According to research and explorations conducted on mars. It was believed that the planet once supported life. This resulted from some evidence indicating the presence of water and a thick warm atmosphere on
mars in the past. Due to this, man became curious to explore the planet as the red planet is believed to be similar to earth. Many technological tools have evolved with advancements in science and technology, making the entire exploration mission easy. Machine learning standout to be an essential technical tool today that is in use for mars exploration. Although the field is new, little work has been done in
exploring mars' weather patterns for possible habitation of life. This work relied on the strength of machine learning techniques to analyse the mars data obtained from the EMM EMIRS instrument
database. In this work, various techniques such as exploration, pre-processing, model development, and evaluations were performed on the dataset to predict the variation in daily atmospheric temperatures
of mars present within the dataset. Seven machine learning models were developed in this work: Random Forest, Linear regression, SVM, ANN, CNN, Lasso Regression and Decision tree. The
developed models were subjected to hyperparameters fine-tuning their accuracies. Finally, each model was evaluated using RMSE, MAE, and R2 value evaluation techniques. Following the evaluation, random forest outperformed all other six models used in this work with scores as follows: RMSE=1.5525, MSE=2.4105, MAE=1.1939 and R2=0.8283. Finally, the scores obtained were visualised.