Machine learning-based calculation and characteristic analysis of terrestrial heat flow in the Songliao Basin
GONG Ming-Xu1(), BAI Li-Ge2, ZENG Zhao-Fa2(), WU Feng-Shou1
1. China Ship Survey and Design Institute Co.,Ltd.,Shanghai 200063,China 2. College of Geo-Exploration Science and Technology,Jilin University,Changchun 130026,China
Terrestrial heat flow has a high reference value for the evaluation of geothermal resources since it can directly indicate the Earth's internal heat on the surface.However,no high-quality and high-resolution terrestrial heat flow measurements have been conducted in the Songliao Basin due to costly and difficult conventional heat flow measurements based on the drilling technology.Machine learning,as a technology for data analysis,can identify patterns in data and utilize these patterns to automatically calculate unknown data.This study calculated the regional terrestrial heat flow using the machine learning method.Based on the measured data of global terrestrial heat flow and the geological structure data,both the Kriging regression algorithm and the machine learning algorithm were used to calculate the terrestrial heat flow in a known heat flow distribution area,as well as the root mean square error and the correlation coefficient.The machine learning algorithm yielded results with a smaller error and a higher correlation.Then,the terrestrial heat flow in the Songliao Basin was calculated using the machine learning method.As revealed by the calculation results,the terrestrial heat flow is the highest (more than 80 mWm-2) in the Songliao basin and gradually decreases outward in a circular pattern centered on the area between Daqing and Songyuan.The results are highly consistent with the measured results of the regional geothermal gradient,providing a reference for further analysis of the distribution patterns of geothermal resources in the Songliao Basin.Finally,the sensitivity of geological characteristics was analyzed using the Sobol method to quantify the effects of various parameters.This study verifies that the machine learning method has a high research and application value in the calculation of terrestrial heat flow.
Pang X Q, Chen Z M, Chen F J. Discussion on the calculation method of nonlinear variation paleoheat flow stripping simulation[J]. Journal of Daqing Petroleum Institute, 1994, 18(2):9-16.
Wei D P, Shi Y L, Tang M C, et al. Retrieving terrestrial heat flow from meteorological and geothermal data[J]. Chinese Journal of Geophysics, 1992, 35(6):733-739.
Dong W J, Tang M C. Preliminary results of calculating multi-year average soil heat flow using ground temperature data from meteorological stations[J]. Plateau Meteorology, 1992, 11(2):115-125.
[5]
Fox M C, Purucker M E, Olsen N. Inferring magnetic crustal thickness and geothermal heat flux from crustal magnetic field models[R]. Danish Meteorological Institute, 2009.
[6]
Martos Y M, Catalan M, Jordan T A, et al. Heat flux distribution of Antarctica Unveiled[J]. Geophysical Research Letters, 2017, 44(22):11417-11426.
doi: 10.1002/grl.v44.22
Tang H H, Guo L H, Fang Y. Estimation of heat flow in the southeast margin of the Qinghai-Tibet Plateau and correlation analysis with seismic activity[J]. Chinese Journal of Geophysics, 2020, 63(3):1056-1069.
[8]
Goutorbe B, Poort J, Lucazeau F, et al. Global heat flow trends resolved from multiple geological and geophysical proxies[J]. Geophysical Journal International, 2011, 187(3):1405-1419.
doi: 10.1111/j.1365-246X.2011.05228.x
[9]
Rezvanbehbahani S, Stearns L A, Kadivar A, et al. Predicting the geothermal heat flux in Greenland:A machine learning approach[J]. Geophysical Research Letters, 2017, 44(24):12271-12279.
[10]
Lucazeau F. Analysis and mapping of an updated terrestrial heat flow data set[J]. Geochemistry,Geophysics,Geosystems, 2019, 20(8):4001-4024.
doi: 10.1029/2019GC008389
[11]
Haklidir T. Prediction of reservoir temperatures using hydrogeochemical data,Western Anatolia geothermal systems(Turkey):A machine learning approach[J]. Natural Resources Research, 2020, 29(4):1-14.
doi: 10.1007/s11053-020-09627-1
[12]
Lösing M, Ebbing J. Predicting geothermal heat flow in Antarctica with a machine learning approach[J]. Journal of Geophysical Research:Solid Earth, 2021, 126(6):1-16.
[13]
刘卓. 基于变物性约束的重磁界面反演研究与应用[D]. 长春: 吉林大学, 2019.
[13]
Liu Z. Research and application of gravity and magnetic interface inversion based on variable physical property constraints[D]. Changchun: Jilin University, 2019.
Wang K Y, Liu D, Liu J R, et al. Research on crustal structure in Northeast China[J]. Progress in Geophysics, 2015, 30(1):61-69.
[16]
Samuel A. Some studies in machine learning using the game of checkers[J]. IBM Journal of Research and Development, 1959, 3(3):210-229.
doi: 10.1147/rd.33.0210
[17]
Russell S, Norvig P. Artificial intelligence:A modern approach,Third Edition[J]. Artificial Intelligence, 2011, 175:935-937.
doi: 10.1016/j.artint.2011.01.005
[18]
Fox Maule C, Purucker M E, Olsen N. Inferring magnetic crustal thickness and geothermal heat flux from crustal magnetic field models[R]. Danish Meteorological Institute, 2009.
