Classification method of carbonate reservoir welltest interpretation model based on long and short-term memory network

Abstract

The development of carbonate reservoirs is inseparable from the measurement of formation parameters, and well test interpretation techniques are often used to determine these parameters. Determining the carbonate reservoir type according to the shape of the well test interpretation curve will help people better understand the reservoir situation and enable more precise well test interpretation. This research focusing on the well test interpretation of carbonate oil and gas reservoirs combined with the actual data of the mine field and uses deep learning algorithms such as feature value extraction, clustering and neural network training to classify the types of carbonate oil and gas reservoirs. Neural network training is further carried out for different types of carbonate reservoirs, so as to achieve the purpose of identifying reservoir types at the algorithm level.