Oil production and pressure multimodal forecasting integrating high-frequency production data

Production forecasts (oil, gas, water) are important for the management of petroleum reservoirs. Previous results in the literature indicate the effectiveness of using machine learning models in short-term predictive analysis; however, such models are dependent on a large amount of input data. For example, rates are measured daily in the Brazilian Pre-salt fields. Some measures are high-frequency data (wellhead pressure and temperature, for instance), thus requiring additional treatment so that such time series can be used together by the same forecasting model. However, combining the daily series with an interpolation of the high-frequency series can prevent ML models from learning relevant patterns. This work proposes a multimodal approach in which high-frequency and daily series are treated separately. These series can be in different granularities and the model can take advantage of their particularities. This strategy was validated for a 30-day forward forecast in real Brazilian Pre-salt wells, and the results obtained indicated that the use of multimodal learning brought an improvement in oil production and pressure forecasting.

Recommended citation: Leopoldo André Dutra Lusquino Filho, Rafael de Oliveira Werneck, Pedro Ribeiro Mendes Júnior, Manuel Castro, Eduardo dos Santos Pereira, Renato Moura, Vítor Hugo de Sousa Ferreira, Alexandre Mello Ferreira, Alessandra Davolio Gomes, and Anderson de Rezende Rocha. Oil production and pressure multimodal forecasting integrating high-frequency production data. In IBP, editor, Rio Oil & Gas 2022: Sessões Técnicas Digitais e Presenciais | Technical Sessions (Video Presentations + Technical Papers in PDF), number 308, Rio de Janeiro | Brasil, September 2022.
DOI | Download Paper | Download Bibtex