skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


  • NSF Public Access
  • Search Results
  • Applying machine learning methods to detect convection using Geostationary Operational Environmental Satellite-16 (GOES-16) advanced baseline imager (ABI) data
Title: Applying machine learning methods to detect convection using Geostationary Operational Environmental Satellite-16 (GOES-16) advanced baseline imager (ABI) data
Abstract. An ability to accurately detect convective regions isessential for initializing models for short-term precipitation forecasts.Radar data are commonly used to detect convection, but radars that providehigh-temporal-resolution data are mostly available over land, and the qualityof the data tends to degrade over mountainous regions. On the other hand,geostationary satellite data are available nearly anywhere and in near-realtime. Current operational geostationary satellites, the GeostationaryOperational 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 andinfrared data even without vertical information of the convective system.Existing detection algorithms using visible and infrared data look forstatic features of convective clouds such as overshooting top or lumpy cloudtop surface or cloud growth that occurs over periods of 30 min to anhour. This study represents a proof of concept that artificial intelligence(AI) is able, when given high-spatial- and high-temporal-resolution data fromGOES-16, to learn physical properties of convective clouds and automate thedetection process. A neural network model with convolutional layers is proposed to identifyconvection from the high-temporal resolution GOES-16 data. The model takesfive temporal images from channel 2 (0.65 µm) and 14 (11.2 µm) asinputs and produces a map of convective regions. In order to provideproducts comparable to the radar products, it is trained against Multi-RadarMulti-Sensor (MRMS), which is a radar-based product that uses a rathersophisticated method to classify precipitation types. Two channels fromGOES-16, each related to cloud optical depth (channel 2) and cloud topheight (channel 14), are expected to best represent features of convectiveclouds: high reflectance, lumpy cloud top surface, and low cloud toptemperature. The model has correctly learned those features of convectiveclouds and resulted in a reasonably low false alarm ratio (FAR) and highprobability of detection (POD). However, FAR and POD can vary depending onthe threshold, and a proper threshold needs to be chosen based on thepurpose.  more » « less
Award ID(s):
2019758
PAR ID:
10422689
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
Atmospheric Measurement Techniques
Volume:
14
Issue:
4
ISSN:
1867-8548
Page Range / eLocation ID:
2699 to 2716
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Monthly Weather Review)
    Abstract The evolution of model-based cloud-top brightness temperatures (BT) associated with convective initiation (CI) is assessed for three bulk cloud microphysics schemes in the Weather Research and Forecasting Model. Using a composite-based analysis, cloud objects derived from high-resolution (500 m) model simulations are compared to 5-minGOES-16imagery for a case study day located near the Alabama–Mississippi border. Observed and simulated cloud characteristics for clouds reaching CI are examined by utilizing infrared BTs commonly used in satellite-based CI nowcasting methods. The results demonstrate the ability of object-based verification methods with satellite observations to evaluate the evolution of model cloud characteristics, and the BT comparison provides insight into a known issue of model simulations producing too many convective cells reaching CI. The timing of CI from the different microphysical schemes is dependent on the production of ice in the upper levels of the cloud, which typically occurs near the time of maximum cloud growth. In particular, large differences in precipitation formation drive differences in the amount of cloud water able to reach upper layers of the cloud, which impacts cloud-top glaciation. Larger cloud mixing ratios are found in clouds with sustained growth leading to more cloud water lofted to the upper levels of the cloud and the formation of ice. Clouds unable to sustain growth lack the necessary cloud water needed to form ice and grow into cumulonimbus. Clouds with slower growth rates display similar BT trends as clouds exhibiting growth, which suggests that forecasting CI using geostationary satellites might require additional information beyond those derived at cloud top. 
    more » « less
  2. ; ; ; ; ; ; (, Artificial Intelligence for the Earth Systems)
    Abstract Geostationary satellite imagers provide historical and near-real-time observations of cloud-top patterns that are commonly associated with severe convection. Environmental conditions favorable for severe weather are thought to be represented well by reanalyses. Predicting exactly where convection and costly storm hazards like hail will occur using models or satellite imagery alone, however, is extremely challenging. The multivariate combination of satellite-observed cloud patterns with reanalysis environmental parameters, linked to Next Generation Weather Radar (NEXRAD) estimated maximum expected size of hail (MESH) using a deep neural network (DNN), enables estimation of potentially severe hail likelihood for any observed storm cell. These estimates are made where satellites observe cold clouds, indicative of convection, located in favorable storm environments. We seek an approach that can be used to estimate climatological hailstorm frequency and risk throughout the historical satellite data record. Statistical distributions of convective parameters from satellite and reanalysis show separation between nonsevere and severe hailstorm classes for predictors that include overshooting cloud-top temperature and area characteristics, vertical wind shear, and convective inhibition. These complex, multivariate predictor relationships are exploited within a DNN to produce a likelihood estimate with a critical success index of 0.511 and Heidke skill score of 0.407, which is exceptional among analogous hail studies. Furthermore, applications of the DNN to case studies demonstrate good qualitative agreement between hail likelihood and MESH. These hail classifications are aggregated across an 11-yr Geostationary Operational Environmental Satellite (GOES) image database fromGOES-12/13to derive a hail frequency and severity climatology, which denotes the central Great Plains, the Midwest, and northwestern Mexico as being the most hail-prone regions within the domain studied. 
