Kx and NASA FDL: Space Weather, GNSS and Exoplanets

10 Jul 2018 | , ,
Share on:

By Robert Hill

Kx is delighted to once more be partnering with the NASA Frontier Development Laboratory (NASA FDL) team on two exciting challenges facing the space sector. This follows from last year’s successful solar activity detection work, which resulted in the ‘FlareNet’ tool (supported by Kx and Lockheed Martin) that demonstrated the potential for AI assisted solar weather prediction.

The first challenge, which is related to space weather, will be to include the application of Global Navigation Satellite Systems (GNSS) data as a tool for monitoring solar activity and ionospheric modelling. This research is based on the fact that GPS signals are affected by the solar environment in a way that allows deductions to be made about the behavior of our planet’s ionosphere as it is battered by the solar wind.

This is very exciting as it is a relatively new domain requiring solutions. The ability to utilize the power of Kx to provide real-time insights from time-series data will be a useful resource for both science and commercial applications. Potential applications include spacecraft management and space traffic management because this research fills a crucial gap in knowledge for the future of global space operations.

Kx will be partnering with NASA FDL, Lockheed Martin and IBM on this challenge.

The second challenge takes us completely out of our solar system and into the cosmos, searching for planets that orbit around other stars, termed exoplanets, using data from the brand new NASA Transiting Exoplanet Survey Satellite, or TESS.

TESS will revolutionize how we directly perceive the universe, providing new insight into entirely new solar systems.

As you can imagine, finding planets, which are relatively small and dull compared to their very bright and large parent star is a very difficult challenge. The challenge is made even more demanding as follow-up observations need to be identified every 27 days as the spacecraft changes its field of view. At the moment, diagnosis of exoplanet candidates still requires manual analysis – a tremendous challenge for humans in the time window available. This time crunch problem remains unresolved, and is suited to AI approaches by automating the classification analysis currently done by human experts.

Developing this machine learning tool for hunting exoplanets will also give Kx fantastic inroads to other avenues of exploration requiring the automation of processes in relation to change detection and feature extraction, widely used in the observation of the Earth.

 

SUGGESTED ARTICLES

ML and kdb+

Machine Learning Toolkit Update: Cross-Validation and ML Workflow in kdb+

23 Jul 2019 | , ,

The Kx machine learning team has an ongoing project of periodically releasing useful machine learning libraries and notebooks for kdb+. This release relates to the areas of cross-validation and standardized code distribution procedures for incorporating both Python and q distribution. Such procedures are used in feature creation through the FRESH algorithm and cross-validation within kdb+/q.

kx and machine learning

Machine Learning Toolkit Update: Multi-parameter FRESH and updated utilities

25 Apr 2019 | , ,

This latest toolkit release, is the first in a series of planned releases in 2019 that will add updates to the functionality of the FRESH (Feature Extraction based on Scalable Hypothesis tests) algorithm and the addition of a number of accuracy metrics, preprocessing functions and utilities. In conjunction with code changes, modifications to the namespace structure of the toolkit have been made to streamline the code and improve user experience.