Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On the impact of key design aspects in simulated Hybrid Quantum Neural Networks for Earth Observation

Lorenzo Papa, Alessandro Sebastianelli, Gabriele Meoni, Irene Amerini

TL;DR

This research investigates through three cases of study fundamental aspects of hybrid quantum machine models for EO tasks aiming to provide a solid groundwork for future research studies towards more adequate simulations and looking at the post-NISQ era.

Abstract

Quantum computing has introduced novel perspectives for tackling and improving machine learning tasks. Moreover, the integration of quantum technologies together with well-known deep learning (DL) architectures has emerged as a potential research trend gaining attraction across various domains, such as Earth Observation (EO) and many other research fields. However, prior related works in EO literature have mainly focused on convolutional architectural advancements, leaving several essential topics unexplored. Consequently, this research investigates through three cases of study fundamental aspects of hybrid quantum machine models for EO tasks aiming to provide a solid groundwork for future research studies towards more adequate simulations and looking at the post-NISQ era. More in detail, we firstly (1) investigate how different quantum libraries behave when training hybrid quantum models, assessing their computational efficiency and effectiveness. Secondly, (2) we analyze the stability/sensitivity to initialization values (i.e., seed values) in both traditional model and quantum-enhanced counterparts. Finally, (3) we explore the benefits of hybrid quantum attention-based models in EO applications, examining how integrating quantum circuits into ViTs can improve model performance.

On the impact of key design aspects in simulated Hybrid Quantum Neural Networks for Earth Observation

TL;DR

This research investigates through three cases of study fundamental aspects of hybrid quantum machine models for EO tasks aiming to provide a solid groundwork for future research studies towards more adequate simulations and looking at the post-NISQ era.

Abstract

Quantum computing has introduced novel perspectives for tackling and improving machine learning tasks. Moreover, the integration of quantum technologies together with well-known deep learning (DL) architectures has emerged as a potential research trend gaining attraction across various domains, such as Earth Observation (EO) and many other research fields. However, prior related works in EO literature have mainly focused on convolutional architectural advancements, leaving several essential topics unexplored. Consequently, this research investigates through three cases of study fundamental aspects of hybrid quantum machine models for EO tasks aiming to provide a solid groundwork for future research studies towards more adequate simulations and looking at the post-NISQ era. More in detail, we firstly (1) investigate how different quantum libraries behave when training hybrid quantum models, assessing their computational efficiency and effectiveness. Secondly, (2) we analyze the stability/sensitivity to initialization values (i.e., seed values) in both traditional model and quantum-enhanced counterparts. Finally, (3) we explore the benefits of hybrid quantum attention-based models in EO applications, examining how integrating quantum circuits into ViTs can improve model performance.

Paper Structure

This paper contains 14 sections, 12 equations, 1 figure, 26 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Cases of Study
  4. Quantum Libraries
  5. Sensitivity to initialization
  6. Architectures
  7. Experimental Setup
  8. Training Dataset
  9. Implementation Details
  10. Results and Discussion
  11. Comparison of Quantum Libraries
  12. Study on the Stability Towards Initialization Values
  13. Towards Hybrid Quantum Vision Transformers for Earth Observation
  14. Conclusions and Future Worls

Figures (1)

  • Figure 1: Graphical representation of the three reference models employed in this research study. Each traditional architecture, i.e., NN4EOv1, NN4EOv2, NN4EOv3, and ViT, is composed of a sequence of convolutional/self-attention layers (in orange/yellow) in addition to fully connected layers for classification. Differently, the quantum models, i.e., HQNN4EOv1, HQNN4EOv2, HQNN4EOv3, and HQViT, are developed by stacking a quantum circuit to the fully connected layers of traditional models. Within the same architectural design, double lines are used to distinguish between traditional and hybrid designs, while a Bloch sphere represents the single qubit circuit.