Reference : Monitoring and Early Detection of Wildfires Using Multiple-payload Fractionated Spacecraft
Scientific congresses, symposiums and conference proceedings : Unpublished conference
Engineering, computing & technology : Aerospace & aeronautics engineering
http://hdl.handle.net/10993/53552
Monitoring and Early Detection of Wildfires Using Multiple-payload Fractionated Spacecraft
English
Alandihallaj, Mohammadamin mailto [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SPASYS > ; University of Toronto - U of T > Institute for Aerospace Studies]
Emami, M. Reza mailto [University of Toronto - U of T > Institute for Aerospace Studies]
20-Sep-2022
Yes
73rd International Astronautical Congress (IAC)
18-22 September 2022
[en] Fire detection ; Fractionated spacecraft ; Convolutional neural network
[en] The paper discusses the deployment of multiple-payload fractionated spacecraft as a surveillance system for autonomously monitoring and detecting wildfires at early stages in any area on the Earth’s surface. The fractionated system, consisting of 12 operational CubeSats, four reserved CubeSats, and one Mothership, acquires images in 13 spectral bands within the visible, near infrared, and short-wave infrared regions with high spatial resolutions. A dynamic fire-hazard index is introduced, based on geographic coordinates, environmental parameters, and weather conditions, to prioritize the areas for the probability of wildfires. Then, a convolutional neural network is designed to identify potentially hazardous areas and detect the early stages of wildfire spots. The detection method is based on the processed images and geographic locations as well as measurements of thermal anomalies, smoke, and unusual variations of regional atmospheric conditions. The effectiveness of the surveillance system is examined through several case studies using numerical simulations.
http://hdl.handle.net/10993/53552

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Limited access
IAC-2022_paper_8.pdfPublisher postprint662.7 kBRequest a copy

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.