AI/machine learning

Automated Production Forecasting Uses Novel Machine-Learning-Based Approach

Supervised learning was used to develop an ensemble of models that account for historical production data, geolocation parameters, and completion parameters to forecast production behavior of oil and gas wells.

<b>Fig. 1—</b>Basins included in model training.
Source: Paper SPE 212723

Production forecasting and hydrocarbon reserve estimation play a major role in production planning and field evaluation. Traditional methods of production forecasting use historical production data and do not account for completion and geolocation attributes that limit their prediction ability, especially for wells with a short production history. This study presents a novel data-driven approach that accounts for the completion and geolocation parameters of a well along with its historical production data to forecast production.

This work used supervised learning to develop an ensemble of machine-learning (ML) -based models to forecast production behavior of oil and gas wells. The developed models account for historical production data, geolocation parameters, and completion parameters as features. The data set used to create the models consists of publicly available data from 80,000 unconventional wells in North America (Fig. 1). The developed models are rigorously tested against 5% of the original data set. The models are systematically studied and compared against traditional forecasting techniques.

The created ensemble of models was tested by forecasting the production of 3,700 wells, and the obtained results were compared against real production data. The models appear to clearly capture the natural decline trend of the produced hydrocarbon. In cases where the natural decline of the well has been temporarily modified, possibly because of operations, the production during other periods of the time series matches the prediction. This indicates that, unlike in traditional methods, such changes don’t adversely affect the forecasting ability of this method.

The study includes a systematic investigation and comparison of the forecast from the developed model with the forecast from a traditional method. The comparison revealed that, for short-production history wells (available production data from 2 to 12 months), the error rate in the predicted production behavior from traditional methods was higher when compared with the developed method. As the quantity of historical production data increases, the forecasting ability of traditional methods improves. By comparison, the decline from the developed method matches the real production data for both short- and long-production history wells and clearly outperforms the traditional methods based on blind tests.

Find the complete paper here.