Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field

TL;DR

This paper develops a convLSTM-based machine learning model to predict spatio-temporal parameters like saturation and pressure in an oil field, demonstrating promising results in porous media forecasting.

Contribution

It introduces a novel convLSTM architecture tailored for spatio-temporal forecasting in the SACROC oil field, including a comprehensive workflow from data preprocessing to error analysis.

Findings

ConvLSTM models accurately predict saturation and pressure over time.

The approach effectively captures spatio-temporal dynamics in porous media.

The workflow facilitates systematic data handling and model evaluation.

Abstract

A machine learning architecture composed of convolutional long short-term memory (convLSTM) is developed to predict spatio-temporal parameters in the SACROC oil field, Texas, USA. The spatial parameters are recorded at the end of each month for 30 years (360 months), approximately 83% (300 months) of which is used for training and the rest 17% (60 months) is kept for testing. The samples for the convLSTM models are prepared by choosing ten consecutive frames as input and ten consecutive frames shifted forward by one frame as output. Individual models are trained for oil, gas, and water saturations, and pressure using the Nesterov accelerated adaptive moment estimation (Nadam) optimization algorithm. A workflow is provided to comprehend the entire process of data extraction, preprocessing, sample preparation, training, testing of machine learning models, and error analysis. Overall, the convLSTM for spatio-temporal prediction shows promising results in predicting spatio-temporal parameters in porous media.