US 12,292,310 B2
Machine learning based methane emissions monitoring
Nader Salman, Tomball, TX (US); and Lukasz Zielinski, Arlington, MA (US)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
Filed on Dec. 13, 2023, as Appl. No. 18/537,978.
Claims priority of provisional application 63/485,944, filed on Feb. 20, 2023.
Claims priority of provisional application 63/433,004, filed on Dec. 15, 2022.
Prior Publication US 2024/0200991 A1, Jun. 20, 2024
Int. Cl. G01D 21/00 (2006.01); G06N 20/00 (2019.01)
CPC G01D 21/00 (2013.01) [G06N 20/00 (2019.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
collecting sensor data from a plurality of sensors, comprising:
creating a training database for a particular facility and a sensor layout by performing operations comprising:
generating a series of test releases of a pollutant at different rates,
detecting concentrations for a range of wind and other meteorological conditions at the sensors,
moving an emission source to various places around a facility, and
repeating the detecting after moving the emission source;
applying an augmentation model to the sensor data to form a regression training set, wherein the augmentation model modifies the sensor data to generate synthetic input and applies a physics-based model to the synthetic input to create synthetic output, wherein the synthetic input and the synthetic output are combined to generate the regression training set comprising a plurality of regression output values corresponding to a plurality of input values, wherein the plurality of regression output values comprises the synthetic output and wherein the plurality of input values comprises the synthetic input;
creating a classification training set for a classification model by applying a threshold to the plurality of regression output values from the regression training set to generate a plurality of classification output values, wherein the plurality of classification output values comprises binary values;
training a regression model with the regression training set to generate a regression prediction; and
training the classification model with the classification training set to generate a classification prediction.