Data underlying the publication: Multi-Objective Optimization of Energy Efficiency and Geomechanical Safety in High-Temperature Aquifer Thermal Energy Storage (HT-ATES) Systems Based on Coupled Thermo-Hydro-Mechanical (THM) Analysis

This repository contains the complete code and dataset for a multi-objective optimization framework developed for the design of High-Temperature Aquifer Thermal Energy Storage (HT-ATES) systems. The research focuses on achieving a balanced design that enhances energy production while minimizing geomechanical risks. Our approach involves building surrogate models using XGBoost to approximate high-fidelity THM simulation outputs and integrating these models with a NSGA-II based optimization algorithm. This framework efficiently explores the trade-offs among competing objectives, enabling the identification of optimal design configurations. The implementation is done in Python and leverages libraries such as pymoo (0.6.1.3), XGBoost (2.1.3), and scikit-learn (1.2.2).

本仓库收录了为高温含水层热能储存（High-Temperature Aquifer Thermal Energy Storage, HT-ATES）系统设计所开发的多目标优化框架的完整代码与数据集。本研究旨在实现兼顾提升能源产出与最小化地质力学风险的均衡设计方案。我们的研究方案采用XGBoost构建代理模型，以近似高保真热-水-力学（Thermal-Hydraulic-Mechanical, THM）仿真输出结果，并将此类代理模型与基于NSGA-II的优化算法相集成。该框架可高效探索多冲突目标间的权衡关系，助力最优设计构型的筛选与确定。本框架基于Python语言实现，并依赖pymoo（0.6.1.3）、XGBoost（2.1.3）与scikit-learn（1.2.2）等开源工具库。