scholarly journals A Deep Learning Approach to Downscale Geostationary Satellite Imagery for Decision Support in High Impact Wildfires

Forests ◽  
2021 ◽  
Vol 12 (3) ◽  
pp. 294
Author(s):  
Nicholas F. McCarthy ◽  
Ali Tohidi ◽  
Yawar Aziz ◽  
Matt Dennie ◽  
Mario Miguel Valero ◽  
...  
Keyword(s):  
Deep Learning ◽  
Decision Support ◽  
Real Time ◽  
Forest Fires ◽  
Wildland Fire ◽  
Fire Spread ◽  
Low Earth Orbit ◽  
Practical Implementation ◽  
Spatiotemporal Resolution ◽  
Active Fire

Scarcity in wildland fire progression data as well as considerable uncertainties in forecasts demand improved methods to monitor fire spread in real time. However, there exists at present no scalable solution to acquire consistent information about active forest fires that is both spatially and temporally explicit. To overcome this limitation, we propose a statistical downscaling scheme based on deep learning that leverages multi-source Remote Sensing (RS) data. Our system relies on a U-Net Convolutional Neural Network (CNN) to downscale Geostationary (GEO) satellite multispectral imagery and continuously monitor active fire progression with a spatial resolution similar to Low Earth Orbit (LEO) sensors. In order to achieve this, the model trains on LEO RS products, land use information, vegetation properties, and terrain data. The practical implementation has been optimized to use cloud compute clusters, software containers and multi-step parallel pipelines in order to facilitate real time operational deployment. The performance of the model was validated in five wildfires selected from among the most destructive that occurred in California in 2017 and 2018. These results demonstrate the effectiveness of the proposed methodology in monitoring fire progression with high spatiotemporal resolution, which can be instrumental for decision support during the first hours of wildfires that may quickly become large and dangerous. Additionally, the proposed methodology can be leveraged to collect detailed quantitative data about real-scale wildfire behaviour, thus supporting the development and validation of fire spread models.

scholarly journals Fractal properties of forest fires in Amazonia as a basis for modelling pan-tropical burnt area

2014 ◽  
Vol 11 (6) ◽  
pp. 1449-1459 ◽  
Author(s):  
I. N. Fletcher ◽  
L. E. O. C. Aragão ◽  
A. Lima ◽  
Y. Shimabukuro ◽  
P. Friedlingstein
Keyword(s):  
Forest Fires ◽  
Large Scale ◽  
Fire Spread ◽  
Small Scale ◽  
Burnt Area ◽  
Active Fire ◽  
Fractal Properties ◽  
Dynamic Global Vegetation Models ◽  
Vegetation Models ◽  
Global Vegetation

Abstract. Current methods for modelling burnt area in dynamic global vegetation models (DGVMs) involve complex fire spread calculations, which rely on many inputs, including fuel characteristics, wind speed and countless parameters. They are therefore susceptible to large uncertainties through error propagation, but undeniably useful for modelling specific, small-scale burns. Using observed fractal distributions of fire scars in Brazilian Amazonia in 2005, we propose an alternative burnt area model for tropical forests, with fire counts as sole input and few parameters. This model is intended for predicting large-scale burnt area rather than looking at individual fire events. A simple parameterization of a tapered fractal distribution is calibrated at multiple spatial resolutions using a satellite-derived burnt area map. The model is capable of accurately reproducing the total area burnt (16 387 km2) and its spatial distribution. When tested pan-tropically using the MODIS MCD14ML active fire product, the model accurately predicts temporal and spatial fire trends, but the magnitude of the differences between these estimates and the GFED3.1 burnt area products varies per continent.

scholarly journals Near Real-Time Automated Early Mapping of the Perimeter of Large Forest Fires from the Aggregation of VIIRS and MODIS Active Fires in Mexico

2020 ◽  
Vol 12 (12) ◽  
pp. 2061 ◽  
Author(s):  
Carlos Ivan Briones-Herrera ◽  
Daniel José Vega-Nieva ◽  
Norma Angélica Monjarás-Vega ◽  
Jaime Briseño-Reyes ◽  
Pablito Marcelo López-Serrano ◽  
...  
Keyword(s):  
Real Time ◽  
Forest Fires ◽  
Large Scale ◽  
Infrared Imaging ◽  
Activity Patterns ◽  
Burned Area ◽  
Management Decision ◽  
Coarse Scale ◽  
Early Evaluation ◽  
Active Fire

