Towards global flood mapping onboard low cost satellites with machine learning
Spaceborne Earth observation is a key technology for flood response, offering valuable information to decision makers on the ground. Very large constellations of small, nano satellites- 'CubeSats' are a promising solution to reduce revisit time in disaster areas from days to hours. However...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
Springer Nature
2021
|
| _version_ | 1826311201402912768 |
|---|---|
| author | Mateo-Garcia, G Veitch-Michaelis, J Smith, L Oprea, SV Schumann, G Gal, Y Baydin, AG Backes, D |
| author_facet | Mateo-Garcia, G Veitch-Michaelis, J Smith, L Oprea, SV Schumann, G Gal, Y Baydin, AG Backes, D |
| author_sort | Mateo-Garcia, G |
| collection | OXFORD |
| description | Spaceborne Earth observation is a key technology for flood response, offering valuable information to decision makers on the ground. Very large constellations of small, nano satellites- 'CubeSats' are a promising solution to reduce revisit time in disaster areas from days to hours. However, data transmission to ground receivers is limited by constraints on power and bandwidth of CubeSats. Onboard processing offers a solution to decrease the amount of data to transmit by reducing large sensor images to smaller data products. The ESA's recent PhiSat-1 mission aims to facilitate the demonstration of this concept, providing the hardware capability to perform onboard processing by including a power-constrained machine learning accelerator and the software to run custom applications. This work demonstrates a flood segmentation algorithm that produces flood masks to be transmitted instead of the raw images, while running efficiently on the accelerator aboard the PhiSat-1. Our models are trained on WorldFloods: a newly compiled dataset of 119 globally verified flooding events from disaster response organizations, which we make available in a common format. We test the system on independent locations, demonstrating that it produces fast and accurate segmentation masks on the hardware accelerator, acting as a proof of concept for this approach. |
| first_indexed | 2024-03-07T08:06:16Z |
| format | Journal article |
| id | oxford-uuid:3befdca0-deb1-4cbe-aa30-763d8e55d82e |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T08:06:16Z |
| publishDate | 2021 |
| publisher | Springer Nature |
| record_format | dspace |
| spelling | oxford-uuid:3befdca0-deb1-4cbe-aa30-763d8e55d82e2023-10-31T12:15:40ZTowards global flood mapping onboard low cost satellites with machine learningJournal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:3befdca0-deb1-4cbe-aa30-763d8e55d82eEnglishSymplectic ElementsSpringer Nature2021Mateo-Garcia, GVeitch-Michaelis, JSmith, LOprea, SVSchumann, GGal, YBaydin, AGBackes, DSpaceborne Earth observation is a key technology for flood response, offering valuable information to decision makers on the ground. Very large constellations of small, nano satellites- 'CubeSats' are a promising solution to reduce revisit time in disaster areas from days to hours. However, data transmission to ground receivers is limited by constraints on power and bandwidth of CubeSats. Onboard processing offers a solution to decrease the amount of data to transmit by reducing large sensor images to smaller data products. The ESA's recent PhiSat-1 mission aims to facilitate the demonstration of this concept, providing the hardware capability to perform onboard processing by including a power-constrained machine learning accelerator and the software to run custom applications. This work demonstrates a flood segmentation algorithm that produces flood masks to be transmitted instead of the raw images, while running efficiently on the accelerator aboard the PhiSat-1. Our models are trained on WorldFloods: a newly compiled dataset of 119 globally verified flooding events from disaster response organizations, which we make available in a common format. We test the system on independent locations, demonstrating that it produces fast and accurate segmentation masks on the hardware accelerator, acting as a proof of concept for this approach. |
| spellingShingle | Mateo-Garcia, G Veitch-Michaelis, J Smith, L Oprea, SV Schumann, G Gal, Y Baydin, AG Backes, D Towards global flood mapping onboard low cost satellites with machine learning |
| title | Towards global flood mapping onboard low cost satellites with machine learning |
| title_full | Towards global flood mapping onboard low cost satellites with machine learning |
| title_fullStr | Towards global flood mapping onboard low cost satellites with machine learning |
| title_full_unstemmed | Towards global flood mapping onboard low cost satellites with machine learning |
| title_short | Towards global flood mapping onboard low cost satellites with machine learning |
| title_sort | towards global flood mapping onboard low cost satellites with machine learning |
| work_keys_str_mv | AT mateogarciag towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT veitchmichaelisj towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT smithl towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT opreasv towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT schumanng towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT galy towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT baydinag towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning AT backesd towardsglobalfloodmappingonboardlowcostsatelliteswithmachinelearning |