CLOUD COMPUTATION OF NONANTICIPATIVE ANALOGS FOR HEAT/COLD WAVES TELECONNECTIONS
Dmytro Zubov · DOAJ (DOAJ: Directory of Open Access Journals) · 2015
In this original research work, a nonanticipative analog method is used for the long-term forecast of the air temperature extremes for specifically located places. Arguments of forecast models are datasets from around the world, which reflects the concept of teleconnections. Presented approach is more useful than current methods for predicting extreme values because it does not require the estimation of a probability distribution from scarce observations. Up to 26% of all extremes are specifically predicted. The methodology has 100% accuracy with respect to the sign of predicted and actual values. Forecast models are designed in the Microsoft Windows Azure public cloud.