Deep Neural Network Cloud-Type Classification (DeepCTC) Model and Its Application in Evaluating PERSIANN-CCS

Abstract

Satellite remote sensing plays a pivotal role in characterizing hydrometeorological components including cloud types and their associated precipitation. The Cloud Profiling Radar (CPR) on the Polar Orbiting CloudSat satellite has provided a unique dataset to characterize cloud types. However, data from this nadir-looking radar offers limited capability for estimating precipitation because of the narrow satellite swath coverage and low temporal frequency. We use these high-quality observations to build a Deep Neural Network Cloud-Type Classification (DeepCTC) model to estimate cloud types from multispectral data from the Advanced Baseline Imager (ABI) onboard the GOES-16 platform. The DeepCTC model is trained and tested using coincident data from both CloudSat and ABI over the CONUS region. Evaluations of DeepCTC indicate that the model performs well for a variety of cloud types including Altostratus, Altocumulus, Cumulus, Nimbostratus, Deep Convective and High clouds. However, capturing low-level clouds remains a challenge for the model. Results from simulated GOES-16 ABI imageries of the Hurricane Harvey event show a large-scale perspective of the rapid and consistent cloud-type monitoring is possible using the DeepCTC model. Additionally, assessments using half-hourly Multi-Radar/Multi-Sensor (MRMS) precipitation rate data (for Hurricane Harvey as a case study) show the ability of DeepCTC in identifying rainy clouds, including Deep Convective and Nimbostratus and their precipitation potential. We also use DeepCTC to evaluate the performance of the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks-Cloud Classification System (PERSIANN-CCS) product over different cloud types with respect to MRMS referenced at a half-hourly time scale for July 2018. Our analysis suggests that DeepCTC provides supplementary insights into the variability of cloud types to diagnose the weakness and strength of near real-time GEO-based precipitation retrievals. With additional training and testing, we believe DeepCTC has the potential to augment the widely used PERSIANN-CCS algorithm for estimating precipitation.

Applying machine learning methods to detect convection using Geostationary Operational Environmental Satellite-16 (GOES-16) advanced baseline imager (ABI) data

“…Machine learning and in particular neural networks are emerging in many remote sensing applications for clouds (Mahajan and Fataniya, 2020). Application of neural networks has led to more use of geostationary satellite data in cloud-related products such as cloud type classification or rainfall rate estimation, which has been challenging in the past (Bankert et al, 2009;Afzali Gorooh et al, 2020;Hayatbini et al, 2019;Hirose et al, 2019). Especially using GOES-16, raining clouds are detected by Liu et al (2019) with a deep neural network model, and radar reflectivity is estimated by Hilburn et al (2020) using a model with convolutional layers.…”

A Model Tree Generator (MTG) Framework for Simulating Hydrologic Systems: Application to Reservoir Routing

“…Figure 10 shows the normalized RMSE values for the training data set for the cross-validation in red. In most cases, MTG (1) and MTG(2) shows superior performance over training data, except for case (c). The superior performance of the MTG is due to the regressed lines employed in the terminal nodes.…”

“…Data-driven models are effective tools for simulating nonlinear and complex systems, and have been widely used for regression and classification problems [1,2]. These models rely on statistical and numerical approaches for simulating the underlying system, rather than employing physics-based equations [3,4].…”

Four Decades of Intensifying Precipitation from Tropical Cyclones

“…One of the barriers to making a conclusive assessment of historic TC precipitation is the lack of high-resolution and global precipitation data available for over 30 years, the minimum duration set by the World Meteorological Organization (WMO) for climate scale studies. Thanks to the rapid advancement of satellite precipitation estimating algorithms (Hayatbini et al 2019, Afzali Gorooh et al 2020, Sadeghi et al 2020, the first High-Resolution Precipitation Climate Data Records (HRPCDR) are being produced, making precipitation measurements at 0.04° and subdaily spatiotemporal resolution available back to 1980. Available at higher spatiotemporal resolutions than other CDRs of precipitation like Precipitation Estimates from Remotely Sensed Information using Artificial Neural Networks-CDR (PERSIANN-CDR; Ashouri et al 2015) and Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS; Funk et al 2015), HRPCDRs are shown to better capture the pattern and intensity of the most intense precipitation rates-an invaluable improvement to accurately assess TC precipitation.…”