Distance correlation is a new measure of relationships between random variables introduced by Szekely et al (2007). Distance correlation is determined by the distances over all pairs of points while Pearson correlation is determined by the distance between each point and mean. Therefore, distance correlation has properties of a true dependence measure. In this thesis, we build 6 best models for 6 types of crop (barley, canola, flax, oats, pea and spring wheat) in Regina, Saskatchewan by using distance correlation. Despite the complexity of other factors, we show how temperature and precipitation affect crop yield in the Canadian growing season from April to September. Equipped with this information, we are able to estimate the future viability as well as the supply of crops in Canada in response to climate change.