Crowd-Sourced Wildfire Spread Prediction With Remote Georeferencing Using Smartphones

Nikos Bogdos,Elias S Manolakos

doi:10.1109/access.2019.2931456

Abstract

Wildfires are natural hazards with severe consequences worryingly worsening for many climate-change affected regions of our planet. Unfortunately, technologies that can provide real-time fire-line information, such as satellites, in-field sensors, and social media texts, exhibit low spatial/temporal resolution or cannot be deployed cost-effectively in widespread geographical areas. We present the design, development, and implementation of a novel software service, called CITISENS, which by exploiting commodity smartphone sensors allows ordinary citizens to easily georeference a fire-line in real-time and report its coordinates as they are photographing a wildfire. The location/orientation sensors and the camera are used to compute the view-ray of the smartphone, and a digital elevation model is employed to estimate the ray's intersection with the topography. We have tested the georeferencing accuracy obtained and it is to be on par with, or even better, than that of existing satellite wildfire hotspot services. When combined with FLogA, a flexible wildfire spread simulator we have also developed, CITISENS offers the following unique advantages: real-time prediction of burn probabilities, dynamic assimilation of citizen-reported hotspots into ongoing simulations for improved predictive accuracy, and decision support to issue citizen alarms based on the estimated time-dependent risk at their location due to an approaching wildfire.

Highlights

We have become the passive observers of the dire consequences of climate change on wildfires’ frequency and scale
We have presented novel methods enabling the generation of quality Volunteered Geographic Information (VGI) from citizens during wildfire events and a VGI framework that can support a crowd-sourced Dynamic Data Driven Assimilation System (DDDAS) for effective wildfires course prediction
The developed CITISENS service consists of a set of collaborating applications providing to decision-makers take advantage of streams of georeferenced hotspots that can be used to improve the quality of wildfire propagation predictions

Summary

INTRODUCTION

We have become the passive observers of the dire consequences of climate change on wildfires’ frequency and scale. The CITISENS wildfire DDDAS algorithm, as currently implemented, takes as input the defined MSS (utilizing initially uniform scenarios weighting) and reconfigures the weights dynamically according to the prediction performance of the individual scenarios measured against reported hotspot data contributed by citizens. The reconfiguration of scenarios weights works as follows: The user of the CITISENS viewer application (presumably a trusted public entity) observes the hotspot reports as they arrive and has the option to assimilate them at any time to update the wildfire simulation. In the case of subsequent hotspot reports for the same area, the user of the CITISENS viewer has the option to use an existing wildfire simulation and assimilate the new reports (to update the burn probabilities) using the PHP-written DDDAS software component. The CITISENS viewer can run on any mobile platform as well

TESTING SCHEME The two locations used for the georeferencing tests were

Findings

CONCLUSIONS