US 12,404,763 B2
Wireless hydrogen subsurface sensing framework for reservoir optimization
Klemens Katterbauer, Dhahran (SA); Abdallah Al Shehri, Dhahran (SA); and Abdulaziz S. Al-Qasim, Dammam (SA)
Assigned to SAUDI ARABIAN OIL COMPANY, Dhahran (SA)
Filed by SAUDI ARABIAN OIL COMPANY, Dhahran (SA)
Filed on Aug. 5, 2022, as Appl. No. 17/817,910.
Prior Publication US 2024/0044242 A1, Feb. 8, 2024
Int. Cl. E21B 47/00 (2012.01); E21B 43/243 (2006.01)
CPC E21B 47/00 (2013.01) [E21B 43/243 (2013.01); E21B 2200/22 (2020.05)] 17 Claims
OG exemplary drawing
 
1. A method for optimizing a wireless sensor network for monitoring hydrogen production from fire flooding in a sub-surface reservoir,
the wireless sensor network comprising a plurality of sensors,
wherein each sensor of the plurality of sensors is configured to locally sense environmental conditions in the reservoir,
wherein the plurality of sensors provide a sensing coverage of the environmental conditions for at least a region of the reservoir, and
wherein the plurality of sensors is configured to communicate the locally sensed environmental condition via the plurality of sensors in multi-hop fashion to a base station;
the method comprising:
obtaining, from each sensor, a first measurement of the environmental conditions;
obtaining, from each sensor, a first measurement of a communication performance in presence of the environmental conditions that are prevalent during the measurement of the environmental conditions;
training a machine learning model to generate an estimate of the communication performance of each sensor of the plurality of sensors based on the first measurement of the environmental conditions and the first measurement of the communication performance obtained for the plurality of sensors;
determining a subset of the plurality of sensors by removing at least one sensor from the plurality of sensors without compromising the sensing coverage of the environmental conditions;
obtaining from each sensor of the subset of the plurality of sensors, a second measurement of the environmental conditions;
predicting, by the trained machine learning model operating on the second measurement, a predicted communication performance of the subset of the plurality of sensors;
determining that the predicted communication performance is sufficient to communicate the second measurement to the base station; and
monitoring the environmental conditions in the reservoir using only the subset of the plurality of sensors, based on the determination that the predicted communication performance is sufficient.