地球与行星物理论评（中英文）2026，Vol.57Issue(2)：177-190,14.DOI:10.19975/j.dqyxx.2025-017
基于深度神经网络的南极洲大地热流预测
Prediction of geothermal heat flow in Antarctica based on deep neural network
摘要
Abstract
The Antarctic ice sheet plays an increasingly significant regulating role in the global climate system,where geothermal heat flow(GHF)serves as a critical indicator of basal thermal conditions.Understanding its spa-tial distribution is essential for studying its dynamic evolution.Current GHF measurements in Antarctica remain limited to merely 52 data points due to extreme cold geological conditions and prohibitive drilling costs.Existing GHF estimates based on geological and geophysical data exhibit substantial uncertainties and fail to account for non-linear heat transfer processes in the bedrock.Deep learning algorithms demonstrate superior predictive capabilities for sparse data interpolation by capturing coupled relationships between GHF and multi-source data features.We develop a deep neural network(DNN)integrated with a high-dimensional uncertainty quantification framework to predict Antarctic GHF distribution.Utilizing over 4000 global GHF observations and 22 geological and geophysi-cal features(including crustal thickness,gravity/magnetic anomalies,and Moho depth)as training data,we validate the model against known GHF points in Australia and Antarctica.The uncertainty quantification method reorga-nizes the training dataset through correlation,sensitivity,and principal component analysis,combined with DNN model to determine optimal GHF distribution.Prediction results reveal the GHF range of 24-103 mW/m2 with a mean value of 60.1 mW/m2,showing a 10.05%error relative to measured data.The Gamburtsev Subglacial Moun-tains exhibit significant high GHF anomalies(50-74 mW/m2).Uncertainty quantification confirms high confid-ence levels for these GHF predictions.Our model successfully interprets spatial heterogeneity characteristics of Antarctic crustal thermal structure,and the prediction results can be further applied to model Antarctic-scale ice sheet dynamics or thermodynamics,provide reliable data support for studies on ice sheet motion and subglacial lake distribution.关键词
深度神经网络/大地热流/南极洲/不确定性量化Key words
deep neural network/geothermal heat flow/Antarctica/uncertainty quantification分类
天文与地球科学引用本文复制引用
初东方,范晓鹏,李静,白利舸,王卓,郭井学..基于深度神经网络的南极洲大地热流预测[J].地球与行星物理论评（中英文）,2026,57(2):177-190,14.基金项目
吉林省教育厅重大项目:季节性冻融过程黑土地关键参数监测研究(JJKH20241295KJ) （JJKH20241295KJ）
地球信息探测仪器教育部重点实验室(吉林大学)专项经费课题:寒区中深层同轴换热器传热机理与地球物理反演研究(GEIOF20230201)Supported by the Key Natural Science Program of Jilin Provincial Education Department(Grant No.JJKH20241295KJ)and the Special Fund of Key Laboratory of Geoghysical Exploration Equipment,Ministry of Education(Jilin University)(Grant No.GEIOF20230201) （吉林大学）
