Flood Prediction Using Classical and Quantum Machine Learning Models

TL;DR

This paper addresses the challenge of flood forecasting under climate variability by integrating classical and quantum machine learning in a hybrid framework and evaluating it on daily floods along the Wupper River in 2023. It compares a broad suite of models—from SVM, KNN, and AR to Adaboost, QBoost, QSVC_ML, and quantum autoregressive neural networks—focusing on training time, accuracy, and scalability. Key findings show that while some classical models achieve high accuracy with fast training, quantum models offer competitive performances in classification and potential gains in efficiency, though results are mixed for regression tasks. The work demonstrates the practical potential of quantum technologies for climate-adaptation applications and outlines a path toward real-time, data-fusion–driven flood forecasting with hybrid quantum-classical architectures.

Abstract

This study investigates the potential of quantum machine learning to improve flood forecasting we focus on daily flood events along Germany's Wupper River in 2023 our approach combines classical machine learning techniques with QML techniques this hybrid model leverages quantum properties like superposition and entanglement to achieve better accuracy and efficiency classical and QML models are compared based on training time accuracy and scalability results show that QML models offer competitive training times and improved prediction accuracy this research signifies a step towards utilizing quantum technologies for climate change adaptation we emphasize collaboration and continuous innovation to implement this model in real-world flood management ultimately enhancing global resilience against floods

Figures (11)

• Figure 1: Learning Curve for SVM Model
• Figure 2: Distribution of Flood Events
• Figure 3: Time Series of Water Level
• Figure 4: Seasonal Patterns in River Data
• Figure 5: Time Series of Weather Data