Hybrid Quantum CNN for Cross-Sensor Spaceborne Volcanic Thermal Activity Recognition Worldwide

2026-07-29

AI Summary

This work addresses the limitations of classical deep learning models in on-orbit processing of global multi-source satellite thermal anomaly data—specifically their poor cross-sensor generalization, heavy reliance on large annotated datasets, and incompatibility with onboard computational constraints. To overcome these challenges, the authors propose a hybrid quantum AlexNet architecture that integrates a parameterized quantum circuit (PQC) as a trainable layer embedded within a classical convolutional backbone. By leveraging quantum embedding to map high-level image features into a high-dimensional Hilbert space, the model substantially enhances feature discriminability and environmental robustness. Experimental results demonstrate that, compared to purely classical counterparts, the proposed approach achieves higher accuracy and superior cross-domain generalization in volcanic thermal anomaly detection across diverse sensors, while significantly reducing both the number of trainable parameters and the required volume of training data.

Abstract

As Earth Observation (EO) enters the Big Data era, the exponential volume of daily satellite imagery poses significant computational and storage challenges for classical Deep Learning (DL) models. Moreover, current approaches often struggle to generalize across heterogeneous sensors and volcanic environments while requiring large labeled datasets and substantial computational resources. These limitations are particularly critical for emerging On-Board Processing (OBP) applications, where memory, computational power, and annotated data are inherently limited. This work proposes a Hybrid Quantum AlexNet architecture for cross-sensor recognition of volcanic thermal activity at the global scale. The proposed model combines a classical convolutional backbone for high-level spatial features extraction with a parameterized quantum circuit (PQC) acting as a variational layer. By embedding high-level image representations into a high-dimensional Hilbert space, the quantum layer learns task-specific representations that enhance feature discrimination. Experimental results demonstrate that the proposed hybrid quantum model learns more discriminative feature representations, leading to improved cross-sensor transferability and robustness across heterogeneous volcanic environments using fewer trainable parameters and reduced training data than its classical counterpart.

Problem

• cross-sensor
• volcanic thermal activity
• on-board processing
• generalization
• big data

Innovation

• Hybrid Quantum CNN
• Parameterized Quantum Circuit
• Cross-sensor Recognition
• On-Board Processing
• Volcanic Thermal Activity