This research presents a novel approach to modeling Spark Ignition (SI) engines by integrating deep learning methodologies with Design of Experiments (DOE) principles. Traditional SI engine modeling often relies on complex physical equations or empirical correlations, which can be computationally intensive and may struggle to capture the full spectrum of engine behavior under varying operating conditions. This study aims to overcome these limitations by developing a data-driven SI engine model capable of accurately predicting performance and emissions characteristics. A comprehensive DOE framework will be employed to systematically generate a robust dataset encompassing a wide range of engine input parameters (e.g., engine speed, load, spark timing, air-fuel ratio). This meticulously curated dataset will then be used to train and validate various deep learning architectures, including but not limited to Artificial Neural Networks (ANNs) and Recurrent Neural Networks (RNNs) or Convolutional Neural Networks (CNNs) depending on the nature of the input features.