Wildfire Risk Forecasting Using Weights of Evidence and Statistical Index Models

Salavati, Ghafar; Saniei, Ebrahim; Ghaderpour, Ebrahim; Hassan, Quazi K.

doi:10.3390/su14073881

Cited by 21 publications

(23 citation statements)

References 76 publications

(104 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The wildfire risk and forest fire spread are also influenced by several other factors, such as topography, changes in LULC, distance from the road, source of ignition and moisture content of the fuel [6][7][8][9][10][11][12][13]. Moreover, the fire spread along the direction of the slope, elevation and topographic characteristics of the surface area are also important.…”

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Analysis of Fire Foci and Environmental Degradation in the Biomes of Northeastern Brazil

et al. 2022

View full text Add to dashboard Cite

Forest fires destroy productive land throughout the world. In Brazil, mainly the Northeast of Brazil (NEB) is strongly affected by forest fires and bush fires. Similarly, there is no adequate study of long-term data from ground and satellite-based estimation of fire foci in NEB. The objectives of this study are: (i) to evaluate the spatiotemporal estimation of fires in NEB biomes via environmental satellites during the long term over 1998–2018, and (ii) to characterize the environmental degradation in the NEB biomes via orbital products during 1998–2018, obtained from the Burn Database (BDQueimadas) for 1794 municipalities. The spatiotemporal variation is estimated statistically (descriptive, exploratory and multivariate statistics) from the Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and Standardized Precipitation Index (SPI) through the Climate Hazards Group InfraRed Precipitation Station (CHIRPS). Moreover, we identify 10 homogeneous groups of fire foci (G1–G10) with a total variance of 76.5%. The G1 group is the most extended group, along with the G2 group, the exception being the G3 group. Similarly, the G4–G10 groups have a high percentage of hotspots, with more values in the municipality of Grajaú, which belongs to the agricultural consortium. The gradient of fire foci from the coast to the interior of the NEB is directly associated with land use/land cover (LULC) changes, where the sparse vegetation category and areas without vegetation are mainly involved. The Caatinga and Cerrado biomes lose vegetation, unlike the Amazon and Atlantic Forest biomes. The fires detected in the Cerrado and Atlantic Forest biomes are the result of agricultural consortia. Additionally, the two periods 2003–2006 and 2013–2018 show periods of severe and prolonged drought due to the action of El Niño.

show abstract

Section: Introductionmentioning

confidence: 99%

Spatiotemporal Analysis of Fire Foci and Environmental Degradation in the Biomes of Northeastern Brazil

et al. 2022

View full text Add to dashboard Cite

show abstract

“…domain expertise of the forest fire risk analysis as semantic rules; (3) we propose a rulebased reasoning method for obtaining the corresponding predicting data required by the machine learning-based forest fire prediction methods from KG according to the specific situations; (4) we show experiments for demonstrating the benefits of the proposed method in the aspects of multi-source heterogeneous spatio-temporal data fusion and machine learning-based forest fire predictions.…”

Section: Knowledge Graph-based Forest Fire Prediction System (Kgffp)mentioning

confidence: 99%

“…Commonly used approaches include fire indices and mechanism models for forest fire predictions that consider the closely related occurrence factors of forest fires. Salavatiet et al [3] conducted research in the city of Sanandaj, located in the west of Iran. In this study, fire risk potential is assessed using Weights of Evidence (WoE) and Statistical Index (SI) models.…”

Section: Introductionmentioning

confidence: 99%

Spatio-Temporal Knowledge Graph Based Forest Fire Prediction with Multi Source Heterogeneous Data

Yang

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Forest fires have frequently occurred and caused great harm to people’s lives. Many researchers use machine learning techniques to predict forest fires by considering spatio-temporal data features. However, it is difficult to efficiently obtain the features from large-scale, multi-source, heterogeneous data. There is a lack of a method that can effectively extract features required by machine learning-based forest fire predictions from multi-source spatio-temporal data. This paper proposes a forest fire prediction method that integrates spatio-temporal knowledge graphs and machine learning models. This method can fuse multi-source heterogeneous spatio-temporal forest fire data by constructing a forest fire semantic ontology and a knowledge graph-based spatio-temporal framework. This paper defines the domain expertise of forest fire analysis as the semantic rules of the knowledge graph. This paper proposes a rule-based reasoning method to obtain the corresponding data for the specific machine learning-based forest fire prediction methods, which are dedicated to tackling the problem with real-time prediction scenarios. This paper performs experiments regarding forest fire predictions based on real-world data in the experimental areas Xichang and Yanyuan in Sichuan province. The results show that the proposed method is beneficial for the fusion of multi-source spatio-temporal data and highly improves the prediction performance in real forest fire prediction scenarios.

show abstract

“…Depending on the practices employed and the nature of the fire, the behavior and environmental impact of this burning can vary considerably. In addition to climate factors, topographic variables, such as altitude, slope, and aspect, can also affect the behavior and speed of forest fires' spread [7].…”

Section: Introductionmentioning

confidence: 99%

Spatial Analysis of the Occurrence and Spread of Wildfires in Southwest Madagascar

Champin

Taïbi

Ballouche

2022

Fire

View full text Add to dashboard Cite

The island of Madagascar, located in the southern hemisphere between the equator and the Tropic of Capricorn in the Indian Ocean, 450 km from the African continent, is particularly affected by wildfires. The vegetation of the phytogeographic Western Domain of the island consists largely of savannas, wooded grassland, and secondary grassland, maintained by the repeated action of fire operating each year on a seasonal cycle. Rural populations employ fire to manage land use. Depending on the burning practice and the environment in which the fires happen, the impacts vary. This paper supplement the studies that have so far located and quantified wildfires by taking into account their different behaviors, particularly their spread. We analyzed the modalities of the relationship between the two fire products, active fire and burned area, derived from Moderate Resolution Imaging Spectroradiometer (MODIS) data to establish a typology based on fire spread patterns. We identified three general patterns of fire behaviors, as well as their locations in the studied area. Spatial analysis of this patterns enabled us to understand spatial logics better. Type 1 fires are the least frequently observed and have many active fires, but little or no burned area. Type 2 fires are the most common and have areas that burn like a mosaic. Type 3 fires are observed slightly less frequently than the previous type and have few active fires and large burned areas. An inter-annual analysis reveals the spatial stability or variability of these fire types.

show abstract

Wildfire Risk Forecasting Using Weights of Evidence and Statistical Index Models

Cited by 21 publications

References 76 publications

Spatiotemporal Analysis of Fire Foci and Environmental Degradation in the Biomes of Northeastern Brazil

Spatiotemporal Analysis of Fire Foci and Environmental Degradation in the Biomes of Northeastern Brazil

Spatio-Temporal Knowledge Graph Based Forest Fire Prediction with Multi Source Heterogeneous Data

Spatial Analysis of the Occurrence and Spread of Wildfires in Southwest Madagascar

Contact Info

Product

Resources

About