With the continuous growth in global population and productivity, the demand for natural gas, the cleanest fossil fuel, is expected to increase significantly. Accurate daily gas production forecasting of shale and sandstone reservoirs ensures a reliable gas supply. However, the complex and non-linear gas data (reservoir and production data) makes this difficult. To address these challenges, we propose a novel model named TimeNet, which utilizes a mix of convolutional neural networks (CNN), bidirectional gated recurrent units (BiGRU), attention mechanisms (AM), and Time2Vec. Time2Vec is integrated to automatically capture important complex and non-linear temporal information and mitigate burdensome time series pre-processing. The CNN layer extracts spatial features influencing gas production, while the BiGRU captures high-level temporal features and irregular trends in the time series data. The AM helps in understanding embedded information for accurate learning. Each component of the TimeNet model serves a distinct function in the prediction task, optimizing its strengths. Testing on two real-world datasets from the Fenchuganj conventional sandstone gas field and the Marcellus shale gas field confirms the proposed model's effectiveness. Comparative analysis demonstrates the superior performance of the proposed model on the two datasets, exhibiting an of 97.25 % and 97.57 % in shale and sandstone gas, respectively.