Interpretable machine learning optimization(InterOpt)for operational parameters:A case study of highly-efficient shale gas development

An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning,and is demonstrated via optimization of shale gas development.InterOpt consists of three parts:a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space(i.e.,virtual environment);:the Sharpley value method in inter-pretable machine learning is applied to analyzing the impact of geological and operational parameters in each well(i.e.,single well feature impact analysis):and ensemble randomized maximum likelihood(EnRML)is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost.In the experiment,InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions,and finally achieves an average cost reduction of 9.7%for a case study with 104 wells.

Present Situation of China's Shale Gas Exploration and Development

In recent years,with China＇s continuous investment in shale gas exploration and the continuous efforts of scientific workers,China’s shale gas exploration and development has achieved leap-forward development.In2011,China＇s State Council approved shale gas as a new mineral resource.In 2014,shale gas was first proved at geological reserves of 106.8 billion m^3.

Determination of the local magnitudes of small earthquakes using a dense seismic array in the Changning-Zhaotong Shale Gas Field,Southern Sichuan Basin

With the development of unconventional shale gas in the southern Sichuan Basin,seismicity in the region has increased significantly in recent years.Though the existing sparse regional seismic stations can capture most earthquakes with ML≥2.5,a great number of smaller earthquakes are often omitted due to limited detection capacity.With the advent of portable seismic nodes,many dense arrays for monitoring seismicity in the unconventional oil and gas fields have been deployed,and the magnitudes of those earthquakes are key to understand the local fault reactivation and seismic potentials.However,the current national standard for determining the local magnitudes was not specifically designed for monitoring stations in close proximity,utilizing a calibration function with a minimal resolution of 5 km in the epicentral distance.That is,the current national standard tends to overestimate the local magnitudes for stations within short epicentral distances,and can result in discrepancies for dense arrays.In this study,we propose a new local magnitude formula which corrects the overestimated magnitudes for shorter distances,yielding accurate event magnitudes for small earthquakes in the Changning-Zhaotong shale gas field in the southern Sichuan Basin,monitored by dense seismic arrays in close proximity.The formula is used to determine the local magnitudes of 7,500 events monitored by a two-phased dense array with several hundred 5 Hz 3 C nodes deployed from the end of February 2019 to early May 2019 in the Changning-Zhaotong shale gas field.The magnitude of completeness(MC)using the dense array is-0.1,compared to MC 1.1 by the sparser Chinese Seismic Network(CSN).In addition,using a machine learning detection and picking procedure,we successfully identify and process some 14,000 earthquakes from the continuous waveforms,a ten-fold increase over the catalog recorded by CSN for the same period,and the MC is further reduced to-0.3 from-0.1 compared to the catalog obtained via manual processing using the same dense array.The proposed local magnitude formula can be adopted for calculating accurate local magnitudes of future earthquakes using dense arrays in the shale gas fields of the Sichuan Basin.This will help to better characterize the local seismic risks and potentials.