US 12,236,329 B2
Estimate ore content based on spatial geological data through 3D convolutional neural networks
Bianca Zadrozny, Rio de Janeiro (BR); Helon Vicente Hultmann Ayala, Rio de Janeiro (BR); Breno William Santos Rezende de Carvalho, Rio de Janeiro (BR); Daniel Salles Chevitarese, Rio de Janeiro (BR); Daniela de Mattos Szwarcman, Rio de Janeiro (BR); Lucas Correia Villa Real, Sao Paulo (BR); Marcio Ferreira Moreno, Rio de Janeiro (BR); and Paulo Rodrigo Cavalin, Rio de Janeiro (BR)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Sep. 5, 2018, as Appl. No. 16/122,859.
Prior Publication US 2020/0074270 A1, Mar. 5, 2020
Int. Cl. G06N 3/04 (2023.01); G01V 20/00 (2024.01); G06N 3/08 (2023.01)
CPC G06N 3/04 (2013.01) [G01V 20/00 (2024.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computing device comprising:
a network interface;
a processor; and
a storage device storing a set of instructions, wherein an execution of the set of instructions by the processor configures the computing device to perform acts comprising:
receiving structured geological data that is derived based on spatial geological information that is converted into tensors and associated with an input region, the spatial geological information comprising one or more different types of data;
training a prediction model to produce a prediction output based on an average grade of an ore of a target mineral type at a target region nested in the input region, by using the tensors of the received structured geological data of the input region, wherein the use of tensors improves the time efficiency of the training of the prediction model;
identifying a relationship of the structured geological data to the prediction output; and
determining a revised input region based on the identified relationship without changing the target region.