In this paper, a machine learning system is introduced to improve satellite-based rainfall retrievals by incorporating the high resolution radar observations from the DFW network. In particular, the National Oceanic and Atmospheric Administration (NOAA) Climate Prediction Center has developed a morphing technique (i.e., CMORPH) is first applied to derive combined PMW-based retrievals and combined IR data from multiple satellites (Joyce et al. 2014; Xie et al. 2017). The combined PMW-based retrievals and IR data then serve as input to the proposed machine learning model. The high-quality DFW rainfall products are used as target to train the model. The model training with a large number of precipitation events is detailed. The trained model is evaluated using existing CMORPH products and surface rainfall measurements from gauge networks during independent (testing) precipitation events.
References
Chandrasekar, V., H. Chen, and B. Philips, 2017: Principles of High-Resolution Radar Network for Hazard Mitigation and Disaster Management in an Urban Environment. Journal of the Meteorological Society of Japan, (in press)
Chen, H., and V. Chandrasekar, 2015: The Quantitative Precipitation Estimation System for Dallas- Fort Worth (DFW) Urban Remote Sensing Network. Journal of Hydrology, 531, 259-271.
Joyce, R.J., J.E. Janowiak, P.A. Arkin, and P. Xie, 2004: CMORPH: A Method that Produces Global Precipitation Estimates from Passive Microwave and Infrared Data at High Spatial and Temporal Resolution. J. Hydrometeor., 5, 487-503.
Xie, P., R. Joyce, S. Wu, S. Yoo, Y. Yarosh, F. Sun, and R. Lin, 2017: Reprocessed, Bias-Corrected CMORPH Global High-Resolution Precipitation Estimates from 1998. J. Hydrometeor., 18, 1617-1641.
![](images/flag.png)
![](images/blue_ribbon.png)