It is essential for firefighters to identify the stages of fire development when conducting the fire emergency response operation. However, at present, the approaches for firefighters to identify the stages of fire development on the fireground mainly rely on subjective observation and judgment to the signs and symptoms changing on-site, which is highly unreliable and ambiguous. Therefore, to enhance firefighters’ situational awareness, a machine learning approach by using Gaussian Mixture Models and Hidden Markov Models (GMM-HMM) to automatically identify the stages of fire development from compartment temperatures is proposed in this paper. To provide enough data samples for unsupervised model training, the CFD-based fire simulation—Fire Dynamics Simulator (FDS)—is applied to generate a large volume of simulated training data. Taking the ISO 9705 fire test room as our case study environment, we collect simulation data under 100 fire scenarios within this room to formulate the recognition model. By using the difference between the fire growth time in terms of the model estimated value and the actual value from HRR to evaluate the accuracy of the recognition, we find that the recognition model indicates an average of 98% accuracy within the 2 min error range in cross-validation, and acceptable performance of recognition are also found from the case examined by the real experimental data.