Improved Gas Plume Identification Using Nearest Neighbor Methods for Background Estimation

Jarman, Scout Cabe; Hampel-Arias, Zigfried; Carr, Adra Victoria; Moon, Kevin R.

doi:10.1109/TGRS.2025.3597245

Improved Gas Plume Identification Using Nearest Neighbor Methods for Background Estimation

Journal Article · Fri Aug 08 00:00:00 EDT 2025 · IEEE Transactions on Geoscience and Remote Sensing

DOI:https://doi.org/10.1109/TGRS.2025.3597245· OSTI ID:2589872

^[1]; ^[2]; ^[2]; ^[1]

Utah State Univ., Logan, UT (United States)
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Longwave infrared (LWIR) hyperspectral imaging (HSI) can be used for many tasks in remote sensing, including detecting and identifying effluent gases by LWIR sensors on airborne platforms. Identification is used after detection to increase confidence in weakly detected plumes, reduce false positives from detection, and distinguish between similar and confounding material signatures. Background estimation is an important step used to reveal the unique spectral characteristics of the detected gas, allowing the identification model to determine what the gas is specifically. The importance of proper background estimation increases when dealing with weak signals, large libraries of gases of interest, and uncommon or heterogeneous backgrounds. In this article, we propose two methods for background estimation: a novel k-nearest segments (KNS) algorithm and the standard k-nearest neighbors (KNN) algorithm. We test our methods and three existing background estimation methods for comparison against global background estimation to determine which performs best at estimating the true background radiance under a plume and for increasing identification confidence using a neural network classification model. We compare the different methods using 640 simulated weak plumes in an urban environment. For identification, our KNS algorithm improves median neural network identification confidence by 53.2%. For background radiance estimation, the KNN algorithm provides a median of 49 times less RMSE than global background estimation. Furthermore, KNN is the easiest method to tune for different plumes, making it an excellent “out of the box” background estimator.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA), Office of Defense Nuclear Nonproliferation

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 2589872

Report Number(s):: LA-UR--24-31408; 10.1109/TGRS.2025.3597245; 1558-0644

Journal Information:: IEEE Transactions on Geoscience and Remote Sensing, Journal Name: IEEE Transactions on Geoscience and Remote Sensing Vol. 63; ISSN 1558-0644; ISSN 0196-2892

Publisher:: Institute of Electrical and Electronics Engineers (IEEE)Copyright Statement

Country of Publication:: United States

Language:: English

References (37)

