Calculating method and system of ultimate recoverable reserves of shale gas reservoirs

Abstract

The invention provides the calculating method and system of the ultimate recoverable reserves of shale gas reservoirs. The method comprises the following steps of S1, acquiring the characteristic dataof the shale gas reservoirs, wherein the characteristic data includes the porosities of the shale gas reservoirs, permeability, a completion method, a drilling parameter, a crack length and flow conductivity; and S2, inputting the characteristic data into a trained machine learning model and acquiring the predicted value of the ultimate recoverable reserves of the shale gas reservoirs. In the invention, known historical data is fully used, the machine learning model is established without any hypotheses, the characteristic data closely related to the ultimate recoverable reserves of the shalegas reservoirs is input into a trained support machine learning model so as to acquire the predicted value of the ultimate recoverable reserves of the shale gas reservoirs, and the acquired predictedvalue accords with the real rule of the shale gas reservoirs so that the assessment result of the ultimate recoverable reserves is real, reliable and accurate.

Description

technical field [0001] The invention relates to the technical field of shale gas exploration, and more particularly, to a method and system for calculating the final recoverable reserves of a shale gas reservoir. Background technique [0002] At present, unconventional natural gas in the world includes shale gas, coalbed methane, and tight gas. The reserves of shale gas resources are equivalent to the sum of coalbed methane and tight gas resources, and their reserves account for about half of the total of the three types of unconventional natural gas. Shale gas is an unconventional natural gas stored in dark shale or high-carbon shale, with typical in-situ accumulation model characteristics. Shale gas reservoir is a kind of organic-rich dark shale or high carbonaceous shale, which has the characteristics of low porosity and ultra-low permeability, and mainly accumulates natural gas in adsorbed or free state. Compared with conventional gas reservoirs, the characteristic of s...

AI Technical Summary

Problems solved by technology

The production decline curve method is only applicable to wells whose production begins to decline, and is not applicable to the calculation of recoverable reserves of fixed production wells that have reached quasi-steady flow but no production decline; for wells whose production begins to decline, this curve fitting method is in It is carried out on the basis of many assumptions. Due to the idealization of the conditions, the results obtained by this method cannot be well applied to the actual production of the oil field, and have no guiding significance for the actual production.

As for the flow model method, since shale gas is an unconventional gas reservoir with low porosity and ultra-low permeability, the pore conditions are very complex, and there are gas slippage effects, adsorption effects, and non-Darcy flow, etc. At present, when establishing the flow model, the flow in the pores is still regarded as Darcy flow, which fundamentally does not conform to the actual law of shale gas reservoirs, and the conclusions drawn naturally have deviations

[0004] To sum up, it can be seen that when evaluating the reserves of shale gas reservoirs through the existing technology, the reuse of historical data is not emphasized, which makes a large amount of data idle. Most of the proposed methods are carried out under assumed ideal conditions, and do not In line with the actual law of shale gas reservoirs, resulting in biased and inaccurate assessment of the ultimate recoverable reserves

Images