Reservoir Modeling Assisted with Knowledge-Enhanced Large Language Models
Open Access
- 25 September 2026
- Vol. 14 (19) , 3076
Abstract
Reservoir simulation is an important technique to characterize subsurface fluid flow and to support reservoir development and production optimization. Conventional reservoir modeling requires engineers to extract model-relevant information from heterogeneous data, organize the information into predefined formats, and generate simulator-specific input files through professional software. Constructing and iteratively updating such models can often take months of effort due to the high modeling complexity. Large language models (LLMs) offer a potential alternative by translating modeling requirements into simulator input instructions through natural language modeling instructions. However, proprietary reservoir simulators are poorly represented in public training corpora, and their keyword systems may differ substantially from those of widely documented commercial simulators. This study addresses these challenges using the Compositional Advanced Simulation System (COMPASS), an in-house reservoir simulator for unconventional resources, as the target simulator. The proposed knowledge-enhanced LLM framework combines retrieval-augmented generation (RAG) with schema-constrained tool calling to support well-control instruction generation. On the 50-task RECURRENT benchmark using DeepSeek-V4.1-Flash, the four generation strategies achieved average accuracies of 0.67%, 74%, 98%, and 100% for Strategy I (zero-shot), Strategy II (RAG), Strategy III (schema-constrained tool calling), and Strategy IV (RAG combined with schema-constrained tool calling), respectively. Additional experiments with different base LLMs showed accuracies ranging from 92.0% to 100.0%. These results demonstrate that combining enterprise-domain knowledge retrieval with schema-constrained output generation can substantially improve the reliability of LLM-based generation for proprietary reservoir simulation software.Keywords
Funding Information
- SINOPEC Exploration and Production Research Institute
This publication has 15 references indexed in Scilit:
- Temperature Field Prediction of Glulam Timber Connections Under Fire Hazard: A DeepONet-Based ApproachFire, 2025
- OpenFOAMGPT: A retrieval-augmented large language model (LLM) agent for OpenFOAM-based computational fluid dynamicsPhysics of Fluids, 2025
- Artificial intelligence in geoenergy: bridging petroleum engineering and future-oriented applicationsJournal of Petroleum Exploration and Production Technology, 2025
- Construction and preliminary application of large language model for reservoir performance analysisPetroleum Exploration and Development, 2024
- Research status and application of artificial intelligence large models in the oil and gas industryPetroleum Exploration and Development, 2024
- TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIsIntelligent Computing, 2024
- Competition-level code generation with AlphaCodeScience, 2022
- Dense Passage Retrieval for Open-Domain Question Answering2020
- History matching time-lapse seismic data using the ensemble Kalman filter with multiple data assimilationsComputational Geosciences, 2012
- Recent progress on reservoir history matching: a reviewComputational Geosciences, 2010