Forecasting the Weather behind Pa Sak Jolasid Dam using Quantum Machine Learning

Abstract

This paper extends the idea of creating a Quantum Machine Learning classifier and applying it to real weather data from the weather station behind the Pa Sak Jonlasit Dam. A systematic study of classical features and optimizers with different iterations of parametrized circuits is presented. The study of the weather behind the dam is based on weather data from 2016 to 2022 as a training dataset. Classification is one problem that can be effectively solved with quantum gates. There are several types of classifiers in the quantum domain, such as Quantum Support Vector Machine (QSVM) with kernel approximation, Quantum Neural Networks (QNN), and Variational Quantum Classification (VQC). According to the experiments conducted using Qiskit, an open-source software development kit developed by IBM, Quantum Support Vector Machine (QSVM), Quantum Neural Network (QNN), and Variable Quantum Classification (VQC) achieved accuracy 85.3%, 52.1%, and 70.1% respectively. Testing their performance on a test dataset would be interesting, even in these small examples.