{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T03:52:16Z","timestamp":1760241136572,"version":"build-2065373602"},"reference-count":26,"publisher":"MDPI AG","issue":"24","license":[{"start":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T00:00:00Z","timestamp":1575504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>A machine learning approach was developed to improve the bad pixel maps that mask damaged or unusable pixels in the imaging spectrometers of National Aeronautics and Space Administration (NASA) Orbiting Carbon Observatory-2 (OCO-2) and Orbiting Carbon Observatory-3 (OCO-3). The OCO-2 and OCO-3 instruments use nearly 500,000 pixels to record high resolution spectra in three infrared wavelength ranges. These spectra are analyzed to retrieve estimates of the column-average carbon dioxide (XCO    2) concentration in Earth\u2019s atmosphere. To meet mission requirements, these XCO    2     estimates must have accuracies exceeding 0.25%, and small uncertainties in the bias or gain of even one detector pixel can add significant error to the retrieved XCO    2     estimates. Thus, anomalous pixels are identified and removed from the data stream by applying a bad pixel map prior to further processing. To develop these maps, we first characterize each pixel\u2019s behavior through a collection of interpretable and statistically well-defined metrics. These features and a prior map are then used as inputs in a Random Forest classifier to assign a likelihood that a given pixel is bad. Consequently, the likelihoods are analyzed and thresholds are chosen to produce a new bad pixel map. The machine learning approach adopted here has improved data quality by identifying hundreds of new bad pixels in each detector. Such an approach can be generalized to other instruments that require independent calibration of many individual elements.<\/jats:p>","DOI":"10.3390\/rs11242901","type":"journal-article","created":{"date-parts":[[2019,12,5]],"date-time":"2019-12-05T11:16:31Z","timestamp":1575544591000},"page":"2901","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Classification of Anomalous Pixels in the Focal Plane Arrays of Orbiting Carbon Observatory-2 and -3 via Machine Learning"],"prefix":"10.3390","volume":"11","author":[{"given":"Yuliya","family":"Marchetti","sequence":"first","affiliation":[{"name":"Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Dr, Pasadena, CA 91109, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0459-4630","authenticated-orcid":false,"given":"Robert","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Dr, Pasadena, CA 91109, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4573-9998","authenticated-orcid":false,"given":"David","family":"Crisp","sequence":"additional","affiliation":[{"name":"Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Dr, Pasadena, CA 91109, USA"}]}],"member":"1968","published-online":{"date-parts":[[2019,12,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"6904","DOI":"10.1364\/AO.47.006904","article-title":"Robust autonomous detection of the defective pixels in detectors using a probabilistic technique","volume":"47","author":"Ghosh","year":"2008","journal-title":"Appl. Opt."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2393","DOI":"10.1109\/JSTARS.2014.2324654","article-title":"Advanced anomalous pixel correction algorithms for hyperspectral thermal infrared data: The TASI-600 case study","volume":"7","author":"Santini","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"11594","DOI":"10.1364\/OE.17.011594","article-title":"Scene-based spectral calibration assessment of high spectral resolution imaging spectrometers","volume":"17","author":"Guanter","year":"2009","journal-title":"Opt. Express"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"65651E","DOI":"10.1117\/12.720050","article-title":"Median spectral-spatial bad pixel identification and replacement for hyperspectral SWIR sensors","volume":"Volume 6565","author":"Fischer","year":"2007","journal-title":"Proceedings of the Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIII"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1117\/12.257162","article-title":"Detection and correction of bad pixels in hyperspectral sensors","volume":"Volume 2821","author":"Kieffer","year":"1996","journal-title":"Proceedings of the Hyperspectral Remote Sensing and Applications"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Chapman, J.W., Thompson, D.R., Helmlinger, M.C., Bue, B.D., Green, R.O., Eastwood, M.L., Geier, S., Olson-Duvall, W., and Lundeen, S.R. (2019). Spectral and Radiometric Calibration of the Next, Generation Airborne Visible Infrared Spectrometer (AVIRIS-NG). Remote Sens., 11.","DOI":"10.3390\/rs11182129"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"012002","DOI":"10.1088\/1742-6596\/772\/1\/012002","article-title":"A novel algorithm for bad pixel detection and correction to improve quality and stability of geometric measurements","volume":"772","author":"Celestre","year":"2016","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_8","unstructured":"Han, T., Goodenough, D.G., Dyk, A., and Love, J. (2002, January 24\u201328). Detection and correction of abnormal pixels in Hyperion images. