{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T23:41:47Z","timestamp":1771458107790,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2017,11,7]],"date-time":"2017-11-07T00:00:00Z","timestamp":1510012800000},"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>Image data from space-borne thermal infrared (IR) sensors are used for a variety of applications, however they are often limited by their temporal resolution (i.e., repeat coverage). To potentially increase the temporal availability of thermal image data, a study was performed to determine the extent to which thermal image data can be simulated from available atmospheric and surface data. The work conducted here explored the use of Modern-Era Retrospective analysis for Research and Applications, Version 2 (MERRA-2) developed by The National Aeronautics and Space Administration (NASA) to predict top-of-atmosphere (TOA) thermal IR radiance globally at time scales finer than available satellite data. For this case study, TOA radiance data was derived for band 31 (10.97    \u03bc   m) of the Moderate-Resolution Imaging Spectroradiometer (MODIS) sensor. Two approaches have been followed, namely an atmospheric radiative transfer forward modeling approach and a supervised learning approach. The first approach uses forward modeling to predict TOA radiance from the available surface and atmospheric data. The second approach applied four different supervised learning algorithms to the atmospheric data. The algorithms included a linear least squares regression model, a non-linear support vector regression (SVR) model, a multi-layer perceptron (MLP), and a convolutional neural network (CNN). This research found that the multi-layer perceptron model produced the lowest overall error rates with an root mean square error (RMSE) of 1.36 W\/m     2    \u00b7sr\u00b7   \u03bc   m when compared to actual Terra\/MODIS band 31 image data. These studies found that for radiances above 6 W\/m     2    \u00b7sr\u00b7   \u03bc   m, the forward modeling approach could predict TOA radiance to within 12 percent, and the best supervised learning approach can predict TOA to within 11 percent.<\/jats:p>","DOI":"10.3390\/rs9111133","type":"journal-article","created":{"date-parts":[[2017,11,7]],"date-time":"2017-11-07T11:46:01Z","timestamp":1510055161000},"page":"1133","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Predicting Top-of-Atmosphere Thermal Radiance Using MERRA-2 Atmospheric Data with Deep Learning"],"prefix":"10.3390","volume":"9","author":[{"given":"Tania","family":"Kleynhans","sequence":"first","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, NY 14623, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew","family":"Montanaro","sequence":"additional","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, NY 14623, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron","family":"Gerace","sequence":"additional","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, NY 14623, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Kanan","sequence":"additional","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, 54 Lomb Memorial Drive, Rochester, NY 14623, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2017,11,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.rse.2017.01.029","article-title":"Derivation and validation of the stray light correction algorithm for the thermal infrared sensor onboard Landsat 8","volume":"191","author":"Gerace","year":"2017","journal-title":"Remote Sens. Environ."},{"key":"ref_2","unstructured":"Hang, P., Nichoe, J., and Tse, R. (2011, January 11\u201313). Temporal characteristics of thermal satellite images for urban climate study. Proceedings of the Joint Urban Remote Sensing Event, Munich, Germany."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.rse.2005.09.023","article-title":"An analysis of urban thermal characteristics and associated land cover in Tampa Bay and Las Vegas using Landsat satellite data","volume":"104","author":"Xian","year":"2006","journal-title":"Remote Sens. Environ."},{"key":"ref_4","unstructured":"Kleynhans, T., Montanaro, M., Gerace, A., and Kanan, C. (2011, January 1\u20135). Atmospheric correction of landsat thermal infrared data: A calculator based on north american regional reanaly sis (NARR) data. Proceedings of the ASPRS 2011 Annual Conference, Milwaukee, WI, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"11607","DOI":"10.3390\/rs61111607","article-title":"Landsat-8 Thermal Infrared Sensor (TIRS) vicarious radiometric calibration","volume":"6","author":"Barsi","year":"2014","journal-title":"Remote Sens."},{"key":"ref_6","unstructured":"Laraby, K. (2017). Landsat Surface Temperature Product: Global Validation and Uncertainty Estimation. [Ph.D. Thesis, Rochester Institute of Technology]."},{"key":"ref_7","unstructured":"Berk, A., Bernstein, L., and Robertson, D. (1988). MODTRAN: A Moderate Resolution Model for LOWTRAN 7, Spectral Sciences Inc.. Technical Report."},{"key":"ref_8","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G.E. (,  2012). ImageNet classification with deep convolutional neural networks. Proceedings of the 25th International Conference on Neural Information Processing Systems\u2014Volume 1, Lake Tahoe, NV, USA."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/2251-712X-9-1","article-title":"Forecasting S & P 500 index using artificial neural networks and design of experiments","volume":"9","author":"Niaki","year":"2013","journal-title":"J. Ind. Eng. Int."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.neunet.2004.02.002","article-title":"New training strategies for constructive neural networks with application to regression problems","volume":"17","author":"Ma","year":"2004","journal-title":"Neural Netw."