Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 5
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Automatizando y acelerando el procesamiento de Datos LiDAR con IA

  • Sánchez Gayet, Paula|||0009-0003-6372-716X
  • González Fernández, Irene|||0000-0001-8602-6495
  • Cortés Fité, Ana|||0000-0003-1697-1293
  • Margalef, Tomàs|||0000-0001-6384-7389
  • Suppi, Remo|||0000-0002-0373-8292
  • Carrillo, Carlos|||0000-0003-3606-7517
Con los avances tecnológicos recientes, los datos LiDAR están siendo cada vez más solicitados y utilizados en diversas áreas, no solo para visualización, sino también en la planificación urbana, la gestión forestal y otras aplicaciones administrativas. Para aprovechar eficazmente los datos LiDAR, es esencial georreferenciarlos, limpiarlos y clasificarlos. Estos procesos pueden realizarse manualmente, donde un operador asigna etiquetas o elimina puntos, o mediante algoritmos y técnicas de aprendizaje automático que automatizan el proceso. Sin embargo, persisten muchas limitaciones en estos procesos debido al tamaño de las nubes de puntos LiDAR y al costo computacional asociado para procesarlos. Para abordar este desafío, en este trabajo se propone una metodología para automatizar y acelerar el procesamiento de nubes de puntos, que incluye la asignación de color a cada punto, la eliminación de superposiciones y ruido, así como la clasificación de los puntos, entre otras tareas. Este proceso se paralelizará y se ejecutará en entornos cloud.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Edge computing driven forest fire spread simulation, An energy-aware study

  • Carrillo, Carlos|||0000-0003-3606-7517
  • Margalef, Tomàs|||0000-0001-6384-7389
  • Espinosa, Antonio|||0000-0002-6460-3789
  • Cortés Fité, Ana|||0000-0003-1697-1293
An accurate and fast prediction of forest fire evolution is a crucial issue to minimize its impact. One of the challenges facing forest fire spread simulators is the uncertainty surrounding the input data. While high-performance computing (HPC) platforms help reduce these uncertainties, their accessibility during emergencies is limited due to infrastructure constraints. real time data collection using sensors onboard Unmanned Aerial Vehicles (UAVs) in real time can significantly reduce their uncertainty. However, transmitting this data to HPC environments and returning the results to firefighters remains difficult, especially in areas with poor connectivity. We propose using Edge Computing to address these challenges, leveraging low-consumption GPU-accelerated embedded systems for in situ data processing and wildfire spread simulation. For simulation purposes, the FARSITE forest fire spread simulator has been used. This work aims to demonstrate the feasibility of leveraging Embedded Systems with low-consumption GPUs to simulate short-term forest fire spread evolution (up to 5 hours) at high resolution (5 meters). The obtained results highlight that these devices can gather data, simulate the hazard, and deliver prediction results in situ, even without connectivity, opening up the possibility of monitoring and predicting fire behavior at high resolution without employing HPC platforms.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Realistic wildfire growth simulations applying a differentiable parametric representation of the fire front based on Composite Bézier curves

  • González Fernández, Irene|||0000-0001-8602-6495
  • Carrillo, Carlos|||0000-0003-3606-7517
  • Cortés Fité, Ana|||0000-0003-1697-1293
  • Margalef, Tomàs|||0000-0001-6384-7389
Modelling the evolution of a forest fire in Wildland Urban Interface (WUI) areas is still a major challenge in the field of forest fire simulation. Most existing forest fire spread simulators are based on polygonal representations of the fire perimeter, which often fail to capture the complexities of fire behaviour in these areas. Elliptical Wave Propagation (EWP) based simulators rely on this type of forest fire perimeter representation, that is, they represent the fire perimeter as a series of points connected by straight lines where the evolution of the fire front is performed by evaluating the spread of each perimeter point using as the spread direction the direction of the normal vector at each of them. To this end, EWP-based simulators have been built on top of the Richard model, which uses a differentiable parametric representation of the fire front. However, due to the polygonal representation used by EWP-based simulators, these cannot exploit the mathematical potential of using a parametric representation of the fire perimeter, which could compromise the accuracy of the simulations. To address these limitations, we propose a novel parametric representation of the fire front using Composite Bézier Curves (CBC). The proposed wildfire perimeter representation improves the realism of the fire shapes being smooth and rounded. The first implementation of this proposal was done keeping the original method of normal vector calculation. This approach has been called Composite Bézier Curves using Neighbours (CBCN). However, an improved methodology has also been proposed where a more accurate method for calculating the normal vector directions is used, which is aligned with the curvatures of the fire front, thereby improving the overall modelling of fire dynamics. This advanced proposal has been called Composite Bézier Curves using Differentials (CBCD). Both proposed methodologies have been integrated into FARSITE, a well-known EWP-based forest fire spread simulator. Traditional polygonal representation (LIN) and the new CBC-based approach (CBCN and CBCD) were tested in ideal scenarios and two real cases. The obtained results show that any CBC-based representation generates more realistic fire shapes and they also enhance the simulator's ability to model fire spread in WUI areas, with CBCD being the proposal that obtains the best results.
Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Enhancing the realism of wildfire simulation using composite Bézier curves

