Crowd-Sourced Wildfire Spread Prediction With Remote Georeferencing Using Smartphones

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 fireline 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.

The role of citizen science mobile apps in facilitating a contemporary digital agora

“…Techniques and methods associated with CS mobile apps (n = 114). Using data collected from untrained individuals in prognosis methods can contribute to reducing the negative effects of certain risk phenomena by improving prevention systems (Annis and Nardi 2019;Bogdos and Manolakos 2019;Finazzi 2020a). The great drawback of VGI derives from the fact that this is considered qualitative information.…”

The FireLoc System - Geolocating Forest Fires with Crowdsourced Data

“…Other approaches based on crowdsourced data have been proposed, using, e.g., data extracted from social media (e.g., Al-Salehi et al, 2021;Tavra et al, 2021;Arapostathis & Karantzia, 2019) or dedicated apps, such as the CITISENS project in Greece (Bogdos & Manolakos, 2019). However, the geolocation with data collection from social media has many limitations, including the data and metadata obtained using the available social media Advances in Forest Fire Research 2022 -D. X.…”

“…For example, the CITISENS project uses a methodology that geolocates the events using additional data collected from the smartphone, such as gyroscope and accelerometer data, to identify the observer's line of sight and geolocates the observed fire events by intersecting the estimated line of sight with a Digital Elevation Model. The authors stated that the geolocation estimated following such methodology provided accurate results (Bogdos & Manolakos, 2019), even though it assumes that the observer has a direct line of sight to the fire (i.e., it would not work in case the observer is just seeing a column of smoke). Therefore, it would be interesting, in a subsequent stage, to compare the geolocation accuracy obtained with both approaches and determine if the fusion of both methodologies is able to increase the accuracy of the geolocation of observed events.…”