For shale oil reservoirs in the Jimusar sag of Junggar Basin, the fracturing treatments are challenged by poor prediction accuracy and difficulty in parameter optimization. This paper presents a fracturing parameter intelligent optimization technique for shale oil reservoirs and verifies it by field application. A self-governing database capable of automatic capture, storage, call and analysis is established. With this database, 22 geological and engineering variables are selected for correlation analysis. A separated fracturing effect prediction model is proposed, with the fracturing learning curve decomposed into two parts: (1) overall trend, which is predicted by the algorithm combining the convolutional neural network with the characteristics of local connection and parameter sharing and the gated recurrent unit that can solve the gradient disappearance; and (2) local fluctuation, which is predicted by integrating the adaptive boosting algorithm to dynamically adjust the random forest weight. A strategy gradient-genetic-particle swarm algorithm is designed, which can adaptively adjust the inertia weights and learning factors in the iterative process, significantly improving the optimization ability of the optimization strategy. The fracturing effect prediction and optimization strategy are combined to realize the intelligent optimization of fracturing parameters. The field application verifies that the proposed technique significantly improves the fracturing effects of oil wells, and it has good practicability.

Based on the analyses of the core, cast thin section, physical property, CT, wireline loggings, well tests and seismic data, taking the Lower Cretaceous Yamama Formation in Oilfield A of the Central Arabian Basin as an example, the sedimentation and diagenesis characteristics and favorable reservoir distribution in semi-restricted carbonate ramp are clarified. The results show that semi-restricted carbonate ramp is enriched with Algae, Benthic foraminifera, Bivalve, Bacinella, and peloids, and is characterized by diverse low-energy and shallow-water lithofacies. The depositional environment of the Yamama Formation at early stage is dominated by open shelf, and then is dominated by large scale lagoon, locally being grain shoal, patchy reef, back shoal and tidal flat. There are three sequences in the Yamama Formation, namely I, II, and III, from bottom to top. During the regression cycle, the sequence I is dominated by cementation, the sequence II by dissolution, and the sequence III by alternating cementation and dissolution. The reservoirs are composed of packstone, wackstone and bindstone, with varying lithological sequence laterally which is difficult to be correlated. The reservoirs are porous, with the space contributed by micropores, moldic pores, and skeletal pores, as well as less primary intergranular pores, corresponding to medium- and micro-throats. The physical properties generally exhibit low to medium porosity, and low to ultra-low permeability. The medium-high permeability reservoirs are underdeveloped. It is found that the development of favorable reservoir in semi-restricted carbonate ramp are controlled by high-energy sedimentation locally, soluble bioclastic enrichment, and intense dissolution. Local high-energy grain shoals and patchy reef contain primary intergranular pores with no intense cementation, and they are important facies of favorable reservoirs in semi-restricted carbonate ramp. Low- to medium-energy facies such as lagoon and back shoal are rich in soluble bioclastics such as Algae and Bacinella. The bioclastics were intensely dissolved, forming a large number of moldic pores and skeletal pores, which effectively improved the reservoir physical properties, thus facilitating the formation of large-scale favorable reservoirs. The favorable reservoirs of the Yamama Formation in Oilfield A are mainly distributed in the north-central anticline axis of YA member and YB member.