Predicting burnt areas during the summer season in Portugal by combining wildfire susceptibility and spring meteorological conditions

Bergonse, Rafaello; Oliveira, Sandra; Gonçalves, Ana; Nunes, Sílvia A.; DaCamara, Carlos C.; Zêzere, José Luı́s

doi:10.1080/19475705.2021.1909664

Cited by 12 publications

(6 citation statements)

References 42 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Drought conditions, especially in Mediterranean countries, are a good example of the relationship between climate and fire [56][57][58], as the danger of fire rises with increasing droughts their duration and intensity [59]. The drought situation of the year 2017, in Portugal, helps to understand the events of the great wildfires that have occurred that year, bearing in mind, however, that the relationship between drought and wildfires is complex [60].…”

Section: Discussionmentioning

confidence: 99%

Multi-Indices Diagnosis of the Conditions That Have Led to the Two 2017 Major Wildfires in Portugal

Andrade¹,

Bugalho²

2022

Preprint

View full text Add to dashboard Cite

Forest fires though part of a natural forest renewal process, when frequent and assuming large-scale proportions have detrimental impacts on biodiversity, agroforestry systems, soil erosion, air and water quality, infrastructures, and economy. Portugal (PT) endures extreme forest fires, with a record of burned area in 2017. These extreme wildfire events (EWE) concentrated in few days but with high burned areas, are among other factors, linked to severe fire weather conditions. In this study a comparison between several fire danger indices is performed for a reference period 2001‒2021 and 2017 (May‒October) for the Fire Weather Index (FWI), Continuous Haines Index (CHI), Keetch-Byram drought index (KBDI), Burning Index (BI) and Fire Danger index (FDI). A daily analysis for the so-called Pedrogão Grande wildfire (June 17th) and the October major fires (October 15th) included the Spread Component (SP) and Ignition Component (IC). Results revealed high above average values for all indices for 2017 in comparison with 2001‒2021 particularly, for October. High statistically significant monthly correlations between FWI, FDI and BI were found, along with lower between FWI and CHI. These correlations are depicted in the spatial patterns between FWI and FDI for the two EWE. The spatial distribution of FDI, SC and IC had the best performance in capturing the locations of the occurrence of the two EWEs’. The outcomes allowed to conclude, that since fire danger depends on several factors a multi-index’s diagnosis is highly relevant, though calibration and scale adjustment are needed for PT. The implementation of a Multi-index’s Prediction System should be able to further enhance the ability of tracking and forecast unique EWE, since the shortcomings of some indices are compensated by the information retrieved by others as shown in this study. Overall, a new forecast system can help ensuring the development of appropriate spatial preparedness plans, proactive responses by the civil protection regarding firefighter’s management, suppression efforts to minimize the detrimental impacts of wildfires in Portugal.

show abstract

Section: Discussionmentioning

confidence: 99%

Multi-Indices Diagnosis of the Conditions That Have Led to the Two 2017 Major Wildfires in Portugal

Andrade¹,

Bugalho²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Wildfire data used in this study are BA polygons derived from satellite data provided for the period 2001-2019 by Portuguese national authorities (ICNF, 2020). This dataset was successfully used in many other studies, by a large number of authors for a wide variety of purposes (Bergonse et al, 2021;Tarín-Carrasco et al, 2021). Only wildfires with BA > 100 ha that occurred during the extended summer season, here defined between 15 May and 31 October, were considered in this study.…”

Section: Burnt Areamentioning

confidence: 99%

Drivers of extreme burnt area in Portugal: fire weather and vegetation

Calheiros

Benali

Pereira

et al. 2022

Nat. Hazards Earth Syst. Sci.

View full text Add to dashboard Cite

Abstract. Fire weather indices are used to assess the effect of weather on wildfire behaviour and to support fire management. Previous studies identified the high daily severity rating percentile (DSRp) as being strongly related to the total burnt area (BA) in Portugal, but it is still poorly understood how this knowledge can support fire management at a smaller spatial scale. The aims of this study were to (1) assess whether the 90th DSRp (DSR90p) threshold is adequate for estimating most of the BA in mainland Portugal; (2) analyse the spatial variability of the DSRp threshold that explains a large part of BA, at higher resolution; and, (3) analyse whether vegetation cover can justify the DSRp spatial variability. We used weather reanalysis data from ERA5-Land, wildfire and land use data from Portuguese land management departments for an extended summer period (15 May to 31 October) from 2001 to 2019. We computed and related DSRp to large wildfires (BA > 100 ha) and land use to clarify the effectiveness of the DSRp for estimating BA in Portugal and assess how vegetation influences it. Results revealed that the DSR90p is an adequate indicator of extreme fire weather days and BA in Portugal. In addition, the spatial pattern of the DSRp associated with most of the total BA shows variability at the municipality scale. Municipalities where large wildfires occur with more extreme weather conditions have most of the BAs in forests and are in coastal areas. By contrast, municipalities where large wildfires occur with less extreme weather conditions are predominantly covered by shrublands and are situated in eastern and inland regions. These findings are a novelty for fire science in Portugal and should be considered by fire managers and fire risk assessors.

show abstract

“…This technique is easy to implement and also facilitates interpretation of the results obtained and possible duplication of the methodology in other regions or countries. [16]. Trucchia and friends proposed a study which is RF based.…”

Section: Introductionmentioning

confidence: 99%

Comparison of the Machine Learning Methods to Predict Wildfire Areas

BAYAT

Yildiz

2022

Turkish Journal of Science and Technology

View full text Add to dashboard Cite

In the last decades, global warming has changed the temperature. It caused an increasing the wildfire in everywhere. Wildfires affect people's social lives, animal lives, and countries' economies. Therefore new prevention and control mechanisms are required for forest fires. Artificial intelligence and neural networks have been benefited from in the management of forest fires since the 1990s. Since that time, machine learning (ML) methods have been used in environmental science in various subjects. This study aims to present a performance comparison of ML algorithms applied in fire management. In this paper, different ML models were used to forecast fire size based on various characteristics such as temperature, wind, humidity and precipitation, using records of 512 wildfires that took place in a national park in Northern Portugal.

show abstract

Predicting burnt areas during the summer season in Portugal by combining wildfire susceptibility and spring meteorological conditions

Cited by 12 publications

References 42 publications

Multi-Indices Diagnosis of the Conditions That Have Led to the Two 2017 Major Wildfires in Portugal

Multi-Indices Diagnosis of the Conditions That Have Led to the Two 2017 Major Wildfires in Portugal

Drivers of extreme burnt area in Portugal: fire weather and vegetation

Comparison of the Machine Learning Methods to Predict Wildfire Areas

Contact Info

Product

Resources

About