In contrast with current operational products of burned area, which are generally available one month after the fire, active fires are readily available, with potential application for early evaluation of approximate fire perimeters to support fire management decision making in near real time. While previous coarse-scale studies have focused on relating the number of active fires to a burned area, some local-scale studies have proposed the spatial aggregation of active fires to directly obtain early estimate perimeters from active fires. Nevertheless, further analysis of this latter technique, including the definition of aggregation distance and large-scale testing, is still required. There is a need for studies that evaluate the potential of active fire aggregation for rapid initial fire perimeter delineation, particularly taking advantage of the improved spatial resolution of the Visible Infrared Imaging Radiometer (VIIRS) 375 m, over large areas and long periods of study. The current study tested the use of convex hull algorithms for deriving coarse-scale perimeters from Moderate Resolution Imaging Spectroradiometer (MODIS) and Visible Infrared Imaging Radiometer Suite (VIIRS) active fire detections, compared against the mapped perimeter of the MODIS collection 6 (MCD64A1) burned area. We analyzed the effect of aggregation distance (750, 1000, 1125 and 1500 m) on the relationships of active fire perimeters with MCD64A1, for both individual fire perimeter prediction and total burned area estimation, for the period 2012–2108 in Mexico. The aggregation of active fire detections from MODIS and VIIRS demonstrated a potential to offer coarse-scale early estimates of the perimeters of large fires, which can be available to support fire monitoring and management in near real time. Total burned area predicted from aggregated active fires followed the same temporal behavior as the standard MCD64A1 burned area, with potential to also account for the role of smaller fires detected by the thermal anomalies. The proposed methodology, based on easily available algorithms of point aggregation, is susceptible to be utilized both for near real-time and historical fire perimeter evaluation elsewhere. Future studies might test active fires aggregation between regions or biomes with contrasting fuel characteristics and human activity patterns against medium resolution (e.g., Landsat and Sentinel) fire perimeters. Furthermore, coarse-scale active fire perimeters might be utilized to locate areas where such higher-resolution imagery can be downloaded to improve the evaluation of fire extent and impact.

Numerical Prediction of the Fire Spread in Vegetative Fuels Using NISTWFDS Model

2015 ◽  
Vol 20 ◽  
pp. 177-192 ◽  
Author(s):  
Hadj Miloua
Keyword(s):  
Forest Fires ◽  
Wildland Fire ◽  
Radiation Heat Transfer ◽  
Fire Behavior ◽  
Reaction Diffusion ◽  
Fire Spread ◽  
Three Dimensions ◽  
Forest Stands ◽  
Fire Dynamics ◽  
Wind Climate

Current study focuses to the application of an advanced physics-based (reaction–diffusion) fire behavior model to the fires spreading through surface vegetation such as grasslands and elevated vegetation such as trees present in forest stands. This model in three dimensions, called Wildland Fire Dynamics Simulator WFDS, is an extension, to vegetative fuels, of the structural FDS developed at NIST. For simplicity, the vegetation was assumed to be uniformly distributed in a tree crown represented by a well defined geometric shape. This work on will focus on predictions of thermal function such as the radiation heat transfer and and thermal function for diverse cases of spatial distribution of vegetation in forest stands. The influence of wind, climate characteristics and terrain topography will also be used to extend and validate the model. The results obtained provide a basis to carry out a risk analysis for fire spread in the studied vegetative fuels in the Mediterranean forest fires.

scholarly journals Emulation of wildland fire spread simulation using deep learning

2021 ◽  
Vol 141 ◽  
pp. 184-198
Author(s):  
Frédéric Allaire ◽  
Vivien Mallet ◽  
Jean-Baptiste Filippi
Keyword(s):  
Deep Learning ◽  
Wildland Fire ◽  
Fire Spread

Real-time wildland fire spread modeling using tabulated flame properties

2017 ◽  
Vol 91 ◽  
pp. 872-881 ◽  
Author(s):  
Matthieu de Gennaro ◽  
Yann Billaud ◽  
Yannick Pizzo ◽  
Savitri Garivait ◽  
Jean-Claude Loraud ◽  
...  
Keyword(s):  
Real Time ◽  
Wildland Fire ◽  
Fire Spread

Built structure identification in wildland fire decision support

2011 ◽  
Vol 20 (1) ◽  
pp. 78 ◽  
Author(s):  
David E. Calkin ◽  
Jon D. Rieck ◽  
Kevin D. Hyde ◽  
Jeffrey D. Kaiden
Keyword(s):  
At Risk ◽  
Decision Support ◽  
Fire Management ◽  
Wildland Fire ◽  
Management Strategies ◽  
Fire Spread ◽  
The United States ◽  
Structure Identification ◽  
Incident Management ◽  
Wildland Fire Management

