Neural network radiative transfer for imaging spectroscopy

Bue, Brian D.; Thompson, David R.; Deshpande, Shubhankar; Eastwood, Michael; Green, Robert O.; Natraj, Vijay; Mullen, Terry; Parente, Mario

doi:https://doi.org/10.5194/amt-12-2567-2019

Articles | Volume 12, issue 4

https://doi.org/10.5194/amt-12-2567-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/amt-12-2567-2019

© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 12, issue 4

Research article

|

02 May 2019

Research article |

| 02 May 2019

Neural network radiative transfer for imaging spectroscopy

Brian D. Bue, David R. Thompson, Shubhankar Deshpande, Michael Eastwood, Robert O. Green, Vijay Natraj, Terry Mullen, and Mario Parente

Download

Final revised paper (published on 02 May 2019)
Supplement to the final revised paper
Preprint (discussion started on 18 Jan 2019)

Interactive discussion

Status: closed

AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment

- Printer-friendly version

- Supplement

RC1: 'Nice High Level Overview', Anonymous Referee #1, 02 Feb 2019
- AC1: 'Author responses to referees 1 and 2.', Brian Bue, 15 Mar 2019
RC2: 'Review of "Neural Network Radiative Transfer for Imaging Spectroscopy"', Anonymous Referee #2, 22 Feb 2019
- AC2: 'Author responses to referees 1 and 2', Brian Bue, 15 Mar 2019

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision

AR by Brian Bue on behalf of the Authors (19 Mar 2019) Manuscript

ED: Publish subject to technical corrections (26 Mar 2019) by Lars Hoffmann

AR by Brian Bue on behalf of the Authors (27 Mar 2019) Author's response Manuscript

Post-review adjustments

AA: Author's adjustment | EA: Editor approval

AA by Brian Bue on behalf of the Authors (17 Apr 2019) Author's adjustment Manuscript

EA: Adjustments approved (17 Apr 2019) by Lars Hoffmann

Short summary

Imaging spectrometers provide valuable remote measurements of Earth's surface and atmosphere. These measurements rely on computationally expensive radiative transfer models (RTMs). Spectrometers produce too much data to process with RTMs directly, requiring approximations that trade accuracy for speed. We demonstrate that neural networks can quickly emulate RTM calculations more accurately than current approaches, enabling the application of more sophisticated RTMs than current methods permit.