Leading role of Saharan dust on tropical cyclone rainfall in the Atlantic Basin

Creators: Zhu, Laiyin¹; Wang, Yuan (Corresponding)²; Chavas, Dan³; Johncox, Max⁴; Yung, Yuk L.⁵

1. Western Michigan University
2. Stanford University
3. Purdue University West Lafayette
4. University of Utah
5. California Institute of Technology

Abstract

Tropical cyclone rainfall (TCR) extensively affects coastal communities, primarily through inland flooding. The impact of global climate changes on TCR is complex and debatable. This study uses an XGBoost machine learning model with 19-year meteorological data and hourly satellite precipitation observations to predict TCR for individual storms. The model identifies dust optical depth (DOD) as a key predictor that enhances performance evidently. The model also uncovers a nonlinear and boomerang-shape relationship between Saharan dust and TCR, with a TCR peak at 0.06 DOD and a sharp decrease thereafter. This indicates a shift from microphysical enhancement to radiative suppression at high dust concentrations. The model also highlights meaningful correlations between TCR and meteorological factors like sea surface temperature and equivalent potential temperature near storm cores. These findings illustrate the effectiveness of machine learning in predicting TCR and understanding its driving factors and physical mechanisms.

Copyright and License

© 2024 the Authors, some rights reserved; exclusive licensee American Association for the Advancement of Science. No claim to original U.S. Government Works. Distributed under a Creative Commons Attribution license 4.0 (CC BY).

Acknowledgement

We thank the constructive comments from the anonymous referees.

Funding

Y.W. was supported by the NSF (AGS-2103714). L.Z was supported by the Faculty Research and Creative Activities Award from Western Michigan University.

Contributions

Conceptualization: Y.W., L.Z., and D.C.; data acquisition: L.Z. and Y.W.; methodology: Y.W., L.Z., and D.C.; formal analysis: L.Z., Y.W., and M.J.; writing–original draft: L.Z., Y.W., and D.C.; writing–review and editing: All authors.

Data Availability

All data needed to evaluate the conclusions in the paper are present in the paper and/or the Supplementary Materials. Raw and processed data as well as ML codes are archived at Stanford Digital Repository Services with DOI: https://doi.org/10.25740/vh400jc1009

Supplemental Material

Figs. S1 to S14; Tables S1 and S2 (PDF)

Files

Name	Size	Download all
sciadv.adn6106.pdf md5:81f14923cd449038cd6b62a86303517e	2.8 MB	Preview Download
sciadv.adn6106_sm.pdf md5:2b8fde47207e7d1e8a00dccc46c22c7a	7.3 MB	Preview Download

	All versions	This version
Views	0	0
Downloads	0	0
Data volume	0 Bytes	0 Bytes