  • González Fernández, Irene|||0000-0001-8602-6495
  • Carrillo, Carlos|||0000-0003-3606-7517
  • Cortés Fité, Ana|||0000-0003-1697-1293
  • Margalef, Tomàs|||0000-0001-6384-7389
One of the consequences of climate change is the increase in forest fires around the world. In order to act quickly when this type of natural disaster occurs, it is important to have simulation tools that allow a better approximation of the evolution of the fire, especially in Wildland Urban Interface (WUI) areas. Most forest fire propagation simulators tend to represent the perimeter of the fire in a polygonal way, which often does not allow us to capture the real evolution of the fire in complex environments, both at the terrain and vegetation levels. In this work, we focus on Elliptical Wave Propagation (EWP) based simulators, which represent the perimeter of the fire with a set of points connected to each other by straight lines. When the perimeter grows and new points must be added, the interpolation method used is linear interpolation. This system generates unrealistic shapes of fires. In this work, an interpolation method leveraging Composite Bézier Curves (CBC) is proposed to generate fire evolution shapes in a more realistic way. The proposed method has been incorporated into FARSITE, a well-known EWP-based forest fire spread simulator. Both interpolation methods have been applied to ideal scenarios and a real case. The results show that the proposed interpolation method (CBC) is capable of generating more realistic fire shapes and, in addition, enables the simulator the ability to better simulate the spread of fire in WUI zones.
Dipòsit Digital de Documents de la UAB
Publicación Artículo científico (JournalArticle)

Enhancing high-resolution fuel maps in WUI areas, El Pont de Vilomara fire, a case study

  • Sánchez Gayet, Paula|||0009-0003-6372-716X
  • González Fernández, Irene|||0000-0001-8602-6495
  • Cortés Fité, Ana|||0000-0003-1697-1293
  • Margalef, Tomàs|||0000-0001-6384-7389
  • Carrillo, Carlos|||0000-0003-3606-7517
A precise understanding of the spatial distribution of fuels and buildings at high resolution is crucial for analysing, modelling, and predicting fire behaviour in Wildland-Urban Interface (WUI) areas. However, the challenging and costly nature of estimating and mapping forest fuel attributes presents obstacles to global efforts in creating high-resolution fuel maps. This work addresses these limitations by proposing a strategy to generate high-resolution fuel maps based on the 1 km resolution FirEUrisk fuel map and transforming it into an enriched 20 m resolution fuel map, incorporating constructions and water masks. For simulation purposes, the forest fire spread simulator FARSITE has been used. The proposed enhanced downscaling strategy has been tested on a forest fire that occurred in July 2022 in the village El Pont de Vilomara in Catalonia (north-east of Spain). This work highlights how detailed mapping can significantly improve the precision of forest fire simulations, especially in WUI areas. The higher resolution fuel map provides a more accurate representation of fire behavior (SC 0.8 vs. 0.7) while maintaining the same fire detection (POD) as the unchanged fuel map but significantly reducing false alarms (lower FAR). This improvement contributes to proactive fire prevention strategies and ensures an immediate and effective emergency response.