Application of Support Vector Machines and Genetic Algorithms to Fluid Identification in Offshore Granitic Subduction Hill Reservoirs

YL8 area granite submarine is located in the Songnan low uplift of Qiongdongnan Basin, submarine reservoir fracture development, non-homogeneous strong. Geophysical logging and gas logging do not show a clear pattern of response to the fluid properties of submarine reservoirs, and it is difficult to use logging information to linearly classify granite submarine reservoir fluids in two dimensions. Support Vector Machines (SVM) can map multi-dimensional data into high-dimensional space and construct hyperplanes in high-dimensional space to categorize the samples, which meets the need to incorporate logging curves and mud gas parameters that show complex response relationships with the fluid types of subducted reservoirs into the model.Therefore, in this paper, a support vector machine (GA-SVM) granite subduction reservoir fluid prediction model based on genetic algorithm optimisation is constructed. Firstly, the petrophysical characteristics of different reservoirs in the granite subduction hill were analysed in detail, acquisition and standardisation of logging and mud gas logging multi-dimensional parameters sensitive to reservoir fluids, inputting sensitive parameters into GA-SVM mapping multi-dimensional parameters to higher dimensional space using Gaussian radial kernel functions, using genetic algorithms to perform crossover and mutation operations on the kernel parameter g and the penalty parameter C to obtain the optimal parameter combinations, optimising the number of GA-SVM iterations and model accuracy. The GA-SVM predictions were compared with two other machine learning predictions. As demonstrated through actual case studies in the YL8 area, fluid type recognition compliance rate of 88.2% by GA-SVM, GA-SVM effectively improve the compliance rate of fluid identification in granite subduction reservoirs, provides a new idea for logging interpretation of complex reservoirs in granite subduction reservoirs.