	US 12,236,505 B2
	Systems and methods for generating flood hazard estimation using machine learning model and satellite data
Kian Kenyon-Dean, Toronto (CA); Bo Zhao, Toronto (CA); Keyvan Kasiri, Toronto (CA); Yevgeniy Vahlis, Toronto (CA); Todd Fraser, Toronto (CA); Lyndsay Morrison, Toronto (CA); Michael Torrance, Toronto (CA); and Stella Wu, Toronto (CA)
Assigned to BANK OF MONTREAL, Toronto (CA)
Filed by BANK OF MONTREAL, Toronto (CA)
Filed on Oct. 4, 2021, as Appl. No. 17/493,788.
Claims priority of provisional application 63/087,505, filed on Oct. 5, 2020.
Prior Publication US 2022/0108504 A1, Apr. 7, 2022
Int. Cl. G06T 11/40 (2006.01); G06N 3/045 (2023.01); G06N 3/088 (2023.01); G06T 7/40 (2017.01); G06V 10/94 (2022.01); G06V 30/422 (2022.01)

CPC G06T 11/40 (2013.01) [G06N 3/045 (2023.01); G06N 3/088 (2013.01); G06T 7/40 (2013.01); G06V 10/95 (2022.01); G06V 30/422 (2022.01); G06T 2207/10032 (2013.01); G06T 2207/20084 (2013.01)]

20 Claims

1. A computer-implemented method comprising:

inputting, by a computer, a satellite elevation map;

applying, by the computer, a machine learning model that is trained using a generative adversarial network to output a deterministic hazard mapping algorithm;

applying, by the computer, the generative adversarial network using the outputted deterministic hazard mapping algorithm to generate, based on a mapping from the satellite elevation map, a map representing flood hazard areas that are vulnerable to flooding; and

outputting, by the computer, the map representing the flood hazard areas.