The most reliable archive of atmospheric CO₂ information comprises ice core records spanning the last 800 ka (thousand years ago). The connection between temperature and greenhouse gases, as deduced from ice core records, may help better simulate CO₂ variations. This research aimed to explore the model methods to precisely predict the atmospheric CO₂ concentrations and fill the CO₂ data gaps with CH₄ concentration and temperature proxies (δD and δ¹⁸O) from Antarctica ice cores, employing Artificial Neural Network (ANN) and Wavelet Transform (WT) techniques. This study was divided into three sections to examine various timescales and resolutions. First, coarse-resolution CO₂ records from the Vostok and EPICA Dronning Maud Land cores from 70–120 ka were used. Second, the models were applied to the Dome Fuji core for 9–120 ka. Finally, a high-resolution West Antarctic Ice Sheet (WAIS) Divide ice core record, focusing on the 9–70 ka, was employed. The results showed that between 70–120 ka, the hybrid method surpasses the traditional ANN approach. The hybrid method maintained superior performance in the last phase by utilizing high-resolution WAIS record. The results indicated improved accuracy (r=0.98), reinforcing the notion that hybrid methods yield better outcomes than those relying solely on AI methods.