INDEPENDENT MODEL VALIDATION IS CRITICAL FEEDBACK TO UNDERSTAND WHERE OUR FORECAST MODELS ARE PERFORMING WELL AND WHERE THEY ARE UNRELIABLE. SCIENTIFICALLY VALIDATING SOLAR WIND MODELS IS A NECESSARY GOAL TO IMPROVE THE ACCURACY AND UNDERSTAND WHERE PHYSICS OF THE SYSTEM IS CORRECTLY CAPTURED. IN THIS PROPOSAL WE SEEK TO DEVELOP A REGULAR SET OF STATISTICAL MEASUREMENTS TO EVALUATE SOLAR WIND MODELS THAT ARE: RESOLVED IN TIME NOT BOUND TO A GAUSSIAN DISTRIBUTION ASSUMPTION AND DIRECTLY COMPARABLE BETWEEN MODELS. THESE STATISTICS WILL EMPOWER FORECASTERS AND FUTURE MODEL DEVELOPERS TO FULLY UNDERSTAND WHEN AND HOW ACCURATELY ANY MODEL REPRODUCES THE SOLAR WIND. WE WILL ACHIEVE OUR GOAL THROUGH THE USE OF A SPECIFIC SET OF MACHINE LEARNING (ML) ALGORITHMS: CLUSTER ANALYSIS. CLUSTERING IS THE TECHNIQUE OF IDENTIFYING AND CHARACTERIZING GROUPS OF DATA THAT ALL HAVE SIMILAR BEHAVIOR. THROUGH IDENTIFYING PHYSICALLY SIMILAR GROUPS IN THE MEASURED AND MODELED SOLAR WIND WE CAN MAKE A DIRECT COMPARISON BETWEEN THE MODEL OUTPUT AND DATA. FURTHERMORE THIS TYPE OF ANALYSIS ENABLES AN ACCURATE COMPARISON OF HOW EACH MODEL CAPTURES SPECIFIC STATES OF THE WIND ALLOWING US TO EVALUATE THE MODELS PERFORMANCE AGAINST OTHERS.