Hilburn, Kyle2022-06-232022-06-232022https://hdl.handle.net/10217/235392http://dx.doi.org/10.25675/10217/235392This is the dataset used to train and test the GREMLIN Version-1 model in Hilburn et al. (2021). It consists of GOES-16 ABI, GOES-16 GLM, and MRMS data resampled to the 3 km HRRR grid and matched in time. The samples consist of 256 x 256 pixel images covering severe storms for 6-hour periods with 15-minute refresh over a 92 day period. The time period runs from 2019-04-18 to 2019-07-18. The spatial coverage is eastern CONUS ranging from 29.577 to 48.002 degrees_north latitude and -106.766 to -75.184 degrees_east longitude.Cooperative Institute for Research in the AtmosphereThe objective of this research is to develop techniques for assimilating GOES-R series observations in precipitating scenes for the purpose of improving short-term convective-scale forecasts of high-impact weather hazards. Whereas one approach is radiance assimilation, the information content of GOES-R radiances from its Advanced Baseline Imager saturates in precipitating scenes, and radiance assimilation does not make use of lightning observations from the GOES Lightning Mapper. Here, a convolutional neural network (CNN) is developed to transform GOES-R radiances and lightning into synthetic radar reflectivity fields to make use of existing radar assimilation techniques. We find that the ability of CNNs to utilize spatial context is essential for this application and offers breakthrough improvement in skill compared to traditional pixel-by-pixel based approaches. To understand the improved performance, we use a novel analysis method that combines several techniques, each providing different insights into the network’s reasoning. Channel-withholding experiments and spatial information–withholding experiments are used to show that the CNN achieves skill at high reflectivity values from the information content in radiance gradients and the presence of lightning. The attribution method, layerwise relevance propagation, demonstrates that the CNN uses radiance and lightning information synergistically, where lightning helps the CNN focus on which neighboring locations are most important. Synthetic inputs are used to quantify the sensitivity to radiance gradients, showing that sharper gradients produce a stronger response in predicted reflectivity. Lightning observations are found to be uniquely valuable for their ability to pinpoint locations of strong radar echoes.NetCDFPDFengGOES-RGOES-16ABIGLMMRMSinfrared brightness temperaturelightningradar reflectivitymachine learningGREMLINDatasetThis material is open access and distributed under the terms and conditions of the Creative Commons CC BY: Attribution 4.0 International license (https://creativecommons.org/licenses/by/4.0/).