Open Access

ARTICLE

Deep Learning-Based Investigation of Multiphase Flow and Heat Transfer in CO₂–Water Enhanced Geothermal Systems

Feng He^*, Rui Tan, Songlian Jiang, Chao Qian, Chengzhong Bu, Benqiang Wang

PetroChina Chuanqing Drilling & Exploration Engineering Co., Ltd., Chengdu, 610051, China

* Corresponding Author: Feng He. Email:

(This article belongs to the Special Issue: Multiphase Fluid Flow Behaviors in Oil, Gas, Water, and Solid Systems during CCUS Processes in Hydrocarbon Reservoirs)

Fluid Dynamics & Materials Processing 2025, 21(10), 2557-2577. https://doi.org/10.32604/fdmp.2025.070186

Received 10 July 2025; Accepted 11 September 2025; Issue published 30 October 2025

Abstract

This study introduces a Transformer-based multimodal fusion framework for simulating multiphase flow and heat transfer in carbon dioxide (CO₂)–water enhanced geothermal systems (EGS). The model integrates geological parameters, thermal gradients, and control schedules to enable fast and accurate prediction of complex reservoir dynamics. The main contributions are: (i) development of a workflow that couples physics-based reservoir simulation with a Transformer neural network architecture, (ii) design of physics-guided loss functions to enforce conservation of mass and energy, (iii) application of the surrogate model to closed-loop optimization using a differential evolution (DE) algorithm, and (iv) incorporation of economic performance metrics, such as net present value (NPV), into decision support. The proposed framework achieves root mean square error (RMSE) of 3–5%, mean absolute error (MAE) below 4%, and coefficients of determination greater than 0.95 across multiple prediction targets, including production rates, pressure distributions, and temperature fields. When compared with recurrent neural network (RNN) baselines such as gated recurrent units (GRU) and long short-term memory networks (LSTM), as well as a physics-informed reduced-order model, the Transformer-based approach demonstrates superior accuracy and computational efficiency. Optimization experiments further show a 15–20% improvement in NPV, highlighting the framework’s potential for real-time forecasting, optimization, and decision-making in geothermal reservoir engineering.

---

Keywords

---