Abstract
Abstract. An ability to accurately detect convective regions is essential for initializing models for short-term precipitation forecasts. Radar data are commonly used to detect convection, but radars that provide high-temporal-resolution data are mostly available over land, and the quality of the data tends to degrade over mountainous regions. On the other hand, geostationary satellite data are available nearly anywhere and in near-real time. Current operational geostationary satellites, the Geostationary Operational Environmental Satellite-16 (GOES-16) and Satellite-17, provide high-spatial- and high-temporal-resolution data but only of cloud top properties; 1 min data, however, allow us to observe convection from visible and infrared data even without vertical information of the convective system. Existing detection algorithms using visible and infrared data look for static features of convective clouds such as overshooting top or lumpy cloud top surface or cloud growth that occurs over periods of 30 min to an hour. This study represents a proof of concept that artificial intelligence (AI) is able, when given high-spatial- and high-temporal-resolution data from GOES-16, to learn physical properties of convective clouds and automate the detection process. A neural network model with convolutional layers is proposed to identify convection from the high-temporal resolution GOES-16 data. The model takes five temporal images from channel 2 (0.65 µm) and 14 (11.2 µm) as inputs and produces a map of convective regions. In order to provide products comparable to the radar products, it is trained against Multi-Radar Multi-Sensor (MRMS), which is a radar-based product that uses a rather sophisticated method to classify precipitation types. Two channels from GOES-16, each related to cloud optical depth (channel 2) and cloud top height (channel 14), are expected to best represent features of convective clouds: high reflectance, lumpy cloud top surface, and low cloud top temperature. The model has correctly learned those features of convective clouds and resulted in a reasonably low false alarm ratio (FAR) and high probability of detection (POD). However, FAR and POD can vary depending on the threshold, and a proper threshold needs to be chosen based on the purpose.
Highlights
Artificial intelligence (AI) is flourishing more than ever as we live in the era of big data and increased processing power
Features that distinguish this work from existing work are as follows: (1) studies using machine learning with geostationary satellite data are typically designed for the goal of rainfall rate estimations or classification of various cloud types, while our goal is to detect convection so that appropriate heating can be added to initiate convection in the forecast model; (2) we feed temporal sequences of Geostationary Operational Environmental Satellite-16 (GOES-16) imagery into the neural network model to provide the algorithm with the same information a human would find useful to detect the bubbling texture in GOES-16 imagery indicative of convection; (3) we use a two-step loss function approach which makes the model’s performance less sensitive to threshold choice
false alarm ratio (FAR), probability of detection (POD), success ratio (SR), and critical success index (CSI) can be calculated from the equations below
Summary
Artificial intelligence (AI) is flourishing more than ever as we live in the era of big data and increased processing power. Atmospheric science, with vast quantities of satellite and model data, is not an exception. Numerical weather prediction and remote sensing are ideally suited to machine learning as weather forecasts can be generated on demand, and satellite data are available around the globe (Boukabara et al, 2019). Applying machine learning to forecast models can be beneficial in many ways. It can improve computational efficiency of model physics parameterizations (Krasnopolsky et al, 2005) as well as the development of new parameterizations (O’Gorman and Dwyer, 2018; Brenowitz and Bretherton, 2018; Beucler et al, 2019; Gentine et al, 2018; Rasp et al, 2018; Krasnopolsky et al, 2013).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have