Spectral imaging modalities, including reflectance and X-ray fluorescence, play an important role in conservation science. In reflectance hyperspectral imaging, the data are classified into areas having similar spectra and turned into labeled pigment maps using spectral features and fusing with other information. Direct classification and labeling remain challenging because many paints are intimate pigment mixtures that require a non-linear unmixing model for a robust solution. Neural networks have been successful in modeling non-linear mixtures in remote sensing with large training datasets. For paintings, however, existing spectral databases are small and do not encompass the diversity encountered. Given that painting practices are relatively consistent within schools of artistic practices, we tested the suitability of using reflectance spectra from a subgroup of well-characterized paintings to build a large database to train a one-dimensional (spectral) convolutional neural network. The labeled pigment maps produced were found to be robust within similar styles of paintings.

No abstract

 Fusion of satellites with models for high space and time resolution land surface temperature needed for many surface-atmosphere studies  Developed an approach that evaluates well across array of towers and aircraft observations from an intensive field experiment  Additional downscaling with airborne hyperspectral imagery further refines identification of hot spots as evaluated with drone observations Accepted ArticleThis article has been accepted for publication and undergone full peer review but has not been through the copyediting, typesetting, pagination and proofreading process, which may lead to differences between this version and the Version of Record. Please cite this article as

The split window technique has been used for over thirty years to derive surface temperatures of the Earth with image data collected from spaceborne sensors containing two thermal channels. The latest NASA/USGS Landsat satellites contain the Thermal Infrared Sensor (TIRS) instruments that acquire Earth data in two longwave infrared bands, as opposed to a single band with earlier Landsats. The United States Geological Survey (USGS) will soon begin releasing a surface temperature product for Landsats 4 through 8 based on the single spectral channel methodology. However, progress is being made toward developing and validating a more accurate and less computationally intensive surface temperature product based on the split window method for Landsat 8 and 9 datasets. This work presents the progress made towards developing an operational split window algorithm for TIRS. Specifically, details of how the generalized split window algorithm was tailored for the TIRS sensors are presented, along with geometric considerations that should be addressed to avoid spatial artifacts in the final surface temperature product. Validation studies indicate that the proposed algorithm is accurate to within 2 K when compared to land-based measurements and to within 1 K when compared to water-based measurements, highlighting the improved accuracy that may be achieved over the current single-channel methodology being used to derive surface temperature in the Landsat Collection 2 surface temperature product. Surface temperature products using the split window methodologies described here can be made available upon request for testing purposes.

Abstract: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 µm) 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 ·sr·µm when compared to actual Terra/MODIS band 31 image data. These studies found that for radiances above 6 W/m 2 ·sr·µm, 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.