Computation of a Dynamic Forest Fire Risk Index by the Use of a Long-Term NOAA-AVHRR NDVI Data Set

2003 ◽  
pp. 65-70
Author(s):  
L. Bottai ◽  
R. Costantini ◽  
G. Zipoli ◽  
F. Maselli ◽  
S. Romanelli
Keyword(s):  
Forest Fire ◽  
Risk Index ◽  
Fire Risk ◽  
Data Set ◽  
Noaa Avhrr ◽  
Forest Fire Risk ◽  
Fire Risk Index

scholarly journals Developing a New Hourly Forest Fire Risk Index Based on Catboost in South Korea

2020 ◽  
Vol 10 (22) ◽  
pp. 8213
Author(s):  
Yoojin Kang ◽  
Eunna Jang ◽  
Jungho Im ◽  
Chungeun Kwon ◽  
Sungyong Kim
Keyword(s):  
South Korea ◽  
Forest Fire ◽  
Forest Fires ◽  
Risk Index ◽  
Fire Risk ◽  
Ensemble Model ◽  
Weather Factors ◽  
Meteorological Model ◽  
Forest Fire Risk ◽  
Fire Risk Index

Forest fires can cause enormous damage, such as deforestation and environmental pollution, even with a single occurrence. It takes a lot of effort and long time to restore areas damaged by wildfires. Therefore, it is crucial to know the forest fire risk of a region to appropriately prepare and respond to such disastrous events. The purpose of this study is to develop an hourly forest fire risk index (HFRI) with 1 km spatial resolution using accessibility, fuel, time, and weather factors based on Catboost machine learning over South Korea. HFRI was calculated through an ensemble model that combined an integrated model using all factors and a meteorological model using weather factors only. To confirm the generalized performance of the proposed model, all forest fires that occurred from 2014 to 2019 were validated using the receiver operating characteristic (ROC) curves and the area under the ROC curve (AUC) values through one-year-out cross-validation. The AUC value of HFRI ensemble model was 0.8434, higher than the meteorological model. HFRI was compared with the modified version of Fine Fuel Moisture Code (FFMC) used in the Canadian Forest Fire Danger Rating Systems and Daily Weather Index (DWI), South Korea’s current forest fire risk index. When compared to DWI and the revised FFMC, HFRI enabled a more spatially detailed and seasonally stable forest fire risk simulation. In addition, the feature contribution to the forest fire risk prediction was analyzed through the Shapley Additive exPlanations (SHAP) value of Catboost. The contributing variables were in the order of relative humidity, elevation, road density, and population density. It was confirmed that the accessibility factors played very important roles in forest fire risk modeling where most forest fires were caused by anthropogenic factors. The interaction between the variables was also examined.

scholarly journals Mapping the Forest Fire Risk Zones Using Artificial Intelligence with Risk Factors Data

2022 ◽  
Author(s):  
Volkan Sevinc
Keyword(s):  
Artificial Intelligence ◽  
High Risk ◽  
Forest Fire ◽  
Forest Fires ◽  
Fire Risk ◽  
Geographical Information ◽  
Data Set ◽  
Risk Zone ◽  
Risk Zones ◽  
Forest Fire Risk

Abstract Geographical information system data has been used in forest fire risk zone mapping studies commonly. However, forest fires are caused by many factors, which cannot be explained only by geographical and meteorological reasons. Human-induced factors also play an important role in occurrence of forest fires and these factors depend on various social and economic conditions. This article aims to prepare a fire risk zone map by using a data set consisting of nine human-induced factors, three natural factors, and a temperature factor causing forest fires. Moreover, an artificial intelligence method, k-means, clustering algorithm was employed in preparation of the fire risk zone map. Turkey was selected as the study area as there are social and economic varieties among its zones. Therefore, the forestry zones in Turkey were separated into three groups as low, moderate, and high-risk categories and a map was provided for these risk zones. The map reveals that the forestry zones on the west coast of Turkey are under high risk of forest fire while the moderate risk zones mostly exist in the southeastern zones. The zones located in the interior parts, in the east, and on the north coast of Turkey have comparatively lower forest fire risks.

An evaluation of the utility of NOAA AVHRR images for monitoring forest fire risk in Spain

1991 ◽  
Vol 12 (9) ◽  
pp. 1841-1851 ◽  
Author(s):  
S. LÓPEZ ◽  
F. GONZÁ;LEZ ◽  
R. LLOP ◽  
J. M. CUEVAS
Keyword(s):  
Forest Fire ◽  
Fire Risk ◽  
Noaa Avhrr ◽  
Forest Fire Risk

Analysis of NOAA‐AVHRR NDVI inter‐annual variability for forest fire risk estimation

