Interwell connectivity, an important element in reservoir characterization, especially for water flooding, is used to make decisions for better oil production. The existing methods in literature directly use related data of wells to infer interwell connectivity, but they ignore the influence between different wells. The connection of one well to more than two wells (as is often true in the oil field well pattern) will impact the accuracy of the connectivity analysis. To address this challenge, this paper proposes the Particle Swarm Optimization-based CatBoost for Interwell Connectivity (PSOC4IC) based on relative features to analyze interwell connectivity with the combination of joint mutual information maximization-based denoising sparse autoencoder for inter-feature construction and extraction and PSO-based CatBoost (PSO-CatBoost) for connectivity prediction with high-dimensional noise data. The experimental results show that the PSOC4IC improves analysis accuracy.