Metamorphic testing seeks to validate software in the absence of test oracles. Our application domain is ocean system modeling, where test oracles rarely exist, but where symmetries of the simulated physical systems are known. The input data set is big owing to the requirements of the application domain. This short paper presents work in progress for the automated generation of metamorphic test scenarios using machine learning. We extended our previously proposed method ~cite{Hiremath2020} to identify better Metamorphic relations with reduced computational complexity. We represent metamorphic testing and assume identity map to be the first metamorphic relation. We construct a cost function that minimizes for identifying a metamorphic relation that is orthogonal to previously found metamorphic relations and penalize for the identity map. We use machine leaning algorithm to identify all possible metamorphic relations minimizing the defined cost function. We propose applying dimensionality reduction techniques to identify attributes in the input which have high variance among the identified metamorphic relations. We apply mutation on these selected attributes to identify distinct metamorphic relations with reduced computational complexity.  For experimental evaluation, we subject the two implementations of an ocean-modeling application to the proposed method to present the use of metamorphic relations to test the implementations of the applications.