Articles | Volume 13, issue 9
https://doi.org/10.5194/amt-13-4669-2020
https://doi.org/10.5194/amt-13-4669-2020
Research article
 | 
02 Sep 2020
Research article |  | 02 Sep 2020

Gradient boosting machine learning to improve satellite-derived column water vapor measurement error

Allan C. Just, Yang Liu, Meytar Sorek-Hamer, Johnathan Rush, Michael Dorman, Robert Chatfield, Yujie Wang, Alexei Lyapustin, and Itai Kloog

Related authors

Analysis of a saline dust storm from the Aralkum Desert – Part 1: Consistency of multisensor satellite aerosol products
Xin Xi, Jun Wang, Zhendong Lu, Andrew Sayer, Jaehwa Lee, Robert Levy, Yujie Wang, Alexei Lyapustin, Hongqing Liu, Istvan Laszlo, Changwoo Ahn, Omar Torres, Sabur Abdullaev, and Ralph Kahn
EGUsphere, https://doi.org/10.5194/egusphere-2024-3416,https://doi.org/10.5194/egusphere-2024-3416, 2024
Short summary
Importance of aerosol composition and aerosol vertical profiles in global spatial variation in the relationship between PM2.5 and aerosol optical depth
Haihui Zhu, Randall V. Martin, Aaron van Donkelaar, Melanie S. Hammer, Chi Li, Jun Meng, Christopher R. Oxford, Xuan Liu, Yanshun Li, Dandan Zhang, Inderjeet Singh, and Alexei Lyapustin
Atmos. Chem. Phys., 24, 11565–11584, https://doi.org/10.5194/acp-24-11565-2024,https://doi.org/10.5194/acp-24-11565-2024, 2024
Short summary
Light-absorbing black carbon and brown carbon components of smoke aerosol from DSCOVR EPIC measurements over North America and central Africa
Myungje Choi, Alexei Lyapustin, Gregory L. Schuster, Sujung Go, Yujie Wang, Sergey Korkin, Ralph Kahn, Jeffrey S. Reid, Edward J. Hyer, Thomas F. Eck, Mian Chin, David J. Diner, Olga Kalashnikova, Oleg Dubovik, Jhoon Kim, and Hans Moosmüller
Atmos. Chem. Phys., 24, 10543–10565, https://doi.org/10.5194/acp-24-10543-2024,https://doi.org/10.5194/acp-24-10543-2024, 2024
Short summary
Insights into the long-term (2005–2021) spatiotemporal evolution of summer ozone production sensitivity in the Northern Hemisphere derived with the Ozone Monitoring Instrument (OMI)
Matthew S. Johnson, Sajeev Philip, Scott Meech, Rajesh Kumar, Meytar Sorek-Hamer, Yoichi P. Shiga, and Jia Jung
Atmos. Chem. Phys., 24, 10363–10384, https://doi.org/10.5194/acp-24-10363-2024,https://doi.org/10.5194/acp-24-10363-2024, 2024
Short summary
Instantaneous aerosol and surface retrieval using satellites in geostationary orbit (iAERUS-GEO) – estimation of 15 min aerosol optical depth from MSG/SEVIRI and evaluation with reference data
Xavier Ceamanos, Bruno Six, Suman Moparthy, Dominique Carrer, Adèle Georgeot, Josef Gasteiger, Jérôme Riedi, Jean-Luc Attié, Alexei Lyapustin, and Iosif Katsev
Atmos. Meas. Tech., 16, 2575–2599, https://doi.org/10.5194/amt-16-2575-2023,https://doi.org/10.5194/amt-16-2575-2023, 2023
Short summary

Related subject area

Subject: Others (Wind, Precipitation, Temperature, etc.) | Technique: Remote Sensing | Topic: Validation and Intercomparisons
Turbulence kinetic energy dissipation rate estimated from a WindCube Doppler lidar and the LQ7 1.3 GHz radar wind profiler in the convective boundary layer
Hubert Luce and Masanori Yabuki
Atmos. Meas. Tech., 18, 1193–1208, https://doi.org/10.5194/amt-18-1193-2025,https://doi.org/10.5194/amt-18-1193-2025, 2025
Short summary
Comparison of temperature and wind profiles between ground-based remote sensing observations and numerical weather prediction model in complex Alpine topography: the Meiringen campaign
Alexandre Bugnard, Martine Collaud Coen, Maxime Hervo, Daniel Leuenberger, Marco Arpagaus, and Samuel Monhart
Atmos. Meas. Tech., 18, 1039–1061, https://doi.org/10.5194/amt-18-1039-2025,https://doi.org/10.5194/amt-18-1039-2025, 2025
Short summary
Cluster analysis of vertical polarimetric radio occultation profiles and corresponding liquid and ice water paths from Global Precipitation Measurement (GPM) microwave data
Jonas E. Katona, Manuel de la Torre Juárez, Terence L. Kubar, F. Joseph Turk, Kuo-Nung Wang, and Ramon Padullés
Atmos. Meas. Tech., 18, 953–970, https://doi.org/10.5194/amt-18-953-2025,https://doi.org/10.5194/amt-18-953-2025, 2025
Short summary
Enhanced quantitative precipitation estimation through the opportunistic use of Ku TV-SAT links via a dual-channel procedure
Louise Gelbart, Laurent Barthès, François Mercier-Tigrine, Aymeric Chazottes, and Cécile Mallet
Atmos. Meas. Tech., 18, 351–370, https://doi.org/10.5194/amt-18-351-2025,https://doi.org/10.5194/amt-18-351-2025, 2025
Short summary
The added value and potential of long-term radio occultation data for climatological wind field monitoring
Irena Nimac, Julia Danzer, and Gottfried Kirchengast
Atmos. Meas. Tech., 18, 265–286, https://doi.org/10.5194/amt-18-265-2025,https://doi.org/10.5194/amt-18-265-2025, 2025
Short summary

Cited articles

Adesina, A. J., Kumar, K. R., Sivakumar, V., and Griffith, D.: Direct radiative forcing of urban aerosols over Pretoria (25.75 S, 28.28 E) using AERONET Sunphotometer data: first scientific results and environmental impact, J. Environ. Sci., 26, 2459–2474, https://doi.org/10.1016/j.jes.2014.04.006, 2014. 
Aerosol Robotic Network: Version 2 AOD Data, available at: https://aeronet.gsfc.nasa.gov/, last access: 1 June 2019. 
Boiyo, R., Kumar, K. R., Zhao, T., and Guo, J.: A 10-Year Record of Aerosol Optical Properties and Radiative Forcing Over Three Environmentally Distinct AERONET Sites in Kenya, East Africa, J. Geophys. Res.-Atmos., 124, 1596–1617, https://doi.org/10.1029/2018JD029461, 2019. 
Chen, T. and Guestrin, C.: XGBoost: A Scalable Tree Boosting System, in: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – KDD”16, 785–794, ACM Press, New York, New York, USA, 2016. 
Chen, T. and He, T.: Higgs Boson Discovery with Boosted Trees, Proceedings of the NIPS 2014 Workshop on High-energy Physics and Machine Learning, in: Proc. Mach. Learn. Res., 42, 69–80, 2015. 
Download
Short summary
A flexible machine-learning model was fit to explain the differences between estimates of water vapor from satellites versus ground stations in Northeastern USA. We use nine variables derived from the satellite acquisition and ground characteristics to explain this measurement error. Our results showed overall good agreement, but data from the Terra satellite were drifting too high in recent summers. Our model reduces measurement error and works well in new locations in the northeast.
Share