Assessing tree crown fire damage integrating linear spectral mixture analysis and supervised machine learning on Sentinel-2 imagery

Crown fire damage is a mixture of three principal fire-related components:charred material,scorched foliage,and unaltered green canopy.This study estimated the abundance of these physical alterations in two immediate post-fire Mediterranean forest contexts(Portugal and Italy)by applying linear spectral mixture analysis(LSMA)on Sentinel-2 imagery.The tree crowns fire damage was subsequently mapped,integrating fractional abundance information in a random forest(RF)algorithm,comparing the accuracy resulting from the adoption of generic or image spectral libraries as the primary investigative goal.Although image-derived endmembers resulted in more effectiveness in terms of fire-related components abundance quantification(LMSAderived RMSE<0.1),the F-scores always were≥90%whether generic endmembers or image endmembers derived information was employed.The environmental heterogeneity of the two study areas affected the fire severity gradients,with a prevalence of the charred(PT)(45–46%)and green class(IT)(44–53%).Post-fire temporal monitoring was initialized by applying the proposed strategies,and the preliminary results showed a positive recovery trend in forest vegetation from the first year following the fire event,with a reduced charcoal predominance and an increasing proportion of green components.

Discussion on Detection and Evaluation of Simply Supported Prestressed Concrete Small Box Girder Bridge After a Fire

The article takes a simply supported prestressed concrete small box girder bridge project as an example for inspection and evaluation after a fire incident.This includes appearance detection,concrete color hardness detection,concrete strength detection,concrete surface damage layer detection,reinforcement protective layer detection,and concrete carbonation detection.It is hoped that this analysis can be used as a reference for the detection and evaluation of future bridge projects with fire incidents to smoothen its subsequent repair and maintenance.

An expert system for diagnosing fire-caused damages to reinforced-concrete tunnel lining

During the last four decades, reinforced-concrete structure failures have been happening widely for many reasons, such as increased service loads, war accidents, fire, and durability problems. The economic losses due to those failures are very high. An expert system is an interactive computer-based decision tool that uses both facts and heuristics to solve difficult problems based on knowledge acquired from experts. To realize these requirements, a logic programming visual basic language is used together with visual diagnosis. The expert system, Diagnosis of Fire-Caused Damages to Reinforced-Concrete Tunnel Lining (DFCDRCTL) was developed in this work for diagnosing the annual damages caused by fire. The program is used as an alternative of a human expert to make annual technical decisions in diagnosing fire damages at the second reinforced-concrete tunnel lining segment. It is concluded that the proposed DFCDRCTL expert system is easy to use, and is fast and helpful for engineers.