US 11,768,307 B2
Machine-learning based fracture-hit detection using low-frequency DAS signal
Ge Jin, Houston, TX (US); Kevin Mendoza, Houston, TX (US); Baishali Roy, Houston, TX (US); and Darryl G. Buswell, Houston, TX (US)
Assigned to ConocoPhillips Company, Houston, TX (US)
Filed by ConocoPhillips Company, Houston, TX (US)
Filed on Mar. 11, 2020, as Appl. No. 16/815,378.
Claims priority of provisional application 62/823,440, filed on Mar. 25, 2019.
Prior Publication US 2020/0309982 A1, Oct. 1, 2020
Int. Cl. G01V 1/50 (2006.01); E21B 47/14 (2006.01); G06N 3/084 (2023.01); G06F 17/18 (2006.01); G02B 6/44 (2006.01); G06N 20/00 (2019.01)
CPC G01V 1/50 (2013.01) [E21B 47/14 (2013.01); G02B 6/4401 (2013.01); G06F 17/18 (2013.01); G06N 3/084 (2013.01); G06N 20/00 (2019.01); G01V 2210/646 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a set of features for a first well proximate to a second well, the second well undergoing a hydraulic fracturing process for extraction of natural resources from underground formations, and the set of features including:
a summation strain rate, at a location associated with the set of features, during a set period; and
filtered data corresponding to the summation strain rate;
inputting the set of features into a trained neural network; and
providing, as output of the trained neural network, a probability of a fracture hit at the location associated with the set of features in the first well during a given completion stage of the hydraulic fracturing process in the second well.