| This thesisexplores the use of machine learning inidentifying nuclear reactor transients. Models were producedusing sixsupervised learning techniques. Due to the nature of nuclear power plants, synthetic data was gathered using a reactor simulator. Data was collected on fourdifferent transients andonnormal operations. Transientswere examinedusing a combinationofcore life and poweroutput.The Python TPOT package was used to preprocess data, as well as build and validate models. The results of the test showed that the decision tree model produced the best results with an accuracy of 98.6%, as well as high scoreson the other validation measurements. The other models also performed well with scores in the mid-90s.These high results show that machine learninghas potentialto be a tool to assist reactor operators in diagnosing transients earlier and more accuratelyandcouldaid in accident mitigation and prevention. Keywords:Machine Learning, Reactor Transients, Python, TPOT |