Principal Component Analysis Jolliffe, Ian International Encyclopedia of Statistical Science https://doi.org/10.1007/978-3-642-04898-2_455	book	January 2011
Hyperspectral image segmentation: a comprehensive survey Grewal, Reaya; Kasana, Singara Singh; Kasana, Geeta Multimedia Tools and Applications, Vol. 82, Issue 14 https://doi.org/10.1007/s11042-022-13959-w	journal	October 2022
Spectral–Spatial Hyperspectral Image Classification Based on KNN Huang, Kunshan; Li, Shutao; Kang, Xudong Sensing and Imaging, Vol. 17, Issue 1 https://doi.org/10.1007/s11220-015-0126-z	journal	December 2015
A review of dispersion modelling and its application to the dispersion of particles: An overview of different dispersion models available Holmes, N. S.; Morawska, L. Atmospheric Environment, Vol. 40, Issue 30 https://doi.org/10.1016/j.atmosenv.2006.06.003	journal	September 2006
Segmentation and classification of hyperspectral images using watershed transformation Tarabalka, Y.; Chanussot, J.; Benediktsson, J. A. Pattern Recognition, Vol. 43, Issue 7 https://doi.org/10.1016/j.patcog.2010.01.016	journal	July 2010
Tracking and quantification of gaseous chemical plumes from anthropogenic emission sources within the Los Angeles Basin Buckland, Kerry N.; Young, Stephen J.; Keim, Eric R. Remote Sensing of Environment, Vol. 201 https://doi.org/10.1016/j.rse.2017.09.012	journal	November 2017
Adaptive detection algorithm for full pixel targets in hyperspectral images Acito, N.; Corsini, G.; Diani, M. IEE Proceedings - Vision, Image, and Signal Processing, Vol. 152, Issue 6 https://doi.org/10.1049/ip-vis:20045025	journal	January 2005
Hyperspectral subpixel target detection using the linear mixing model Manolakis, D.; Siracusa, C.; Shaw, G. IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, Issue 7 https://doi.org/10.1109/36.934072	journal	July 2001
Clustering to improve matched filter detection of weak gas plumes in hyperspectral thermal imagery Funk, C. C.; Theiler, J.; Roberts, D. A. IEEE Transactions on Geoscience and Remote Sensing, Vol. 39, Issue 7 https://doi.org/10.1109/36.934073	journal	July 2001
Detection algorithms for hyperspectral imaging applications Manolakis, D.; Shaw, G. IEEE Signal Processing Magazine, Vol. 19, Issue 1 https://doi.org/10.1109/79.974724	journal	January 2002
Modern Trends in Hyperspectral Image Analysis: A Review Khan, Muhammad Jaleed; Khan, Hamid Saeed; Yousaf, Adeel IEEE Access, Vol. 6 https://doi.org/10.1109/ACCESS.2018.2812999	journal	January 2018
An Overview of Background Modeling for Detection of Targets and Anomalies in Hyperspectral Remotely Sensed Imagery Matteoli, Stefania; Diani, Marco; Theiler, James IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 7, Issue 6 https://doi.org/10.1109/JSTARS.2014.2315772	journal	June 2014
A Comprehensive Evaluation of Spectral Distance Functions and Metrics for Hyperspectral Image Processing Deborah, Hilda; Richard, Noel; Hardeberg, Jon Yngve IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 8, Issue 6 https://doi.org/10.1109/JSTARS.2015.2403257	journal	June 2015
3D-CNN and Autoencoder-Based Gas Detection in Hyperspectral Images Özdemir, Okan Bilge; Koz, Alper IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 16 https://doi.org/10.1109/JSTARS.2023.3235781	journal	January 2023
Background Density Nonparametric Estimation With Data-Adaptive Bandwidths for the Detection of Anomalies in Multi-Hyperspectral Imagery Matteoli, Stefania; Veracini, Tiziana; Diani, Marco IEEE Geoscience and Remote Sensing Letters, Vol. 11, Issue 1 https://doi.org/10.1109/LGRS.2013.2250907	journal	January 2014
A Locally Adaptive Background Density Estimator: An Evolution for RX-Based Anomaly Detectors Matteoli, Stefania; Veracini, Tiziana; Diani, Marco IEEE Geoscience and Remote Sensing Letters, Vol. 11, Issue 1 https://doi.org/10.1109/LGRS.2013.2257670	journal	January 2014
Unsupervised Sparse Unmixing of Atmospheric Trace Gases From Hyperspectral Satellite Data Fiscante, Nicomino; Addabbo, Pia; Biondi, Filippo IEEE Geoscience and Remote Sensing Letters, Vol. 19 https://doi.org/10.1109/LGRS.2022.3141551	journal	January 2022
A tutorial overview of anomaly detection in hyperspectral images Matteoli, Stefania; Diani, Marco; Corsini, Giovanni IEEE Aerospace and Electronic Systems Magazine, Vol. 25, Issue 7 https://doi.org/10.1109/MAES.2010.5546306	journal	July 2010
Longwave Infrared Hyperspectral Imaging: Principles, Progress, and Challenges Manolakis, Dimitris; Pieper, Michael; Truslow, Eric IEEE Geoscience and Remote Sensing Magazine, Vol. 7, Issue 2 https://doi.org/10.1109/MGRS.2018.2889610	journal	June 2019
Detection Algorithms in Hyperspectral Imaging Systems: An Overview of Practical Algorithms Manolakis, Dimitris; Truslow, Eric; Pieper, Michael IEEE Signal Processing Magazine, Vol. 31, Issue 1 https://doi.org/10.1109/MSP.2013.2278915	journal	January 2014
