A novel urban vegetation mapping approach for fire risk assessment: A Mediterranean case study

Mahamed, Maria; Wittenberg, Lea; Kutiel, H.; Brook, Anna

doi:10.1007/s11252-023-01364-6

Cited by 3 publications

(1 citation statement)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite the existing research, there remains a gap in thoroughly assessing fire susceptibility using remote sensing data. Previous research has highlighted the application of artificial neural networks and mapping techniques for fire risk assessment and vegetation analysis [46][47][48]. This study addresses this gap by focusing on a specific region with limited datasets.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)

Kanwal,

Rafaqat,

Iqbal

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

As wildfires become increasingly perilous amidst Pakistan’s expanding population and evolving environmental conditions, their global significance necessitates urgent attention and concerted efforts toward proactive measures and international cooperation. This research strives to comprehensively enhance wildfire prediction and management by implementing various measures to contribute to proactive mitigation in Pakistan. Additionally, the objective of this research was to acquire an extensive understanding of the factors that influence fire patterns in the country. For this purpose, we looked at the spatiotemporal patterns and causes of wildfires between 2000 and 2023 using descriptive analysis. The data analysis included a discussion on density-based clustering as well as the distribution of the data across four seasons over a period of six years. Factors that could indicate the probability of a fire occurrence such as weather conditions, terrain characteristics, and fuel availability encompass details about the soil, economy, and vegetation. We used a convolutional neural network (CNN) to extract features, and different machine learning (ML) techniques were implemented to obtain the best model for wildfire prediction. The majority of fires in the past six years have primarily occurred during the winter months in coastal locations. The occurrence of fires was accurately predicted by ML models such as random forest (RF), which outperformed competing models. Meanwhile, a CNN with 1D and 2D was used for more improvement in prediction by ML models. The accuracy increased from an 86.48 to 91.34 accuracy score by just using a CNN 1D. For more feature extraction, a CNN 2D was used on the same dataset, which led to state-of-the-art prediction results. A 96.91 accuracy score was achieved by further tuning the RF model on the total data. Data division by spatial and temporal changes was also used for the better prediction of fire, which can further be helpful for understanding the different prospects of wildfire. This research aims to advance wildfire prediction methodologies by leveraging ML techniques to explore the benefits and limitations of capturing complex patterns and relationships in large datasets. Policymakers, environmentalists, and scholars studying climate change can benefit greatly from the study’s analytical approach, which may assist Pakistan in better managing and reducing wildfires.

show abstract

Section: Introductionmentioning

confidence: 99%

Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)

Kanwal,

Rafaqat,

Iqbal

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

Using FlamMap to assess wildfire behavior in Bohemian Switzerland National Park

Kudláčková,

Poděbradská,

Bláhová

et al. 2023

Nat Hazards

View full text Add to dashboard Cite

The 2022 summer re in Bohemian Switzerland National Park (BSNP) is ranked as the largest in the Czech Republic´s 30-year recorded history, with an affected area over 1000 ha. The FlamMap re modeling system was used to investigate the re behavior associated with the BSNP and to evaluate scenarios under a range of fuel types, fuel moistures, and weather conditions. We used the model to simulate re conditions, propagation, and extent. We focused on matching the observed re perimeter and on re behavior characteristics. The re took place in a region of BSNP that was heavily affected by the Spruce bark beetle (Ips typographus L.) infestation; hence, most of the burned area was in dead spruce forest (Picea abies Karst.). The best FlamMap simulations of observed re behavior and progression were compared with several created scenarios that differed in various input conditions. Scenarios included a re in a healthy spruce forest, in clearcuts, or under different meteorological conditions. We were able to calibrate and use FlamMap to recreate a recent wild re under observed conditions. We found that the re would have likely spread to its observed nal perimeter even if standing dead trees were removed. However, at lower re intensity and with a considerably shorter duration. Alternatively, if healthy standing vegetation with a closed canopy had been present, the wild re perimeter would have been approximately half. Similar results were obtained for both the nonnative spruce forest and the deciduous forest, which is a native alternative.

show abstract

Urban Fire Risk Dynamics and Mitigation Strategies in Shanghai: Integrating Spatial Analysis and Game Theory

Yao,

Zhang,

Chen

et al. 2024

Land

View full text Add to dashboard Cite

In recent decades, the increasing frequency of urban fires, driven by urban functional enhancements and climate change, has posed a growing threat to metropolitan sustainability. This study investigates the temporal and spatial characteristics of fire incidents in Shanghai from 2019 to 2023. Using satellite fire point data and official government records, kernel density analysis and wavelet analysis were employed to analyze the time series and spatial distribution of fire data. Subsequently, eleven primary factors influencing urban fire occurrence were identified, encompassing probability, regional characteristics, and hazard sources. A combined methodology of subjective and objective weights with game theory was used to generate a fire risk assessment at a 1 × 1 km2 grid scale. Furthermore, the spatial distribution characteristics of the assessments were analyzed. The results reveal that the downtown area exhibits the highest intensity of urban fires in terms of spatial domain, with a decreasing intensity towards the suburbs. Temporally, fire frequency demonstrates significant periodicity at an 18a time scale, while clear seasonal fluctuations and periodicity are observed at a 16-22a time scale, with higher occurrences in spring and winter. The study identifies typical aggregation patterns of urban fires, with high-risk centers in downtown Shanghai. Considering the impact of climate change and human activities, high-risk areas may gradually expand to adjacent urban suburbs, presenting a concerning future scenario. By examining the dual attributes of “combustibles and fireproof space” within urban greening systems, this research offers recommendations for the future strategies of disaster prevention and mitigation of green systems in Shanghai.

show abstract

A novel urban vegetation mapping approach for fire risk assessment: A Mediterranean case study

Cited by 3 publications

References 57 publications

Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)

Data-Driven Approaches for Wildfire Mapping and Prediction Assessment Using a Convolutional Neural Network (CNN)

Using FlamMap to assess wildfire behavior in Bohemian Switzerland National Park

Urban Fire Risk Dynamics and Mitigation Strategies in Shanghai: Integrating Spatial Analysis and Game Theory

Contact Info

Product

Resources

About