2006 ◽  
Vol 27 (8) ◽  
pp. 1725-1732 ◽  
Author(s):  
A. Gabban ◽  
J. San‐Miguel‐Ayanz ◽  
P. Barbosa ◽  
G. Libertà
Keyword(s):  
Forest Fire ◽  
Risk Estimation ◽  
Fire Risk ◽  
Annual Variability ◽  
Noaa Avhrr ◽  
Forest Fire Risk

Climate services for forest fire risk management

2020 ◽  
Author(s):  
Céline Deandreis ◽  
Gwendoline Lacressonière ◽  
Marc Chiapero ◽  
Miguel Mendes ◽  
Humberto Diaz Fidalgo ◽  
...  
Keyword(s):  
Forest Fire ◽  
Fire Risk ◽  
Propagation Model ◽  
Economic Losses ◽  
Main Role ◽  
Climate Services ◽  
Fire Weather Index ◽  
Probable Maximum Loss ◽  
Forest Fire Risk

<p>The weather and its climatic evolution play the main role in generating hazard profiles of forest fires. The increased in magnitude and damage of last forest fire seasons has caused a larger concern of the insurance sector for this peril. Due to the lack of knowledge of this risk, there is a widespread low level of insurance coverage of forest fire risk. A first step forward is clearly needed to (1) propose simplified approaches showing how the risk links with its main weather drivers, and (2) re-incentivize the use of insurance by forest managers.</p><p>To answer this objective, ARIA Technologies and its partners have developed a geospatial web-based decision tool to support both forest owners and forest insurance actors in managing the vulnerability of their asset/portfolios to fire risk. RiskFP includes:</p><ul><li>A “realistic disaster scenarios generator module” that allows the generation of hundreds of scenarios of extreme wildfires to complete information from historical fires databases. This information can be used in damage and loss modelling to improve the estimation of the probable maximum loss (PML). In addition, the risk FP “impact module” provides to the users information on the different potential impact like the amount of biomass burnt or the economic losses.</li> <li>A precise mapping of the local forest fire risk through the graphical representation of an index including five risk levels (from low to extreme) that provides an overview of the most critical locations regarding the potential behavior of the fire in case of an hypothetical ignition.</li> <li>A forecasting/projection module to inform the users on the frequency of the severe-extreme days in the mid- and long-term horizons. It can be used by the forestry sector to better anticipate and prepare the next fire season and as a planning tool for long-term operation/investment.</li> </ul><p>At the heart of the platform lies the concept of critical landscape weather patterns (CLP), an empirical fire weather index that identifies severe-extreme weather days derived from hourly records of a representative weather station (Gellie, 2019). It could be computed from past records, seasonal forecast or climate projection allowing to provide fire risk assessment for these different time scales. The CLP module is coupled with a propagation model, the Wildfire Analyst® forest fire simulator at the resolution of about 40m, that is used to estimate the progression and behavior of the fire in space and time. It is based on the standardized and validated semi-empirical Rothermel propagation model (1972).</p><p><strong>Acknowledgements:</strong></p><p>We acknowledge the European Commission for sponsoring this work in the framework of the H2020-insurance project (Grant Agreement number 730381).</p>

A forest fire risk assessment using NOAA AVHRR images in the Valencia area, eastern Spain

1997 ◽  
Vol 18 (10) ◽  
pp. 2201-2207 ◽  
Author(s):  
F. Gonzalez-Alonso ◽  
J. M. Cuevas ◽  
J. L. Casanova ◽  
A. Calle ◽  
P. Illera
Keyword(s):  
Risk Assessment ◽  
Forest Fire ◽  
Fire Risk ◽  
Noaa Avhrr ◽  
Fire Risk Assessment ◽  
Forest Fire Risk

A Satellite Index of Risk of Forest Fire Occurrence in Summer in the Mediterranean Area

1998 ◽  
Vol 8 (4) ◽  
pp. 173 ◽  
Author(s):  
V Prosper-Laget ◽  
A Douguedroit ◽  
JP Guinot
Keyword(s):  
Forest Fire ◽  
Vegetation Index ◽  
Fire Risk ◽  
Mediterranean Area ◽  
Soil Water Deficit ◽  
Fire Occurrence ◽  
Risk Class ◽  
Noaa Avhrr ◽  
Vegetation Stress ◽  
Forest Fire Risk

An index of forest fire risk has been determined by using the vegetation index NDVI and the surface temperature Ts, computed from NOAA-AVHRR over 21 Mediterranean French forests. Those 2 satellite parameters can be interpreted in terms of soil water deficit and vegetation stress in summer. An inverse linear correlation between their values for each forest pixel of 10 dates in 1990 was used to establish the index which has been divided into 5 equal classes. Those classes correspond with 5 risk classes of forest fire occurrence which were mapped for several forests. Periods and areas in the highest risk class correspond with those where the most important number of fires appeared in that year for the studied forests. A statistical model of the period of highest fire risk has also been constructed for each forest.

Sign in / Sign up

Export Citation Format

Share Document