<p dir="ltr">The absence or limited availability of operational statistics at general aviation airports restricts airport managers and operators from assessing comprehensive operational data. The traditional manual compilation of operational statistics is labor-intensive and lacks the depth and accuracy to depict a holistic picture of a general aviation airport’s operations. This research developed a reliable and efficient approach to address the problem by providing a comprehensive and versatile flight status identification framework. </p><p dir="ltr">Leveraging the BlueSky flight simulation module, the research can generate a synthetic flight database to emulate real-world general aviation aircraft’s flight scenarios. Two neural network architectures, namely, an RNN-GAN network and a refined Seq2Seq network, were explored to examine their capability to reconstruct flight trajectories. The Seq2Seq network, which demonstrated better performance, was further employed to estimate the simulated aircraft’s different metrics, such as internal mechanical metrics and flight phase. Additionally, this research undertook an array of diverse tailored evaluation techniques to assess the efficacy of flight status predictions and conducted comparative analyses between various configurations. </p><p dir="ltr">Furthermore, the research concluded by discussing the future development of the framework, emphasizing its potential for generalization across various flight data applications and scenarios. The enhanced methodology for collecting operational statistics and the analysis tool will enable airport managers and regulators to better receive a comprehensive view of the airport’s operations, facilitating airport planning and development.</p>