From Vern's Vision to Computer Vision: The Evolution of Tropical Cyclone Intensity Estimation from Satellite Data

The contribution of Vern Dvorak’s technique for estimation of Tropical Cyclone (TC) intensities from satellites cannot be overstated. In the BAMS article chronicling the method, Velden et al. 2006 stated “The Dvorak Techniques practical appeal and demonstrated skill in the face of dynamic complexity place it among the great meteorological innovations of our time. It is difficult to think of any other meteorological technique that has withstood the test of time and had the same life-saving impact.” The Dvorak Technique’s (DT) enduring usefulness stems from both the concept’s insightful premise that organized convective cloud features and patterns from satellite imagery are related to intensity, and the method’s ability to easily teach analysts how to discern complex cloud patterns and morphology over a broad range of TC intensities. Minor changes have been implemented to the DT over time as use and knowledge on how to best apply the method accrued, especially to account for rapid intensity changes, to address some of the now-known biases, and to improve the DT’s performance in specific TC basins via local TC forecast center expertise. Nearly 50 years later, the method remains a primary tool used by TC warning agencies throughout the world.

The DT method was created in the 1970s and early 1980s when operational weather satellites were limited to visible and IR channels viewing clouds and patterns. When only visible and IR data is available, for most TCs analysts can only see the cloud tops dominated by a central dense overcast (CDO), not critical mid and lower-level storm structure. This can often lead to uncertain center locations and degraded intensity estimates that are dependent on accurate storm position. However, low Earth orbiter (LEO) passive microwave (PMW) imagers and sounders emerged in the late 1980s and opened the door to utilize the best of both worlds: frequent geostationary satellite IR and visible scanning and the “into the cloud” TC structure snapshots from LEO PMW. Thermal channels on microwave sounders are able to depict TC warm core anomalies, and automated algorithms have been developed to relate those anomalies to TC intensity with good success. In addition, active microwave sensors (scatterometers and synthetic aperture radar) became available in the 1990s and 2000s that enabled sensing through rain areas to the ocean surface and derived ocean surface wind vectors thereby providing horizontal surface wind structure.

More recently, automated algorithms such as the Advanced Dvorak Technique (ADT) and Digital Dvorak have been developed in an attempt to ameliorate some of the inherent analyst subjectivity in the DT method. These automated techniques benefit from much improved spatiotemporal resolution of the global geostationary satellite sensors and take only minutes to run computationally, thereby producing intensity estimates at much greater frequency. The ADT is publically available and can be utilized worldwide by TC analysts who have access to the satellite data. Furthermore, the ADT does not require many months of training to produce skillful estimates the way the DT does. The ADT has matured to operational status and now sits alongside the DT as a tool routinely used by global warning agencies.

In the present age we see a transformation underway within the satellite community to harness the power of deep learning tools to analyze satellite imagery and extract key TC properties such as intensity. Deep-learning based tools now have the ability to analyze TCs in ways that Dvorak did, and more. The techniques are being applied to a wide spectrum of satellite frequencies including infrared, visible and microwave and are leading to improvements in satellite-based TC intensity estimates. Despite the adoption of these state-of-the-art methods, Vern’s technique developed 50 years ago remains in use today. This presentation will explore the path from Vern’s ubiquitous DT to the modern day application of deep learning methods to satellite imagery and how they might shed light on what it was that Vern saw in those thousands of images he analyzed with his talented vision.