Designing a Quantum Annealing-Based Method for Optimizing Backpropagation Neural Networks in Greenhouse Gas Emissions Prediction

Greenhouse gas emissions prediction, whether at a macroscopic scale or through building energy demand, commonly employs Backpropagation Neural Network (BPNN) models. These models often encounter issues like extended training durations and difficulties in configuring the optimal number of hidden layers and neurons. Achieving a balance between the complexity of the model and its ability to generalize effectively is essential for creating models that are both efficient and effective. Current approaches to optimizing BPNN structures predominantly utilize classical optimization techniques, often focusing on either the number of hidden layers or the number of neurons. In this paper, we propose a conceptual framework that leverages quantum annealing to optimize BPNN models for GHG emissions prediction. The method is structured in three stages: (1) optimizing the number of hidden layers, (2) optimizing the number of neurons in each layer, and (3) performing neuron pruning optimization. This study focuses on the theoretical design and methodology of the proposed approach, emphasizing its potential to integrate classical and quantum computing paradigms to achieve superior optimization outcomes.