Simulated Cosmic Microwave Background maps to detect signatures of primordial features

This dataset contains simulated Cosmic Microwave Background (CMB) temperature and polarisation maps (T, Q, U) generated using:https://github.com/SkyExplain/SkySimulation The maps were simulated using CAMB and healpy under two cosmological models: the standard ΛCDM model and a model featuring an oscillatory template in the primordial power spectrum, motivated by early Universe physics. The feature is parametrised as: P_R(k) = P_{R,0}(k) [1 + A_lin sin(ω_lin k/k* + φ)] where the feature amplitude A_lin and feature frequency ω_lin are varied across the dataset to explore a range of non-standard primordial signatures. Maps are generated at Planck resolution, with the official Planck galactic mask applied and Planck-like noise added. The noise covariance matrix C_ij was estimated via MCMC sampling of Planck-derived asymmetric uncertainties. These maps are used as input to the neural network model selection pipeline available at: https://github.com/SkyExplain/SkyNeuralNets, with trained network weights available at: 10.5281/zenodo.19445671 The interpretability analysis (SHAP maps using https://github.com/skyexplain/SkyInterpret) derived from these maps is available at: 10.5281/zenodo.19445676