Forecasting Smart Well Production via Deep Learning and Data Driven Optimization

Abstract

As smart well technology is increasingly being adopted in oilfield development projects, the need to optimize controls emerged in order to justify its higher initial investment by considerably increasing net present value. While there are numerous methodologies to achieve this goal, a common fact in all is the need for a great number of computationally expensive reservoir simulations, hindering extensive optimizations. This paper proposes the use of deep learning algorithms in proxy models, in order to accurately replicate the behavior of the simulator by forecasting production based on previous data. Thus, a smaller number of simulations are required for a training dataset, and the proxy can then be used in lieu of the simulator for optimization purposes. Other benefits in the use of the proposed methodology include the gathering of insights on production, as problems might be occurring if measured production noticeably deviates from the forecast. Two case studies were done, and the results indicate that a Long Short-Term Memory Network-based proxy is able to forecast production with a remarkably low error, validating the methodology and supporting its use.

Smart Oil Field Management System Using Evolutionary Intelligence

“…Calvette et al [18] used a Long Short-Term Memory (LSTM) neural network to build a proxy to forecast smart wells production, taking advantage of a large amount of data available in smart oilfields to minimize the use of computationally expensive simulations. It was tested in a simple synthetic box reservoir and a modified version of the PUNQ-S3 reservoir, achieving low errors in both cases.…”

“…In recent studies of ICV [10], [17], [18], [19], methodologies for optimal valves placement joint with ICV optimization were created, presenting a greater potential for actuation. Those approaches reduced the search space of the optimized solution by focusing the control valve in previously determined valve positions, which results in a guaranteed converge of the methodology but not necessarily an optimal global result.…”

Optimized ANFIS Model Using Aquila Optimizer for Oil Production Forecasting

“…Abdullayeva et al [38] established a hybrid model based on the integration of a Convolutional Neural Network (CNN) and LSTM networks, called CNN-LSTM, to forecast the oil production accurately. Calvette et al [39] implemented a deep learning algorithm in a proxy model to precisely duplicate the simulator by predicting the history data of production. Fan et al [1] proposed a hybrid model by incorporating the ARIMA model and LSTM to consider the impact of manual operation and assess the benefit of linearity and nonlinearity.…”