大地测量与地球动力学2026，Vol.46Issue(1)：55-62,85,9.DOI:10.14075/j.jgg.2025.02.038
基于集成学习Stacking算法的南极热流预测模型
Antarctic Heat Flow Prediction Model Based on Stacking Algorithm for Ensemble Learning
摘要
Abstract
Heat flow(HF)refers to the heat energy transmitted from the Earth's interior to the sur-face.It can reveal various processes occurring in the deep Earth and information about energy balance.In the Antarctic region,understanding heat flow is of great significance for simulating the dynamic changes of ice sheets.This study employs the Stacking algorithm in machine learning to construct a heat flow prediction model for Antarctica.The model integrates 13 types of geological and geophysical features related to heat flow as observational input data and incorporates six machine learning algo-rithms commonly used for regression prediction problems,namely GBDT,XGBoost,RF,LightG-BM,ET,and MLP,to predict the distribution characteristics of heat flow.The experimental results show that the prediction accuracy of the Stacking model is superior to that of several benchmark mod-els.The new Antarctic heat flow distribution prediction map obtained through this model is more in line with the actual distribution of heat flow in Antarctica compared with the large-scale estimated heat flow distribution maps drawn by traditional methods,demonstrating more excellent performance.关键词
集成学习/Stacking算法/大地热流/南极洲Key words
ensemble learning/Stacking algorithm/heat flow/Antarctica分类
天文与地球科学引用本文复制引用
蔡轶珩,张晓晴,稂时楠,崔祥斌,何彦良,张恒..基于集成学习Stacking算法的南极热流预测模型[J].大地测量与地球动力学,2026,46(1):55-62,85,9.基金项目
国家自然科学基金(42376253,42576289) （42376253,42576289）
国家重点研发计划(2024YFB3908003). （2024YFB3908003）