    more » « less
  3. ; (, Journal of Hydrometeorology)
    Abstract Observations of clouds and precipitation in the microwave domain from the active dual-frequency precipitation radar (DPR) and the passive Global Precipitation Measurement (GPM) Microwave Imager (GMI) onboard the GPMCore Observatorysatellite are used in synergy with cloud tracking information derived from infrared imagery from theGOES-13andMeteosat-7geostationary satellites for analysis of the life cycle of precipitating cloud systems, in terms of temporal evolution of their macrophysical characteristics, in several oceanic and continental regions of the tropics. The life cycle of each one of the several hundred thousand cloud systems tracked during the 2-yr (2015–16) analysis period is divided into five equal-duration stages between initiation and dissipation. The average cloud size, precipitation intensity, precipitation top height, and convective and stratiform precipitating fractions are documented at each stage of the life cycle for different cloud categories (based upon lifetime duration). The average life cycle dynamics is found remarkably homogeneous across the different regions and is consistent with previous studies: systems peak in size around midlife; precipitation intensity and convective fraction tend to decrease continuously from the initiation stage to the dissipation. Over the three continental regions, Amazonia (AMZ), central Africa (CAF), and Sahel (SAH), at the early stages of clouds’ life cycle, precipitation estimates from the passive GMI instrument are systematically found to be 15%–40% lower than active radar estimates. By highlighting stage-dependent biases in state-of-the-art passive microwave precipitation estimates over land, we demonstrate the potential usefulness of cloud tracking information for improving retrievals and suggest new directions for the synergistic use of geostationary and low-Earth-orbiting satellite observations. 
    more » « less
  4. ; ; ; (, Artificial Intelligence for the Earth Systems)
    Abstract Convective initiation (CI) nowcasting remains a challenging problem for both numerical weather prediction models and existing nowcasting algorithms. In this study, an object-based probabilistic deep learning model is developed to predict CI based on multichannel infraredGOES-16satellite observations. The data come from patches surrounding potential CI events identified in Multi-Radar Multi-Sensor Doppler weather radar products over the Great Plains region from June and July 2020 and June 2021. An objective radar-based approach is used to identify these events. The deep learning model significantly outperforms the classical logistic model at lead times up to 1 h, especially on the false alarm ratio. Through case studies, the deep learning model exhibits dependence on the characteristics of clouds and moisture at multiple altitudes. Model explanation further reveals that the contribution of features to model predictions is significantly dependent on the baseline, a reference point against which the prediction is compared. Under a moist baseline, moisture gradients in the lower and middle troposphere contribute most to correct CI forecasts. In contrast, under a clear-sky baseline, correct CI forecasts are dominated by cloud-top features, including cloud-top glaciation, height, and cloud coverage. Our study demonstrates the advantage of using different baselines in further understanding model behavior and gaining scientific insights. 
    more » « less
  5. ; ; ; ; ; (, Weather and Forecasting)
    Abstract This research attempts to use operational radar and satellite products to identify potential locations of quasi-linear convective system (QLCS) tornadogenesis, which can be difficult to predict. It is hypothesized that deep, discrete updrafts indicate portions of the QLCS capable of producing tornadoes, whereas shallower convection indicates more benign portions of the QLCS. To address this hypothesis, storm reports and storm surveys on 30–31 March 2022, during the second intensive observing period of the 2022 Propagation, Evolution, and Rotation in Linear Storms (PERiLS) field campaign, are used to identify locations of tornadoes within the QLCS. These tornado locations are then compared to representations of upper-tropospheric updrafts, namely, overshooting tops (OTs), which are identified with an algorithm using 1-min-resolution mesoscale sector data fromGOES-16Advanced Baseline Imager infrared brightness temperatures, and radar reflectivity cores aloft, identified with Multi-Radar Multi-Sensor (MRMS) 3D mosaic reflectivity products. Only a fraction (less than 30%) of tornadoes within the QLCS are associated with OTs, though over 85% of tornadoes are located near convective cores as indicated by cores of enhanced reflectivity at 9 km MSL. A numerical simulation of the event is also conducted using the Weather Research and Forecasting (WRF) Model which shows a strong relationship between simulated updraft intensity and reflectivity aloft. Given this apparent support of the hypothesis, the identification of updraft signatures within MRMS and high-resolution geostationary satellite data may ultimately help improve the identification of regions within QLCSs most likely to result in tornadoes. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email