237,207→