This goal of this proposal is to develop advanced techniques to calculate accurate and computationally efficient photometric redshift distance estimators, and to mitigate photometric uncertainties and systematics on clustering measures for galaxies found in large numbers in current and upcoming surveys. The computer codes will incorporate machine learning techniques with a combination of supervised and unsupervised learning algorithms. The methods developed will be applicable to the massive surveys to be undertaken by the future Large Synoptic Survey Telescope, which will, among other things, place precise constraints on Dark Energy.
Broader impacts of the work include training of a postdoc, a graduate student, and undergraduate students, and development of a course in Data Science to be available on line. All computational tools developed will be made available to the general astronomical community.
