Articles | Volume 19, issue 6
https://doi.org/10.5194/bg-19-1777-2022
https://doi.org/10.5194/bg-19-1777-2022
Research article
 | 
31 Mar 2022
Research article |  | 31 Mar 2022

A convolutional neural network for spatial downscaling of satellite-based solar-induced chlorophyll fluorescence (SIFnet)

Johannes Gensheimer, Alexander J. Turner, Philipp Köhler, Christian Frankenberg, and Jia Chen

Related authors

Probabilities of detection of methane plumes by remote sensing and implications for inferred emissions distributions
Ethan Manninen, Apisada Chulakadabba, Maryann Sargent, Zhan Zhang, Harshil Kamdar, Jack Warren, Sébastien Roche, Christopher Chan Miller, Ethan Kyzivat, Joshua Benmergui, Jasna Pittman, Eleanor Walker, Jacob Bushey, Jenna Samra, Jacob Hawthorne, Bingkun Luo, Maya Nasr, Kang Sun, Jonathan Franklin, Xiong Liu, Jia Chen, and Steven Wofsy
Atmos. Chem. Phys., 26, 15915–15929, https://doi.org/10.5194/acp-26-15915-2026,https://doi.org/10.5194/acp-26-15915-2026, 2026
Short summary
SCOUT: Munich Urban Street-level CO2 Sensor Network
Daniel Kühbacher, Jia Chen, Patrick Aigner, Adrian Wenzel, Pascal Rubli, Dominik Brunner, Lukas Emmenegger, and Stuart K. Grange
EGUsphere, https://doi.org/10.5194/egusphere-2026-6001,https://doi.org/10.5194/egusphere-2026-6001, 2026
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary
Satellite Remote Sensing of Methane Point Sources: A Review of Capabilities and Applications
Daniel Cusworth, Daniel Varon, Dylan Jervis, Jason McKeever, Alexander Turner, Christian Frankenberg, John Worden, Andrew Thorpe, Jay Fahlen, Sudhanshu Pandey, Joannes Maasakkers, Ilse Aben, Annmarie Eldering, Riley Duren, Bradley Conrad, Tia Scarpelli, Daniel Bon, Mackenzie Huffman, Itziar Irakulis-Loitxate, Luis Guanter, Jason Schroeder, Benjamin Hmiel, Evan Sherwin, Sean Crowell, Eric Kort, Adam Brandt, Frances Reuland, Maryann Sargent, James East, and Daniel Jacob
EGUsphere, https://doi.org/10.5194/egusphere-2026-6060,https://doi.org/10.5194/egusphere-2026-6060, 2026
This preprint is open for discussion and under review for Atmospheric Chemistry and Physics (ACP).
Short summary
Dual-band information helps constrain canopy water content and temperature retrievals from vegetation optical depth
Yitong Yao, Vincent Humphrey, Alexandra G. Konings, Jeffrey D. Wood, Yujie Wang, Ke Liu, Dien Wu, and Christian Frankenberg
EGUsphere, https://doi.org/10.5194/egusphere-2026-4858,https://doi.org/10.5194/egusphere-2026-4858, 2026
Short summary
Quantifying total methane emissions in the Permian Basin using MFIM: the MethaneSAT FLEXPART Inverse Model
Jacob B. H. Bushey, Michael Bertolacci, Joshua Benmergui, Julian Kostinek, Maryann Sargent, Marvin Knapp, Ethan Kyzivat, Sasha Ayvazov, Marcus Russi, Zhan Zhang, Apisada Chulakadabba, Jia Chen, Christopher Chan Miller, Sébastien Roche, Lucas A. Estrada, James D. East, Luna Yin, James P. Williams, Anthony Himmelberger, Ritesh Gautam, Mark Omara, and Steven C. Wofsy
EGUsphere, https://doi.org/10.5194/egusphere-2026-4693,https://doi.org/10.5194/egusphere-2026-4693, 2026
This preprint is open for discussion and under review for Atmospheric Measurement Techniques (AMT).
Short summary

Cited articles

Akiba, T., Sano, S., Yanase, T., Ohta, T., and Koyama, M.: Optuna: A next-generation hyperparameter optimization framework, in: KDD '19: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 4–8 August 2019, Anchorage, AK, USA, 2623–2631, https://doi.org/10.1145/3292500.3330701, 2019. a
Badgley, G., Field, C. B., and Berry, J. A.: Canopy near-infrared reflectance and terrestrial photosynthesis, Science Advances, 3, e1602244, https://doi.org/10.1126/sciadv.1602244, 2017. a
Benesty, J., Chen, J., Huang, Y., and Cohen, I.: Pearson correlation coefficient, in: Noise reduction in speech processing, 37–40, Springer, ISBN 978-3-642-00295-3, 2009. a, b
Bishop, C. M.: Pattern Recognition and Machine Learning, Springer, 1st edn., New York, NY, ISBN 978-0-387-31073-2, 2007. a
Breiman, L.: Random forests, Mach. Learn., 45, 5–32, 2001. a
Download
Short summary
We develop a convolutional neural network, named SIFnet, that increases the spatial resolution of SIF from TROPOMI by a factor of 10 to a spatial resolution of 0.005°. SIFnet utilizes coarse SIF observations, together with a broad range of high-resolution auxiliary data. The insights gained from interpretable machine learning techniques allow us to make quantitative claims about the relationships between SIF and other common parameters related to photosynthesis.
Share
Altmetrics
Final-revised paper
Preprint