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Toronto, ON, Canada."},{"key":"ref_9","unstructured":"Tan, Y.P., and Acharya, T. (1999, January 15\u201319). A robust sequential approach for the detection of defective pixels in an image sensor. Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, AZ, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1117\/12.498343","article-title":"Principal component analysis of noise in an image-acquisition system: bad pixel extraction","volume":"Volume 5036","author":"Alda","year":"2003","journal-title":"Proceedings of the Photonics, Devices, and Systems II"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Rankin, B.M., Broadwater, J.B., and Smith, M. (2018, January 22\u201327). Anomalous Pixel Replacement and Spectral Quality Algorithm for Longwave Infrared Hyperspectral Imagery. Proceedings of the IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain.","DOI":"10.1109\/IGARSS.2018.8517461"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"549","DOI":"10.5194\/amt-10-549-2017","article-title":"The Orbiting Carbon Observatory-2: First, 18 months of science data products","volume":"10","author":"Eldering","year":"2017","journal-title":"Atmos. Meas. Tech."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6539","DOI":"10.5194\/amt-11-6539-2018","article-title":"Improved retrievals of carbon dioxide from Orbiting Carbon Observatory-2 with the version 8 ACOS algorithm","volume":"11","author":"Eldering","year":"2018","journal-title":"Atmos. Meas. Tech."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., and Tibshirani, R. (2009). The Elements of Statistical Learning, Springer.","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"59","DOI":"10.5194\/amt-10-59-2017","article-title":"The on-orbit performance of the Orbiting Carbon Observatory-2 (OCO-2) instrument and its radiometrically calibrated products","volume":"10","author":"Crisp","year":"2017","journal-title":"Atmos. Meas. Tech."},{"key":"ref_17","unstructured":"Eldering, A., Pollock, R., Lee, R., Rosenberg, R., Oyafuso, F., Granat, R., Crisp, D., and Gunson, M. (2019, December 04). Orbiting Carbon Observatory OCO-2 Level L1b Algorithm Theoretical Basis, Available online: https:\/\/docserver.gesdisc.eosdis.nasa.gov\/public\/project\/OCO\/OCO_L1B_ATBD.pdf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2341","DOI":"10.5194\/amt-12-2341-2019","article-title":"The OCO-3 mission: Measurement objectives and expected performance based on 1 year of simulated data","volume":"12","author":"Eldering","year":"2019","journal-title":"Atmos. Meas. Tech."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1093\/biomet\/81.3.425","article-title":"Ideal spatial adaptation by wavelet shrinkage","volume":"81","author":"Donoho","year":"1994","journal-title":"Biometrika"},{"key":"ref_20","first-page":"10","article-title":"Ten lectures on wavelets","volume":"61","author":"Daubechies","year":"1992","journal-title":"SIAM"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","article-title":"Dynamic programming algorithm optimization for spoken word recognition","volume":"26","author":"Sakoe","year":"1978","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"ref_22","unstructured":"Berndt, D.J., and Clifford, J. (August, January 31). Using dynamic time warping to find patterns in time series. Proceedings of the KDD Workshop, Seattle, WA, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"561","DOI":"10.3233\/IDA-2007-11508","article-title":"Toward accurate dynamic time warping in linear time and space","volume":"11","author":"Salvador","year":"2007","journal-title":"Intell. Data Anal."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1109\/TGRS.2016.2634023","article-title":"Preflight Radiometric Calibration of Orbiting Carbon Observatory 2","volume":"55","author":"Rosenberg","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","unstructured":"Saabas, A. (2017, October 02). Treeinterpreter. Available online: https:\/\/github.com\/andosa\/treeinterpreter."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/S0026-2714(02)00025-2","article-title":"Electrical noise and RTS fluctuations in advanced CMOS devices","volume":"42","author":"Ghibaudo","year":"2002","journal-title":"Microelectron. Reliab."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2901\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:40:23Z","timestamp":1760190023000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/24\/2901"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12,5]]},"references-count":26,"journal-issue":{"issue":"24","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["rs11242901"],"URL":"https:\/\/doi.org\/10.3390\/rs11242901","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2019,12,5]]}}}