Expanding Mars’s Climate Modeling: Interpretable Machine Learning for Modeling Mars Science Laboratory Relative Humidity

Abstract

Abstract For the past several decades, numerous attempts have been made to model the climate of Mars, with extensive studies focusing on the planet’s dynamics and climate. While physical modeling and data assimilation approaches have made significant progress, uncertainties persist in comprehensively capturing the complexities of the Martian climate. We propose a novel approach to Martian climate modeling by leveraging machine-learning techniques that have shown remarkable success in Earth climate modeling. Our study presents a deep neural network designed to model relative humidity in Gale crater, as measured by NASA’s Mars Science Laboratory “Curiosity” rover. By utilizing meteorological variables produced by the Mars Planetary Climate Model, our model accurately predicts relative humidity with a mean error of 3% and an R 2 score of 0.92 over the range of relative humidity compared. Furthermore, we present an approach to predict quantile ranges of relative humidity, catering to applications that require a range of values. To address the challenge of interpretability associated with machine-learning models, we utilize an interpretable model architecture and conduct an in-depth analysis of its decision-making processes. We find that our neural network can model relative humidity at Gale crater using a few meteorological variables, with the monthly mean surface H2O layer, planetary boundary layer height, convective wind speed, and solar zenith angle being the primary contributors. In addition to providing an efficient method for modeling climate variables on Mars, this approach can also be utilized to expand on current data sets by filling spatial and temporal gaps in observations.