Machine Learning for Targeted Assimilation of Satellite Data
Abstract
Optimizing the utilization of huge data sets is a challenging problem for weather prediction. To a significant degree, prediction accuracy is determined by the data used in model initialization, assimilated from a variety of observational platforms. At present, the volume of weather data collected in a given day greatly exceeds the ability of assimilation systems to make use of it. Typically, data is ingested uniformly at the highest fixed resolution that enables the numerical weather prediction (NWP) model to deliver its prediction in a timely fashion. In order to make more efficient use of newly available high-resolution data sources, we seek to identify regions of interest (ROI) where increased data quality or volume is likely to significantly enhance weather prediction accuracy. In particular, we wish to improve the utilization of data from the recently launched Geostationary Operation Environmental Satellite (GOES)-16, which provides orders of magnitude more data than its predecessors. To achieve this, we demonstrate a method for locating tropical cyclones using only observations of precipitable water, which is evaluated using the Global Forecast System (GFS) weather prediction model. Most state of the art hurricane detection techniques rely on multiple feature sets, including wind speed, wind direction, temperature, and IR emissions, potentially from multiple data sources. In contrast, we demonstrate that this model is able to achieve comparable performance on historical tropical cyclone data sets, using only observations of precipitable water.
Keywords
Numeric weather prediction Satellite Machine learning Data assimilation Tropical cyclone Precipitable water Water vapor Global Forecast System (GFS)Notes
Acknowledgement
This work was carried out at NOAA Earth System Research Laboratory (ESRL), University of Colorado Boulder with funding from NOAA. The first author is supported by funding from NOAA Award Number NA14OAR4320125 and the third author is supported by funding from NOAA Award Number NA17OAR4320101. The authors thank Christina Bonfanti for her help to suggest alternative best tracking data produced by NOAA.
References
- 1.Global forecast system (GFS). https://www.ncdc.noaa.gov/data-access/model-data/model-datasets/global-forcast-system-gfs
- 2.Cecil, D.J., Zipser, E.J.: Relationships between tropical cyclone intensity and satellite-based indicators of inner core convection: 85-GHZ ice-scattering signature and lightning. Mon. Weather Rev. 127(1), 103–123 (1999)CrossRefGoogle Scholar
- 3.Dvorak, V.F.: Tropical cyclone intensity analysis and forecasting from satellite imagery. Mon. Weather Rev. 103(5), 420–430 (1975)CrossRefGoogle Scholar
- 4.Ho, S.-S., Talukder, A.: Automated cyclone discovery and tracking using knowledge sharing in multiple heterogeneous satellite data. In: Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 928–936. ACM (2008)Google Scholar
- 5.Ho, S.-S., Talukder, A.: Automated cyclone identification from remote QuikSCAT satellite data. In: 2008 IEEE Aerospace Conference, pp. 1–9. IEEE (2008)Google Scholar
- 6.Jaiswal, N., Kishtawal, C.M., Pal, P.K.: Cyclone intensity estimation using similarity of satellite IR images based on histogram matching approach. Atmos. Res. 118, 215–221 (2012)CrossRefGoogle Scholar
- 7.Knapp, K.R., Kruk, M.C., Levinson, D.H., Diamond, H.J., Neumann, C.J.: The international best track archive for climate stewardship (IBTrACS) unifying tropical cyclone data. Bull. Am. Meteorol. Soc. 91(3), 363–376 (2010)CrossRefGoogle Scholar
- 8.Liu, Y., et al.: Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv preprint arXiv:1605.01156 (2016)
- 9.McBride, J.L., Zehr, R.: Observational analysis of tropical cyclone formation. Part II: comparison of non-developing versus developing systems. J. Atmos. Sci. 38(6), 1132–1151 (1981)CrossRefGoogle Scholar
- 10.Mueller, K.J., DeMaria, M., Knaff, J., Kossin, J.P., Vonder Haar, T.H.: Objective estimation of tropical cyclone wind structure from infrared satellite data. Weather Forecast. 21(6), 990–1005 (2006)CrossRefGoogle Scholar
- 11.Panangadan, A., Ho, S.-S., Talukder, A.: Cyclone tracking using multiple satellite image sources. In: Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, pp. 428–431. ACM (2009)Google Scholar
- 12.Ryan, B.F., Watterson, I.G., Evans, J.L.: Tropical cyclone frequencies inferred from gray’s yearly genesis parameter: validation of GCM tropical climates. Geophys. Res. Lett. 19(18), 1831–1834 (1992)CrossRefGoogle Scholar
- 13.Velden, C.S., Olander, T.L., Wanzong, S.: The impact of multispectral goes-8 wind information on Atlantic tropical cyclone track forecasts in 1995. Part I: dataset methodology, description, and case analysis. Mon. Weather Rev. 126(5), 1202–1218 (1998)CrossRefGoogle Scholar
- 14.Zhuge, X.-Y., Guan, J., Yu, F., Wang, Y.: A new satellite-based indicator for estimation of the western North Pacific tropical cyclone current intensity. IEEE Trans. Geosci. Remote Sens. 53(10), 5661–5676 (2015)CrossRefGoogle Scholar
- 15.Zou, J., Lin, M., Xie, X., Lang, S., Cui, S.: Automated typhoon identification from QuikSCAT wind data. In: 2010 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 4158–4161. IEEE (2010)Google Scholar