QGAPHEnsemble : Combining Hybrid QLSTM Network Ensemble via Adaptive Weighting for Short Term Weather Forecasting

TL;DR

This work tackles short-term weather forecasting by addressing the limitations of statistical models that assume data independence. It introduces two hybrid quantum ensemble approaches, GenHybQLSTM and BO-QEnsemble, which combine QLSTM base models with adaptive weighting and metaheuristic hyperparameter optimization (QGA-PSO and Bayesian optimization). On Ottawa hourly data, BO-QEnsemble achieves the best performance, with a $MAPE$ of $0.91$, outperforming GenHybQLSTM ($0.92$) and a standalone QLSTM ($1.12$). The results demonstrate that integrating quantum-inspired models with Bayesian optimization and adaptive ensembling yields robust, accurate short-term forecasts and has potential applicability to other regions and domains.

Abstract

Accurate weather forecasting holds significant importance, serving as a crucial tool for decision-making in various industrial sectors. The limitations of statistical models, assuming independence among data points, highlight the need for advanced methodologies. The correlation between meteorological variables necessitate models capable of capturing complex dependencies. This research highlights the practical efficacy of employing advanced machine learning techniques proposing GenHybQLSTM and BO-QEnsemble architecture based on adaptive weight adjustment strategy. Through comprehensive hyper-parameter optimization using hybrid quantum genetic particle swarm optimisation algorithm and Bayesian Optimization, our model demonstrates a substantial improvement in the accuracy and reliability of meteorological predictions through the assessment of performance metrics such as MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Prediction Error). The paper highlights the importance of optimized ensemble techniques to improve the performance the given weather forecasting task.

Figures (9)

• Figure 1: QLSTM architecture (Variational Quantum Circuits)
• Figure 2: Quantum Genetic-Particle Swarm Algorithm Based QLSTM network ensemble architecture (GenHybQLSTM Ensemble)
• Figure 3: Flowchart of HybQLSTM Ensemble
• Figure 4: Bayesian based nested optimised QLSTM network ensemble architecture (BO-QEnsemble)
• Figure 5: Flowchart of BO-QEnsemble