Forecasting Typhoon Moving Path Using BPNN-Weighted Grey-C3LSP Tuned by Quantum-Neuron-Based Adaptive Support Vector Regression with Nested Local Adiabatic Evolution

Abstract

A novel forecasting approach is composed of BWGC and NGARCH tuned by quantum-neuro-based adaptive support vector regression with nested local adiabatic evolution. Instead of traditionally (globally) adiabatic evolution algorithm for unstructured search, we focus on the structured adiabatic quantum search by nesting a partial search over a reduced set of variables into a global search for solving an optimization problem on adaptive support vector regression (ASVR) yielding an average complexity of order radicN <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">a</sup> , with a < 1. The proposed method is experimentally applied to predicting typhoon moving path even though fewer sampled data are available to work out possibly real-time look-ahead typhoon moving position. Consequently, it yields satisfactory results of forecasting typhoon moving path when comparing with several alternative methods.