Generative AI-driven forecasting of oil production

TL;DR

This paper explores the use of generative AI models, specifically TimeGrad and Informer, for accurate long-term forecasting of oil and water production in multi-well oilfields, emphasizing uncertainty modeling and efficiency.

Contribution

It introduces the application of generative AI techniques, particularly TimeGrad and Informer, to improve long sequence time series forecasting of oil production with enhanced accuracy and efficiency.

Findings

Informer outperforms TimeGrad in forecasting accuracy

Both models closely match ground truth data

Efficient long-term predictions across multiple sites

Abstract

Forecasting oil production from oilfields with multiple wells is an important problem in petroleum and geothermal energy extraction, as well as energy storage technologies. The accuracy of oil forecasts is a critical determinant of economic projections, hydrocarbon reserves estimation, construction of fluid processing facilities, and energy price fluctuations. Leveraging generative AI techniques, we model time series forecasting of oil and water productions across four multi-well sites spanning four decades. Our goal is to effectively model uncertainties and make precise forecasts to inform decision-making processes at the field scale. We utilize an autoregressive model known as TimeGrad and a variant of a transformer architecture named Informer, tailored specifically for forecasting long sequence time series data. Predictions from both TimeGrad and Informer closely align with the ground truth data. The overall performance of the Informer stands out, demonstrating greater efficiency compared to TimeGrad in forecasting oil production rates across all sites.