The Deep Learning-based Hurricane Intensity Estimator uses neural networks to deliver live hurricane wind speed estimates as soon as satellite data is available, removing the human bottleneck from hurricane assessment and reducing the time to alert authorities about fast-changing severe weather.
Overview
Development Seed partnered with NASA ODSI's Machine Learning team at Marshall Space Flight Center to build a cloud-based system that applies deep learning to live satellite imagery. The system estimates hurricane strength and wind speed up to every 30 seconds, a dramatic improvement over the traditional six-hour cycle that relies on meteorologists manually classifying storms.
Challenge
Hurricane intensity estimates traditionally depend on meteorologists manually matching satellite imagery to known storm patterns. This process is slow and can't keep pace with rapidly changing severe weather. With hurricane seasons growing more destructive, faster and more reliable wind speed estimates are needed to help protect lives and property.
Outcome
A fully automated, cloud-native hurricane estimation pipeline built on NASA Cumulus that ingests live satellite imagery, runs deep learning models at scale, and delivers results through an interactive map explorer and an open API for integration into weather apps, alerting systems, and other decision-making tools.
Development Seed partnered with the Machine Learning team within the Office of Data Science and Informatics (ODSI) at NASA’s Marshall Space Flight Center to create the Deep Learning-based Hurricane Intensity Estimator. This platform uses advanced deep learning techniques to deliver live hurricane wind speed estimates as soon as the data comes off the satellite. This approach has the potential to remove the human bottleneck in hurricane estimation, drastically reducing the time to alert authorities to fast-changing severe weather.
Faster Hurricane Estimates
The primary factor for estimating a hurricane’s destructive potential is wind speed. By creating faster, more reliable estimates of storm wind speeds, authorities may be able to make better decisions about moving people out of harm’s way and moving resources where they’re needed. These decisions can help save both life and property. The issue is growing in urgency: the 2017 hurricane season was the most destructive on record, claiming thousands of lives and causing an estimated $280 billion in damage.
Currently, estimates of cyclone intensity rely upon human application of the Dvorak technique. Meteorologists match satellite imagery of a storm to known patterns. Once matched, it’s possible to estimate wind speed. AI experts at NASA’s Marshall Space Flight Center and Development Seed trained neural networks using historical hurricane imagery and classifications, allowing this workflow to be fully automated.
Working with NASA, we developed a cloud-based approach to apply advanced deep learning techniques at speed and scale. Our approach calculates hurricane strength and wind speed by monitoring live imagery as it’s delivered from weather satellites. This allows NASA to create estimates as fast as the data is delivered, up to every 30 seconds, a significant speedup from the usual six-hour cycle. While we test and refine the model, the system is producing hurricane estimates every hour.
Fast, Continuous Predictions on the Cloud
NASA scientists continuously refine and improve and improve the model using new data and techniques. They need an easy way to test and publish new models and to rerun new models on historic imagery. Cumulus was built precisely for this sort of orchestration of earth observation workflows. We use Cumulus to manage our imagery acquisition and storage; track the code for various versions of the prediction algorithm; rerun new models on prior data; and to create an audit trail of what code was used to produce which results. This system provides NASA scientists with a highly scaleable, reliable, and flexible system that allows them to focus on doing great science.
Data for action
Through the 2018 and 2019 hurricane season we are testing and refining the model to assess its accuracy and utility. As the model improves, we anticipate it may provide one vital input for human and automated decision systems. We designed the system for all these users in mind.
For decision-makers, we built a highly usable data explorer using Mapbox. This tool shows the latest model predictions and allows point-by-point comparison with imagery and data from other sources. All of our results are provided as an API that allows this data to be integrated into other platforms, from weather apps to alerting systems.
Resources
- Paper: Tropical Cyclone Intensity Estimation Using a Deep Convolutional Neural Network
- API Documentation
About NASA ODSI (formerly known as IMPACT)
NASA’s Marshall Space Flight Center Office of Data Science and Informatics (ODSI) is the agency’s premier center for data science innovation, driving groundbreaking scientific discoveries, and pioneering technological advancements and applications across all scientific fields. ODSI partners with Development Seed to advance NASA science through enhanced data science infrastructures and informatics, providing cutting-edge expertise, tools, and capacity building to support key programs and drive transformative scientific breakthroughs.
Have a challenging project that could use our help?
Let's connect
We'd love to hear from you.