Some Challenges for Forest Fire Risk Predictions in the 21st Century

Dios, Víctor Resco de; Nolan, Rachael H.

doi:10.3390/f12040469

Cited by 17 publications

(10 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on relevant temporal-spatial information, some scholars further assess the risk of forest fires [44][45][46][47] and predict the incidence and occurrence of forest fires [48][49][50][51]. Currently, information diffusion theory and geographical information systems are commonly adopted for forest fire risk estimation, which is restricted to historical numbers or probabilities of discovered ignitions in the specific research area [20,45,46,52].…”

Section: Literature Reviewmentioning

confidence: 99%

RETRACTED: The Temporal-Spatial Distribution and Information-Diffusion-Based Risk Assessment of Forest Fires in China

2021

Sustainability

View full text Add to dashboard Cite

As forest fires are becoming a recurrent and severe issue in China, their temporal-spatial information and risk assessment are crucial for forest fire prevention and reduction. Based on provincial-level forest fire data during 1998–2017, this study adopts principal component analysis, clustering analysis, and the information diffusion theory to estimate the temporal-spatial distribution and risk of forest fires in China. Viewed from temporality, China’s forest fires reveal a trend of increasing first and then decreasing. Viewed from spatiality, provinces characterized by high population density and high coverage density are seriously affected, while eastern coastal provinces with strong fire management capabilities or western provinces with a low forest coverage rate are slightly affected. Through the principal component analysis, Hunan (1.33), Guizhou (0.74), Guangxi (0.51), Heilongjiang (0.48), and Zhejiang (0.46) are found to rank in the top five for the severity of forest fires. Further, Hunan (1089), Guizhou (659), and Guanxi (416) are the top three in the expected number of general forest fires, Fujian (4.70), Inner Mongolia (4.60), and Heilongjiang (3.73) are the top three in the expected number of large forest fires, and Heilongjiang (59,290), Inner Mongolia (20,665), and Hunan (5816) are the top three in the expected area of the burnt forest.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

RETRACTED: The Temporal-Spatial Distribution and Information-Diffusion-Based Risk Assessment of Forest Fires in China

2021

Sustainability

View full text Add to dashboard Cite

show abstract

“…Limitations of wildfires prediction methods : We give here, some of the challenges or limitations of forest fire predictors, encountered in the literature [ 5 , 6 ]. Data availability and quality: Forest fire prediction requires a large amount of data from various sources such as weather, vegetation, topography, human activities, etc.…”

Section: Introductionmentioning

confidence: 99%

Predicting wildfires in Algerian forests using machine learning models

Zaïdi

2023

Heliyon

View full text Add to dashboard Cite

“…These studies are capable to perform good results and obtaining high accuracy for predicting forest fires [15][16][17][18][19]. However, some challenges and limitations are encountered by many studies including [20]:…”

Section: Introductionmentioning

confidence: 99%

Machine Learning for Forest Fire Prediction: A Case Study in North Algeria

Ghibeche,

Sellam,

Nouri

et al. 2024

ISI

View full text Add to dashboard Cite

Wildland fires are the most common peril for forests due to climate change. Furthermore, it is an uncontrollable disaster and poses a great deal of threat to human health and ecosystems. In Algeria, almost 40,000 hectares are burned each year, approximately 1% of all existing woodlands of the country. In this work, the forest fire event prediction is highlighted using machine learning. The study utilized data sets from several sources, including fire data obtained from the fire information system for resource management by NASA (FIRMS) and climate data accessed from the NASA energy project API, derived from the MODIS satellite (NASA forecasting of energy resources around the world). Fire data from NASA provides real-time information, spanning from 2000 to 2020. The methodology process of creating the prediction system involved collecting the data, preprocessing the data, finding the best models, training and testing the models, and evaluating them for validation. The machine learning model was trained and validated using 70% and 30% of the set features with a performance accuracy of up to 86%. Upon completion, we deployed our selected machine learning model to create a Web platform enables different end users to check possible future forest fires by select a geographical area on a world map. The objective of our machine learning model is to analyze the weather data of the selecting area on the map in real time and predict whether a fire will occur or not. This prediction system will enhance early detection, allowing prompt response measures to be implemented, reducing the risk of uncontrolled wildfires and safeguarding ecosystems and communities.

show abstract

Some Challenges for Forest Fire Risk Predictions in the 21st Century

Abstract: Global wildfire activity has experienced a dramatic surge since 2017 [...]

Cited by 17 publications

References 44 publications

RETRACTED: The Temporal-Spatial Distribution and Information-Diffusion-Based Risk Assessment of Forest Fires in China

RETRACTED: The Temporal-Spatial Distribution and Information-Diffusion-Based Risk Assessment of Forest Fires in China

Predicting wildfires in Algerian forests using machine learning models

Machine Learning for Forest Fire Prediction: A Case Study in North Algeria

Contact Info

Product

Resources

About