The Fog of War: A Machine Learning Approach to Forecasting Weather on Mars

TL;DR

This paper introduces neural network models to improve forecasting of Martian atmospheric opacity, enhancing energy prediction accuracy for Mars rover operations compared to existing empirical models.

Contribution

The paper presents a novel neural network approach for Martian atmospheric opacity forecasting, outperforming traditional empirical models.

Findings

Neural networks provide more accurate opacity forecasts.

Improved energy availability predictions for Mars rovers.

Enhanced planning capabilities for Mars exploration missions.

Abstract

For over a decade, scientists at NASA's Jet Propulsion Laboratory (JPL) have been recording measurements from the Martian surface as a part of the Mars Exploration Rovers mission. One quantity of interest has been the opacity of Mars's atmosphere for its importance in day-to-day estimations of the amount of power available to the rover from its solar arrays. This paper proposes the use of neural networks as a method for forecasting Martian atmospheric opacity that is more effective than the current empirical model. The more accurate prediction provided by these networks would allow operators at JPL to make more accurate predictions of the amount of energy available to the rover when they plan activities for coming sols.