Quanv4EO: Empowering Earth Observation by means of Quanvolutional Neural Networks

TL;DR

The proposed Quanv4EO framework introduces a quanvolution method for (pre)processing multidimensional EO data, and demonstrates notable improvements in speckle noise reduction, paving the way for more efficient and effective solutions for wide geographical area EO data exploitation.

Abstract

A significant amount of remotely sensed data is generated daily by many Earth observation (EO) spaceborne and airborne sensors over different countries of our planet. Different applications use those data, such as natural hazard monitoring, global climate change, urban planning, and more. Many challenges are brought by the use of these big data in the context of remote sensing applications. In recent years, employment of machine learning (ML) and deep learning (DL)-based algorithms have allowed a more efficient use of these data but the issues in managing, processing, and efficiently exploiting them have even increased since classical computers have reached their limits. This article highlights a significant shift towards leveraging quantum computing techniques in processing large volumes of remote sensing data. The proposed Quanv4EO model introduces a quanvolution method for preprocessing multi-dimensional EO data. First its effectiveness is demonstrated through image classification tasks on MNIST and Fashion MNIST datasets, and later on, its capabilities on remote sensing image classification and filtering are shown. Key findings suggest that the proposed model not only maintains high precision in image classification but also shows improvements of around 5\% in EO use cases compared to classical approaches. Moreover, the proposed framework stands out for its reduced parameter size and the absence of training quantum kernels, enabling better scalability for processing massive datasets. These advancements underscore the promising potential of quantum computing in addressing the limitations of classical algorithms in remote sensing applications, offering a more efficient and effective alternative for image data classification and analysis.

Figures (10)

• Figure 1: Quanvolution Scheme, where is shown a quantum kernel of $2\times2$ qubits (top). Features extracted with the quantum kernel on a Sentinel-1 and Sentinel-2 images (bottom).
• Figure 2: Quanvolution Image Processing Time by varying size of the input image, stride, number of qubits, kernel size and number of output channels. The top left plot shows how the timing is influenced by number of qubits image size and stride. The top right shows how the timing is influenced by number of qubits, image size and kernel size. The bottom plot shows how the timing is influenced by the number of qubits, image size and number of output feature maps.
• Figure 3: Quanvolution processing time with a configuration with 8/16 qubits, $2\times 2$ kernel size and 4 output features map.
• Figure 4: Features Map with random circuit of 16 qubits
• Figure 5: Features Map with random circuit of 9 qubits