Data-driven models for production forecasting and decision supporting in petroleum reservoirs

2025-08-21

AI Summary

In petroleum reservoir engineering, robust, long-term production forecasting from limited wellhead data (e.g., rates and pressures) remains challenging due to poor adaptability to concept drift and weak model generalizability. This paper proposes a geology- and fluid-property-agnostic, data-driven forecasting framework integrating supervised learning—including regression models and neural networks—to systematically optimize concept drift mitigation strategies, retraining frequency, and observational window design. Evaluated on both the UNISIM III synthetic benchmark and real-world deepwater pre-salt reservoir data from Brazil, the framework demonstrates strong adaptability and rapid responsiveness under dynamic reservoir conditions. The approach enables early anomaly detection, production-injection parameter optimization, and probabilistic impact analysis—thereby significantly enhancing operational decision-making efficiency and ultimate oil recovery.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: Learning & Optimization for ROB
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Forecasting production reliably and anticipating changes in the behavior of rock-fluid systems are the main challenges in petroleum reservoir engineering. This project proposes to deal with this problem through a data-driven approach and using machine learning methods. The objective is to develop a methodology to forecast production parameters based on simple data as produced and injected volumes and, eventually, gauges located in wells, without depending on information from geological models, fluid properties or details of well completions and flow systems. Initially, we performed relevance analyses of the production and injection variables, as well as conditioning the data to suit the problem. As reservoir conditions change over time, concept drift is a priority concern and require special attention to those observation windows and the periodicity of retraining, which are also objects of study. For the production forecasts, we study supervised learning methods, such as those based on regressions and Neural Networks, to define the most suitable for our application in terms of performance and complexity. In a first step, we evaluate the methodology using synthetic data generated from the UNISIM III compositional simulation model. Next, we applied it to cases of real plays in the Brazilian pre-salt. The expected result is the design of a reliable predictor for reproducing reservoir dynamics, with rapid response, capability of dealing with practical difficulties such as restrictions in wells and processing units, and that can be used in actions to support reservoir management, including the anticipation of deleterious behaviors, optimization of production and injection parameters and the analysis of the effects of probabilistic events, aiming to maximize oil recovery.

Problem

• Forecasting petroleum reservoir production reliably using data-driven methods
• Developing machine learning models without geological or fluid property data
• Addressing concept drift and optimizing production parameters for oil recovery

Innovation

• Machine learning for production forecasting
• Data-driven approach without geological models
• Handling concept drift with retraining strategies