Forecast Accuracy Comparison
Production forecasting is a critical activity for oil and gas companies, as it can significantly influence field development planning and the economic evaluation of oil and gas assets. Traditional methods employed for production forecasting, such as numerical simulations and decline curve analysis (DCA) models such as Duong, Fetkovich, MBT, Stretched Exponential, etc., are based on assumptions and require extensive domain knowledge. Moreover, for an unconventional reservoir, the estimation of future oil and gas production is complex due to the heterogeneous nature of formations and dynamic operational events. Due to these complexities, combined with the rapid decline rate of wells, an unconventional well often does not follow the natural trend of the depletion regime.
To overcome these challenges, CSE ProdCast was built. It uses an artificial neural network for predictive modeling that can be used to forecast production from existing and new wells. By leveraging time-series data and learning from the data without making any prior assumptions, CSE ProdCast is able to predict a more "natural response" from reservoirs and be more accurate than traditional forecasting methods. It is also quick and cost-effective and can be extended to build production forecasting models using data from multiple wells which renders the forecast more realistic and accurate. CSE ProdCast is robust enough to incorporate any dynamic changes in operational parameters, such as temperature and pressure, and has the capability to forecast all three phases (oil, gas, and water) unlike traditional methods which only forecast a single phase.
CSE ProdCast pulls time-series data directly from the OSIsoft PI System® utilizing the AF SDK. This data is used to run advanced forecasting algorithms in real-time. The results from the algorithms are fed back to the Data Archive and can be displayed and compared to actual values using any of the off-the-shelf PI visualization tools. CSE ProdCast can be installed on any Windows server where the AF SDK is installed and connectivity exists to the Data Archive. Examples include installing the solution directly on the Data Archive server, a server running other analysis services (e.g., Asset Analytics), or a dedicated server.