Machine learning based decline curve analysis for short-term oil production forecast

Abstract

Traditional decline curve analyses (DCAs), both deterministic and probabilistic, use specific models to fit production data for production forecasting. Various decline curve models have been applied for unconventional wells, including the Arps model, stretched exponential model, Duong model, and combined capacitance-resistance model. However, it is not straightforward to determine which model should be used, as multiple models may fit a dataset equally well but provide different forecasts, and hastily selecting a model for probabilistic DCA can underestimate the uncertainty in a production forecast. Data science, machine learning, and artificial intelligence are revolutionizing the oil and gas industry by utilizing computing power more effectively and efficiently. We propose a data-driven approach in this paper to performing short term predictions for unconventional oil production. Two states of the art level models have tested: DeepAR and used Prophet time series analysis on petroleum production data. Compared with the traditional approach using decline curve models, the machine learning approach can be regarded as” model-free” (non-parametric) because the pre-determination of decline curve models is not required. The main goal of this work is to develop and apply neural networks and time series techniques to oil well data without having substantial knowledge regarding the extraction process or physical relationship between the geological and dynamic parameters. For evaluation and verification purpose, The proposed method is applied to a selected well of Midland fields from the USA. By comparing our results, we can infer that both DeepAR and Prophet analysis are useful for gaining a better understanding of the behavior of oil wells, and can mitigate over/underestimates resulting from using a single decline curve model for forecasting. In addition, the proposed approach performs well in spreading model uncertainty to uncertainty in production forecasting; that is, we end up with a forecast which outperforms the standard DCA methods.

Modelling and Forecasting Temporal PM2.5 Concentration Using Ensemble Machine Learning Methods

“…This method works best with data that have 'strong seasonality'. For example, this technique has been used for the forecasting of groundwater levels [33] and variations in oil production [34].…”

Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems

“…1, we decide to use a generalized autoregressive strategy by evolving over all the historical outputs until time t − 1 through the recurrent mapping φ y (.) as ȳt−1 = φ y ( ẏ1:t−1 ), (6) where ȳt−1 ∈ R dy . This generalized auto-regressive strategy can also be applied to z t−1 and u t in (4) to obtain the recurrent latent states and inputs as…”

“…Time series forecasting is a long standing problem in widespread decisionmaking scenarios, for example, dynamic system identification [1,2], prognostic and health management (PHM) of machines [3,4,5], and business demand forecasting [6]. It thus has gained extensive attention from academic and industrial community over decades.…”

Long Short-term Memory (LSTM) Networks for Forecasting Reservoir Performances in Carbon Capture, Utilisation, and Storage (CCUS) Operations

“…Forecasting entails estimating oil, water, and gas production over the life of wells. It enables decision-making for economic evaluation and field development planning (Tadjer et al, 2021).…”