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Kleynhans, T., Montanaro, M., Gerace, A., and Kanan, C. (2017, January 3). Estimating top-of-atmosphere thermal infrared radiance using MERRA-2 atmospheric data. Proceedings of the SPIE Defense and Commercial Sensing Conference, Anaheim, CA, USA.","DOI":"10.1117\/12.2262571"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5419","DOI":"10.1175\/JCLI-D-16-0758.1","article-title":"The modern-era retrospective analysis for research and applications, Version 2 (MERRA-2)","volume":"30","author":"Gelaro","year":"2017","journal-title":"J. Clim."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1871","DOI":"10.1175\/JAS-D-15-0333.1","article-title":"Strengthening of the tropopause inversion layer during the 2009 sudden stratospheric warming: A MERRA-2 Study","volume":"73","author":"Wargan","year":"2016","journal-title":"J. Atmos. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8791","DOI":"10.1002\/2016GL070373","article-title":"The anomalous change in the QBO in 2015\u20132016","volume":"43","author":"Newman","year":"2016","journal-title":"Geophys. Res. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.atmosres.2017.02.015","article-title":"Evaluation of Antarctic snowfall in global meteorological reanalyses","volume":"190","author":"Palerme","year":"2017","journal-title":"Atmos. Res."},{"key":"ref_16","unstructured":"(2017, October 16). MERRA-2 inst3_3d_asm_Np: 3d,3-Hourly, Instantaneous, Pressure-Level, Assimilation, Assimilated Meteorological Fields V5.12.4, Available online: https:\/\/disc.sci.gsfc.nasa.gov\/datasets\/M2I3NPASM_V5.12.4\/summary."},{"key":"ref_17","unstructured":"(2017, October 16). MERRA-2 inst1_2d_asm_Nx: 2d,1-Hourly, Instantaneous, Single-Level, Assimilation, Single-Level Diagnostics V5.12.4, Available online: https:\/\/disc.sci.gsfc.nasa.gov\/datasets\/M2I1NXASM_V5.12.4\/summary."},{"key":"ref_18","unstructured":"(2017, October 16). MAT1NXFLX: tavg1_2d_flx_Nx: MERRA 2D IAU Diagnostic, Surface Fluxes, Time Average 1-Hourly V5.2.0, Available online: https:\/\/disc.sci.gsfc.nasa.gov\/datasets\/MAT1NXFLX_5.2.0\/summary."},{"key":"ref_19","unstructured":"McCarty, W., Coy, L., Gelaro, R., Huang, A., Merkova, D., Smith, E.B., Sienkiewicz, M., and Wargan, K. (2016). MERRA-2 Input Observations: Summary and Assessment."},{"key":"ref_20","unstructured":"NASA Goddard Space Flight Center (2017, November 03). MODIS-Terra, Available online: https:\/\/modis.gsfc.nasa.gov\/."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"S89","DOI":"10.1088\/0026-1394\/40\/1\/320","article-title":"MODIS on-orbit calibration and characterization","volume":"40","author":"Xiong","year":"2003","journal-title":"Metrologia"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Friedl, M., Sulla-Menashe, D., Tan, B., Schneider, A., Ramankutty, N., Sibley, A., and Huang, X. (2010). MODIS Collection 5 Global Land Cover: Algorithm Refinements and Characterization of New Datasets, 2001\u20132012, Boston University. Collection 5.1 IGBP Land Cover.","DOI":"10.1016\/j.rse.2009.08.016"},{"key":"ref_23","unstructured":"Hulley, G., and Hook, S. (2017, November 03). The ASTER Global Emissivity Database (ASTER GED), Available online: https:\/\/lpdaac.usgs.gov."},{"key":"ref_24","unstructured":"Schowengerdt, R.A. (2007). Remote Sensing, Academic Press. [3rd ed.]."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1080\/00401706.1970.10488635","article-title":"Ridge regression: Applications to nonorthogonal problems","volume":"12","author":"Hoerl","year":"1970","journal-title":"Technometrics"},{"key":"ref_26","unstructured":"Mozer, M.C., Jordan, M.I., and Petsche, T. (1997). Support vector regression machines. Advances in Neural Information Processing Systems 9, MIT Press."},{"key":"ref_27","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wang, S.C. (2003). Artificial Neural Network. Interdisciplinary Computing in Java Programming, Springer.","DOI":"10.1007\/978-1-4615-0377-4"},{"key":"ref_29","unstructured":"F\u00fcrnkranz, J., and Joachims, T. (2010, January 21\u201324). Rectified Linear Units Improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_30","unstructured":"Chollet, F. (2017, November 03). Keras. GitHub Repository. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_31","unstructured":"Theano Development Team (arXiv, 2016). Theano: A Python framework for fast computation of mathematical expressions, arXiv."},{"key":"ref_32","unstructured":"Ioffe, S., and Szegedy, C. (arXiv, 2015). Batch Normalization: Accelerating deep network training by reducing internal covariate shift, arXiv."},{"key":"ref_33","unstructured":"Hinton, G.E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. (arXiv, 2012). Improving neural networks by preventing co-adaptation of feature detectors, arXiv."},{"key":"ref_34","unstructured":"NASA Goddard Space Flight Center, and Ocean Ecology Laboratory, Ocean Biology Processing Group (2017, November 03). Moderate-Resolution Imaging Spectroradiometer (MODIS) Terra Ocean Color Data, Available online: https:\/\/oceancolor.gsfc.nasa.gov\/data\/10.5067\/TERRA\/MODIS_OC.2014.0\/."},{"key":"ref_35","unstructured":"Armstrong, E. (2017, November 03). MODIS Sea Surface Temperature (SST) Products, Available online: ftp:\/\/podaac-ftp.jpl.nasa.gov\/allData\/modis\/docs\/MODIS_SST_Guide_Doc.pdf."},{"key":"ref_36","unstructured":"Simonyan, K., Vedaldi, A., and Zisserman, A. (arXiv, 2013). Deep inside convolutional networks: Visualising image classification models and saliency maps, arXiv."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/9\/11\/1133\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:48:26Z","timestamp":1760208506000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/9\/11\/1133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11,7]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2017,11]]}},"alternative-id":["rs9111133"],"URL":"https:\/\/doi.org\/10.3390\/rs9111133","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,11,7]]}}}