Recent ex-urban development within the wildland interface has significantly increased the complexity and associated cost of federal wildland fire management in the United States. Rapid identification of built structures relative to probable fire spread can help to reduce that complexity and improve the performance of incident management teams. Approximate structure locations can be mapped as specific-point building cluster features using cadastral data records. This study assesses the accuracy and precision of building clusters relative to GPS structure locations and compares these results with area mapping of housing density using census-based products. We demonstrate that building clusters are reasonably accurate and precise approximations of structure locations and provide superior strategic information for wildland fire decision support compared with area density techniques. Real-time delivery of structure locations and other values-at-risk mapped relative to probable fire spread through the Wildland Fire Decision Support System Rapid Assessment of Values at Risk procedure supports development of wildland fire management strategies.

Simulation of the Big Elk Fire using coupled atmosphere - fire modeling

2005 ◽  
Vol 14 (1) ◽  
pp. 49 ◽  
Author(s):  
Janice L. Coen
Keyword(s):  
Real Time ◽  
Wildland Fire ◽  
Fire Behavior ◽  
Atmospheric Model ◽  
Fire Spread ◽  
Colorado Front Range ◽  
Front Range ◽  
Computational Performance ◽  
Rigorous Testing ◽  
Wide Range

Models that simulate wildland fires span a vast range of complexity; the most physically complex present a difficult supercomputing challenge that cannot be solved fast enough to become a forecasting tool. Coupled atmosphere–fire model simulations of the Big Elk Fire, a wildfire that occurred in the Colorado Front Range during 2002, are used to explore whether some factors that make simulations more computationally demanding (such as coupling between the fire and the atmosphere and fine atmospheric model resolution) are needed to capture wildland fire parameters of interest such as fire perimeter growth. In addition to a Control simulation, other simulations remove the feedback to the atmospheric dynamics and use increasingly coarse atmospheric resolution, including some that can be computed in faster than real time on a single processor. These simulations show that, although the feedback between the fire and atmosphere must be included to capture accurately the shape of the fire, the simulations with relatively coarse atmospheric resolution (grid spacing 100–500 m) can qualitatively capture fire growth and behavior such as surface and crown fire spread and smoke transport. A comparison of the computational performance of the model configured at these different spatial resolutions shows that these can be performed faster than real time on a single computer processor. Thus, although this model still requires rigorous testing over a wide range of fire incidents, it is computationally possible to use models that can capture more complex fire behavior (such as rapid changes in intensity, large fire whirls, and interactions between fire, weather, and topography) than those used currently in the field and meet a faster-than-real-time operational constraint.

Regional-scale simulations of wildland fire spread informed by real-time flame front observations

2013 ◽  
Vol 34 (2) ◽  
pp. 2641-2647 ◽  
Author(s):  
M.C. Rochoux ◽  
B. Delmotte ◽  
B. Cuenot ◽  
S. Ricci ◽  
A. Trouvé
Keyword(s):  
Flame Front ◽  
Real Time ◽  
Wildland Fire ◽  
Regional Scale ◽  
Fire Spread

scholarly journals Forest Farm Fire Drone Monitoring System Based on Deep Learning and Unmanned Aerial Vehicle Imagery

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Shaoxiong Zheng ◽  
Weixing Wang ◽  
Zeqian Liu ◽  
Zepeng Wu
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Monitoring System ◽  
Forest Fire ◽  
Forest Fires ◽  
Operating Cost ◽  
Operating Efficiency ◽  
Rescue Operation ◽  
Fire Monitoring ◽  
Forest Farm

Forest fires represent one of the main problems threatening forest sustainability. Therefore, an early prevention system of forest fire is urgently needed. To address the problem of forest farm fire monitoring, this paper proposes a forest fire monitoring system based on drones and deep learning. The proposed system aims to solve the shortcomings of traditional forest fire monitoring systems, such as blind spots, poor real-time performance, expensive operational costs, and large resource consumption. The image processing techniques are used to determine whether the frame returned by a drone contains fire. This process is accomplished in real time, and the resultant information is used to decide whether a rescue operation is needed. The proposed method has simple operations, high operating efficiency, and low operating cost. The experimental results indicate that the relative accuracy of the proposed algorithm is 81.97%. In addition, the proposed technique provides a digital ability to monitor forest fires in real time effectively. Thus, it can assist in avoiding fire-related disasters and can significantly reduce the labor and other costs of forest fire disaster prevention and suppression.

Sign in / Sign up

Export Citation Format

Share Document