Light-cone feature selection in methane hyperspectral images

• URL: http://arxiv.org/abs/2504.00793v1
• Date: Tue, 01 Apr 2025 13:51:39 GMT
• Title: Light-cone feature selection in methane hyperspectral images
• Authors: Artur Miroszewski, Jakub Nalepa, Agata M. Wijata,
• Abstract summary: This study focuses on the application of light-cone feature selection in quantum machine learning for methane detection and localization using HSIs.<n>The proposed method leverages quantum methods to enhance feature selection and classification accuracy.<n>It demonstrates the potential of quantum machine learning in improving the remote sensing data analysis for environmental monitoring.
• Score: 2.7847706215729597
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hyperspectral images (HSIs) capture detailed spectral information across numerous contiguous bands, enabling the extraction of intrinsic characteristics of scanned objects and areas. This study focuses on the application of light-cone feature selection in quantum machine learning for methane detection and localization using HSIs. The proposed method leverages quantum methods to enhance feature selection and classification accuracy. The dataset used includes HSIs collected by the AVIRIS-NG instrument captured in geographically diverse locations. In this study, we investigate the performance of support vector machine classifiers with different classic and quantum kernels. The results indicate that the quantum kernel classifier, combined with light-cone feature selection, provides in one metric, superior performance when compared to the classic techniques. It demonstrates the potential of quantum machine learning in improving the remote sensing data analysis for environmental monitoring.

Related papers

• Benchmarking quantum machine learning kernel training for classification tasks [0.0]
  This study focuses on quantum kernel methods in the context of classification tasks.<n>It examines the performance of Quantum Kernel Estimation (QKE) and Quantum Kernel Training (QKT) in connection with two quantum feature mappings.<n> Experimental results indicate that quantum methods exhibit varying performance across different datasets.
  arXiv  Detail & Related papers  (2024-08-17T10:53:06Z)
• SpectralKAN: Kolmogorov-Arnold Network for Hyperspectral Images Change Detection [23.75924656112022]
  Deep learning methods can accurately extract features from hyperspectral images (HSIs) These algorithms perform exceptionally well on HSIs change detection (HSIs-CD) We propose an spectral Kolmogorov-Arnold Network for HSIs-CD (SpectralKAN) SpectralKAN maintains high HSIs-CD accuracy while requiring fewer parameters, FLOPs, GPU memory, training and testing times.
  arXiv  Detail & Related papers  (2024-07-01T04:09:24Z)
• Unsupervised Band Selection Using Fused HSI and LiDAR Attention Integrating With Autoencoder [16.742768644585684]
  Band selection in hyperspectral imaging (HSI) is critical for optimising data processing and enhancing analytical accuracy. Traditional approaches have predominantly concentrated on analysing spectral and pixel characteristics within individual bands independently. This paper introduces a novel unsupervised band selection framework that incorporates attention mechanisms and an Autoencoder for reconstruction-based band selection.
  arXiv  Detail & Related papers  (2024-04-08T07:47:28Z)
• Optical Quantum Sensing for Agnostic Environments via Deep Learning [59.088205627308]
  We introduce an innovative Deep Learning-based Quantum Sensing scheme. It enables optical quantum sensors to attain Heisenberg limit (HL) in agnostic environments. Our findings offer a new lens through which to accelerate optical quantum sensing tasks.
  arXiv  Detail & Related papers  (2023-11-13T09:46:05Z)
• A Survey of Graph and Attention Based Hyperspectral Image Classification Methods for Remote Sensing Data [5.1901440366375855]
  The use of Deep Learning techniques for classification in Hyperspectral Imaging (HSI) is rapidly growing. Recent methods have also explored the usage of Graph Convolution Networks and their unique ability to use node features in prediction.
  arXiv  Detail & Related papers  (2023-10-16T00:42:25Z)
• ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution [76.7408734079706]
  Single hyperspectral image super-resolution (single-HSI-SR) aims to restore a high-resolution hyperspectral image from a low-resolution observation. We propose ESSAformer, an ESSA attention-embedded Transformer network for single-HSI-SR with an iterative refining structure.
  arXiv  Detail & Related papers  (2023-07-26T07:45:14Z)
• Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation [55.9217962930169]
  We present S2ADet, an object detector that harnesses the rich spectral and spatial complementary information inherent in hyperspectral images. S2ADet surpasses existing state-of-the-art methods, achieving robust and reliable results.
  arXiv  Detail & Related papers  (2023-06-14T09:01:50Z)
• An Unsupervised Machine Learning Approach for Ground-Motion Spectra Clustering and Selection [6.3376363722490145]
  This paper presents an unsupervised machine learning algorithm to extract defining characteristics of earthquake ground-motion spectra. A latent feature is a low-dimensional machine-discovered spectral characteristic learned through nonlinear relationships of a neural network autoencoder. Three examples are presented to validate this approach, including the use of synthetic and field recorded ground-motion datasets.
  arXiv  Detail & Related papers  (2022-12-06T18:02:55Z)
• Supervised classification methods applied to airborne hyperspectral images: Comparative study using mutual information [0.0]
  This paper investigates the performance of four supervised learning algorithms, namely, Support Vector Machines SVM, Random Forest RF, K-Nearest Neighbors KNN and Linear Discriminant Analysis LDA. The experiments have been performed on three real hyperspectral datasets taken from the NASA's Airborne Visible/Infrared Imaging Spectrometer Sensor AVIRIS and the Reflective Optics System Imaging Spectrometer ROSIS sensors.
  arXiv  Detail & Related papers  (2022-10-27T13:39:08Z)
• Enhanced detection techniques of Orbital Angular Momentum states in the classical and quantum regimes [48.7576911714538]
  Complex structure inherent in Orbital Angular Momentum (OAM) states makes their detection and classification nontrivial. Most of the current detection schemes are based on models of the OAM states built upon the use of Laguerre-Gauss modes. We employ Hypergeometric-Gaussian modes as the basis states of a refined model that can be used -- in certain scenarios -- to better tailor OAM detection techniques.
  arXiv  Detail & Related papers  (2022-01-19T18:46:34Z)
• Hyperspectral Image Segmentation based on Graph Processing over Multilayer Networks [51.15952040322895]
  One important task of hyperspectral image (HSI) processing is the extraction of spectral-spatial features. We propose several approaches to HSI segmentation based on M-GSP feature extraction. Our experimental results demonstrate the strength of M-GSP in HSI processing and spectral-spatial information extraction.
  arXiv  Detail & Related papers  (2021-11-29T23:28:18Z)
• Advantages and Bottlenecks of Quantum Machine Learning for Remote Sensing [63.69764116066747]
  This concept paper aims to provide a brief outline of quantum computers, explore existing methods of quantum image classification techniques, and discuss the bottlenecks of performing these algorithms on currently available open source platforms. Next steps include expanding the size of the quantum hidden layer and increasing the variety of output image options.
  arXiv  Detail & Related papers  (2021-01-26T09:31:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.