Space Apps Challenge 2018

Missions to the planet Mars need a power source. One of the most compatible sources is photovoltaic system. Because photovoltaic systems are based on exploiting energy from the sun, solar radiation intensity should be known for design. In this study, feed-forward back-propagation artificial neural network(ANN) was used to predict solar radiation according to longitude, latitude, time of the day, temperature, altitude, pressure, amount of dust and volume mixing ratio of water ice clouds. Data used in the model was obtained from Mars Climate Database. Fitness between predicted and actual values of solar radiation indicates that feed-forward back-propagation ANN was an accurate method for prediction compared to other methods. The minimum correlation coefficient for testing the network was 0.97. This model was used to predict mean solar radiation and mean temperature for every location on Mars and then the data was presented on Mars maps in order to determine the best location for harvesting energy from the sun by using photovoltaic power systems. The radiation-temperature belt on Mars was decided to be between latitudes 20°S and 15°N.