Potential of Sentinel-2A Data to Model Surface and Canopy Fuel Characteristics in Relation to Crown Fire Hazard

Abstract

Background: Crown fires are often intense and fast spreading and hence can have serious impacts on soil, vegetation, and wildlife habitats. Fire managers try to prevent the initiation and spread of crown fires in forested landscapes through fuel management. The minimum fuel conditions necessary to initiate and propagate crown fires are known to be strongly influenced by four stand structural variables: surface fuel load (SFL), fuel strata gap (FSG), canopy base height (CBH), and canopy bulk density (CBD). However, there is often a lack of quantitative data about these variables, especially at the landscape scale. Methods: In this study, data from 123 sample plots established in pure, even-aged, Pinus radiata and Pinus pinaster stands in northwest Spain were analyzed. In each plot, an intensive field inventory was used to characterize surface and canopy fuels load and structure, and to estimate SFL, FSG, CBH, and CBD. Equations relating these variables to Sentinel-2A (S-2A) bands and vegetation indices were obtained using two non-parametric techniques: Random Forest (RF) and Multivariate Adaptive Regression Splines (MARS). Results: According to the goodness-of-fit statistics, RF models provided the most accurate estimates, explaining more than 12%, 37%, 47%, and 31% of the observed variability in SFL, FSG, CBH, and CBD, respectively. To evaluate the performance of the four equations considered, the observed and estimated values of the four fuel variables were used separately to predict the potential type of wildfire (surface fire, passive crown fire, or active crown fire) for each plot, considering three different burning conditions (low, moderate, and extreme). The results of the confusion matrix indicated that 79.8% of the surface fires and 93.1% of the active crown fires were correctly classified; meanwhile, the highest rate of misclassification was observed for passive crown fire, with 75.6% of the samples correctly classified. Conclusions: The results highlight that the combination of medium resolution imagery and machine learning techniques may add valuable information about surface and canopy fuel variables at large scales, whereby crown fire potential and the potential type of wildfire can be classified.

Exploitation of Sentinel-2 Time Series to Map Burned Areas at the National Level: A Case Study on the 2017 Italy Wildfires

“…Besides the identification of burned areas, dense multitemporal series of optical satellite observations can be used to extract much more wildfire-related information that can rarely be measured after a wildfire takes place, information regarding, for example, the active fires and the pre-fire land cover type affected by the wildfires. Such thematic data play a major role in supporting knowledge about wildfires since they can be exploited to derive information related to fire fuel load [66] and therefore used to estimate other components of the fire regime and the amount of smoke emitted, and consequently the wildfire impact on air quality. Finally, the comparison of pre-fire and post-fire conditions can be used to monitor ecosystem responses through the restoration of vegetation and to account for environmental losses, such as habitat loss or changes in ecosystem services.…”

Fuel Type Classification Using Airborne Laser Scanning and Sentinel 2 Data in Mediterranean Forest Affected by Wildfires

“…Remote sensing can assist fuel mapping through the characterization of horizontal and vertical forest structure components [20] providing the necessary temporal, spectral and spatial coverage, while being less time-consuming than field surveys or aerial photo interpretation [12]. Several studies have attempted fuel type or properties mapping using passive multispectral remote sensing images [19,[21][22][23] and similar levels of accuracy were found between the use of medium-resolution sensors and very high-resolution ones according to Arroyo et al [18]. Although little comparison has been carried out between the use of multispectral and hyperespectral data, Lasaponara et al [24] determined an increase of around 20% of the overall accuracy when classifying Prometheus fuel types with MIVIS respect to Landsat TM.…”

“…To the best of our knowledge, this is the first attempt to classify fuel types at regional scale using low density ALS data, multispectral Sentinel 2 data, and field work that compares the performance of classification using both datasets together or separately. Sentinel 2 data have been used to characterize canopy fuel characteristics [23], fuel types [49] or mapping wildfire ignition [42], while the integration with ALS for fuel mapping at regional scale requires further analysis. Furthermore, the research analyzes whether differences in the presence of fuel types exists between areas previously burned in 1994 or unburned ones.…”

Comparison of Machine Learning Algorithms for Wildland-Urban Interface Fuelbreak Planning Integrating ALS and UAV-Borne LiDAR Data and Multispectral Images

“…Different authors [8,9] have preferred to use only active sensors, which provide values related to vegetation metrics, while others [10][11][12][13][14] have privileged the combination of multispectral imagery with LiDAR information to improve classification accuracies in forest environments. In all cases, the use of remote sensing substantially reduces the cost of the estimation process [15].…”