Quantum Machine Learning (QML) model for predicting localized temperature variations

[naghul30]

Greeting!!
We (@ManjulaGandhi, @sgayathridevi, @ajithram2003,@mohn1512 and @naghul30 ,aim to implement a Quantum Machine Learning (QML) model for predicting localized temperature variations, inspired by recent advancements in quantum-enhanced predictive modeling. Specifically, we will construct a quantum-classical hybrid pipeline leveraging Quantum Support Vector Machines (QSVM) and Quantum Neural Networks (QNN) to analyze weather data and forecast temperature variations.

Our approach involves utilizing historical meteorological data (temperature, humidity, wind speed, air pressure, solar radiation) and exploring how QML algorithms can improve prediction accuracy compared to classical machine learning techniques. The implementation will be carried out using IBM Qiskit, with performance evaluated using standard metrics like MAE, RMSE, and R-squared.

The attached proposal contains a detailed plan and implementation approach. Please refer to it:
🔗 Predicting Localized Temperature Variations Using Quantum Machine Learning

Additionally, our approach is aligned with recent research in the field:
📄 Potential of Quantum Scientific Machine Learning Applied to Weather Modelling – This paper explores how quantum machine learning can enhance weather prediction by leveraging quantum-enhanced computational techniques.

Would love to hear feedback and explore possible collaborations for implementation on Classiq’s platform. Looking forward to your insights!

[TomerGoldfriend]

Thank you @naghul30 , for which purpose will you need to use IBM Qiskit? we accept contributions that leverage high-level modeling of quantum algorithms using Classiq.
In addition, the paper you have mentioned seems unrelated to QML.

Finally, note that we already have several QSVM examples in our repository: qsvm, qsvm_pauli_feature_map, and an advance applicative example for credit fraud detection. We also have several examples of Quantum Neural Networks. Please specify how your implementation will differ from those.