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.
Highlights
Clouds play a crucial role, as an element of the Earth system, in a wide range of hydrometeorological and engineering applications, yet there is not a deep understating of their physical dynamics
In order to assess the performance of the Deep Neural Network Cloud-Type Classification (DeepCTC) model, common statistical verification indices for multi-class classification models are reported; some sample cloud-type results from GOES-16 Advanced Baseline Imager (ABI) imageries during Hurricane Harvey are illustrated over the Continental United States (CONUS)
We examine the performance of PERSIANN-CCS with reference to MRMS data utilizing volumetric categorical indices [63] such as Volumetric Hit Index (VHI), Volumetric False Alarm Ratio (VFAR) and Volumetric Critical Success Index (VCSI) in addition to Probability of Detection (POD), False Alarm Ratio (FAR) and Critical Success Index (CSI)
Summary
Clouds play a crucial role, as an element of the Earth system, in a wide range of hydrometeorological and engineering applications, yet there is not a deep understating of their physical dynamics. Recent developments in satellite technologies resulting in higher temporal, spatial and spectral resolutions, along with advancements in machine learning techniques and computational power, open great opportunities to develop efficient near real-time models to characterize cloud types and their behaviors. The history of satellite-based cloud detection using infrared and visible imageries began with studies by Booth [3] and Hughes [4], followed by Goodman and Henderson-Sellers [5], Rossow [6], Rossow and Garder [7], Wielicki and Parker [8], Key [9], Yhann and Simpson [10]. Several methods have been developed to classify clouds from single- or multispectral satellite imageries, including threshold-based [12,13,14,15,16] and machine learning approaches. A large number of studies have addressed satellite cloud-type classification from a variety of perspectives but they rely on specific regions. It should be pointed out that the computational expenses and complexity of the implementation of these models are challenging
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call