Hyperspectral Target Detection : An Overview of Current and Future Challenges Nasrabadi, Nasser M. IEEE Signal Processing Magazine, Vol. 31, Issue 1 https://doi.org/10.1109/MSP.2013.2278992	journal	January 2014
Long-Wave Infrared Hyperspectral Remote Sensing of Chemical Clouds: A focus on signal processing approaches Manolakis, Dimitris. g.; Golowich, Steven; DiPietro, Robert S. IEEE Signal Processing Magazine, Vol. 31, Issue 4 https://doi.org/10.1109/MSP.2013.2294804	journal	July 2014
A cluster-based approach for detecting man-made objects and changes in imagery Carlotto, M. J. IEEE Transactions on Geoscience and Remote Sensing, Vol. 43, Issue 2 https://doi.org/10.1109/TGRS.2004.841481	journal	February 2005
Models and Methods for Automated Background Density Estimation in Hyperspectral Anomaly Detection Matteoli, Stefania; Veracini, Tiziana; Diani, Marco IEEE Transactions on Geoscience and Remote Sensing, Vol. 51, Issue 5 https://doi.org/10.1109/TGRS.2012.2214392	journal	May 2013
Class-Dependent Sparse Representation Classifier for Robust Hyperspectral Image Classification Cui, Minshan; Prasad, Saurabh IEEE Transactions on Geoscience and Remote Sensing, Vol. 53, Issue 5 https://doi.org/10.1109/TGRS.2014.2363582	journal	May 2015
Spectral Radiance Modeling and Bayesian Model Averaging for Longwave Infrared Hyperspectral Imagery and Subpixel Target Identification Rankin, Blake M.; Meola, Joseph; Eismann, Michael T. IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, Issue 12 https://doi.org/10.1109/TGRS.2017.2731955	journal	December 2017
Deep Learning for Hyperspectral Image Classification: An Overview Li, Shutao; Song, Weiwei; Fang, Leyuan IEEE Transactions on Geoscience and Remote Sensing, Vol. 57, Issue 9 https://doi.org/10.1109/TGRS.2019.2907932	journal	September 2019
Performance metrics for the evaluation of hyperspectral chemical identification systems Truslow, Eric; Golowich, Steven; Manolakis, Dimitris Optical Engineering, Vol. 55, Issue 2 https://doi.org/10.1117/1.OE.55.2.023106	journal	February 2016
A Limited Memory Algorithm for Bound Constrained Optimization Byrd, Richard H.; Lu, Peihuang; Nocedal, Jorge SIAM Journal on Scientific Computing, Vol. 16, Issue 5 https://doi.org/10.1137/0916069	journal	September 1995
Corrigendum to “Background Radiance Estimation for Gas Plume Quantification for Airborne Hyperspectral Thermal Imaging” Idoughi, Ramzi; Vidal, Thomas H. G.; Foucher, Pierre-Yves Journal of Spectroscopy, Vol. 2016 https://doi.org/10.1155/2016/4616050	journal	December 2016
New perspectives of hyperspectral imaging for clinical research Pallua, Johannes D.; Brunner, Andrea; Zelger, Bernhard NIR news, Vol. 32, Issue 3-4 https://doi.org/10.1177/09603360211024971	journal	June 2021
An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition Yuen, P. Wt; Richardson, M. The Imaging Science Journal, Vol. 58, Issue 5 https://doi.org/10.1179/174313110X12771950995716	journal	October 2010
Determination of trace-gas amounts in plumes by the use of orthogonal digital filtering of thermal-emission spectra Hayden, Andreas; Niple, Edward; Boyce, Bruce Applied Optics, Vol. 35, Issue 16 https://doi.org/10.1364/AO.35.002802	journal	January 1996
Introduction to machine learning: k-nearest neighbors Zhang, Zhongheng Annals of Translational Medicine, Vol. 4, Issue 11 https://doi.org/10.21037/atm.2016.03.37	journal	June 2016
Algorithm AS 136: A K-Means Clustering Algorithm Hartigan, J. A.; Wong, M. A. Applied Statistics, Vol. 28, Issue 1 https://doi.org/10.2307/2346830	journal	January 1979
Overview of Physical Models and Statistical Approaches for Weak Gaseous Plume Detection using Passive Infrared Hyperspectral Imagery Burr, Tom; Hengartner, Nicolas Sensors, Vol. 6, Issue 12 https://doi.org/10.3390/s6121721	journal	December 2006
High spatial resolution imaging of methane and other trace gases with the airborne Hyperspectral Thermal Emission Spectrometer (HyTES) Hulley, Glynn C.; Duren, Riley M.; Hopkins, Francesca M. Atmospheric Measurement Techniques, Vol. 9, Issue 5 https://doi.org/10.5194/amt-9-2393-2016	journal	January 2016

Similar Records

Global and adaptive K-nearest neighbor graphs in a spectral target detector based on Schroedinger Eigenmaps

Journal Article · Sun Dec 03 19:00:00 EST 2017 · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) Proceedings (Online) · OSTI ID:1581649

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

Journal Article · Sun Sep 25 20:00:00 EDT 2022 · IEEE Access · OSTI ID:1922471

ESTIMATING PHOTOMETRIC REDSHIFTS OF QUASARS VIA THE k-NEAREST NEIGHBOR APPROACH BASED ON LARGE SURVEY DATABASES

Journal Article · Thu Aug 01 00:00:00 EDT 2013 · Astronomical Journal (New York, N.Y. Online) · OSTI ID:22118679

Related Subjects

47 OTHER INSTRUMENTATION
97 MATHEMATICS AND COMPUTING
Background Estimation
Gas Plume Identification
LWIR Hyperspectral Image
Neural Network
Segmentation

Improved Gas Plume Identification Using Nearest Neighbor Methods for Background Estimation

Citation Formats

References (37)

Similar Records

Related Subjects