Efficient recovery of petroleum from reservoir and optimized well design and operation through well-based production and automated decline curve analysis

Abstract

Embodiments are directed to automatically detecting an event in a production curve, generating a production estimate using a quantile regression and to performing a probabilistic decline curve analysis. In one scenario, a computer system identifies a candidate break point in a production decline curve which represents a decline in material production at a well. The computer system identifies one trend for the production decline curve occurring before the candidate break point and identifies a second trend for the production decline curve occurring after the candidate break point. The computer system calculates the difference between the first material production decline estimate and the second material production decline estimate and identifies the candidate break points where the difference between the first material production decline estimate and the second material production decline estimate is beyond a threshold value. Identifying the candidate break points allows generation of accurate material production forecasts for the well.