[19]
Amante C, Eakins B W. ETOPO1 1 arc-minute global relief model:Procedures,data sources and analysis[M].National Oceanic and Atmospheric Administration Technical Memorandum,National Environmental Satellite,Data,and Information Service,National Geophysical Data Center, 2009.
[20]
Reguzzoni M, Sampietro D, Sansò F. Global Moho from the combination of the CRUST2.0 model and GOCE data[J]. Geophysical Journal International, 2013, 195:222-237.
doi: 10.1093/gji/ggt247
[21]
Pasyanos M E, Masters T G, Laske G, et al. LITHO1.0:An updated crust and lithospheric model of the Earth[J]. Journal of Geophysical Research:Solid Earth, 2014, 119:2153-2173.
doi: 10.1002/jgrb.v119.3
[22]
Poupinet G, Shapiro N M. Worldwide distribution of ages of the continental lithosphere derived from a global seismic tomographic model[J]. Lithos, 2009, 109(1):125-130.
doi: 10.1016/j.lithos.2008.10.023
[23]
Balmino G, Vales N, Bonvalot S, et al. Spherical harmonic modelling to ultra-high degree of Bouguer and isostatic anomalies[J]. Journal of Geodesy, 2012, 86(7):499-520.
doi: 10.1007/s00190-011-0533-4
[24]
Laske G, Masters G, Ma Z, et al. Update on CRUST1.0 -A1-degree global model of Earth's crust[J]. Geophysical Research Abstracts, 2013,15,2658.
[25]
Kaban M K, Schwintzer P, Reigber C. A new isostatic model of the lithosphere and gravity field[J]. Journal of Geodesy, 2004, 78(6):368-385.
doi: 10.1007/s00190-004-0401-6
[26]
Maus S, Sazonova T, Hemant K, et al. National geophysical data center candidate for the world digital magnetic anomaly map[J]. Geochemistry,Geophysics,Geosystems, 2013, 8(6):1-10.
[27]
Bassin C. The current limits of resolution for surface wave tomography in North America[J]. Eos Transactions American Geophysical Union, 2000,81,F897.
[28]
USGS. Geologic province and thermo-tectonic age maps[M/OL]. https://earthquake.usgs.gov/data/crust/maps.php [2016-09-30].
[29]
Shapiro N M, Ritzwoller M H. Monte-Carlo inversion for a global shear-velocity model of the crust and uppermantle[J]. Geophysical Journal International, 2002, 151(1):88-105.
doi: 10.1046/j.1365-246X.2002.01742.x
[30]
Hartmann J, Moosdorf N. The new global lithological map database GLiM:A representation of rock properties at the Earth surface[J]. Geochemistry,Geophysics,Geosystems, 2012, 13(12):1-37.
doi: 10.1029/2011GC003955
[31]
Coffin M F, Gahagan L M, Lawver L A. Present-day plate boundary digital data compilation[J]. University of Texas Institute for Geophysics Technical Report, 1998,174,5.
[32]
Shapiro N M, Ritzwoller M H. Inferring surface heat flux distributions guided by a global seismic model:Particular application to Antarctica[J]. Earth and Planetary Science Letters, 2004, 223(1):213-224.
doi: 10.1016/j.epsl.2004.04.011
[33]
Gosnold W. The global heat flow database[M/OL]. http://www.heatflow.und.ed-u/index2.html [2016-09-30].
[34]
吴乾蕃. 松辽盆地地热场[J]. 地震研究, 1991, 14(1):31-40.
[34]
Wu Q F. Geothermal field in Songliao basin[J]. Earthquake Research, 1991, 14(1):31-40.
Jiang G Z, Gao P, Rao S, et al. Compilation of earth heat flow data in Chinese Mainland(Fourth Edition)[J]. Chinese Journal of Geophysics, 2016, 59(8):2892-2910.
Liu Y G. Relationship between geothermal field characteristics and oil and gas exploration in Songliao Basin[J]. Petroleum Exploration and Development, 1982(3):26-31.
[37]
He C S, Dong S W, Chen X H, et al. Seismic evidence for plume-induced rifting in the Songliao Basin of Northeast China[J]. Tectonophysics, 2014, 627:171-181.
doi: 10.1016/j.tecto.2013.07.015
Xiao L, Wang F Z, Wang H, et al. Constraints of mantle plume structure on the formation of Songliao basin and Bohai Bay basin[J]. Earth Science-Journal of China University of Geosciences, 2004, 29(3):283-292.
Zhang E H, Jiang C J, Zhang Y G, et al. Discussion on the formation and evolution of deep structure of Xujiaweizi fault depression[J]. Journal of Rock, 2010, 26(1):149-157.
[40]
Sobolo I M. Sensitivity estimates for nonlinear mathematical models[J]. Math. Model. Comput. Exp., 1993, 1(4):407-417.
[41]
Sobolo I M. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates[J]. Math. Comput. Simul., 2001, 55:271-280.
doi: 10.1016/S0378-4754(00)00270-6