We will be in contact shortly.
Kdb Insights
Kdb Insights Overview
Built for The Modern Data Ecosystem
Unified for Richer Analytics
Faster Return on Investment
PyKX Python Interoperability
Services & Support
Financial Services Use Cases
FX Solutions
Quant Research
Surveillance
Trading Analytics
Industry & IoT Use Cases
Automotive
Energy & Utilities
Manufacturing
Telco
Services & Support
Learn
Overview
Featured Courses
KX Academy
Connect
KX Community
Community Events
Developer Blog
Build
Download
Documentation
Support
About Us
Partner with Us
Become a Partner
Find a Partner
Partner Signup
Join Us
Connect with Us
By Diane O’Donoghue
The Frontier Development Lab (FDL) is a public private partnership run annually with both the European Space Agency (ESA) and National Aeronautics and Space Administration (NASA). The objective of FDL is to bring together researchers from the Artificial Intelligence (AI) and space science sectors to tackle a broad spectrum of challenges in the space industry.
This year, I spent eight weeks over the summer collaborating with the participants of FDL, hosted in California by the SETI Institute. The projects included challenges in lunar and heliophysics research, astronaut health and disaster prevention. This whitepaper focuses on the Disaster Prevention, Progress and Response (Floods) challenge, for which KX was a partner.
Floods are one of the most dangerous natural disasters worldwide. All regions can be affected by flooding events and, with the increased variability in weather patterns due to global warming, this is likely to become even more prevalent . The speed at which flooding events can occur, and difficulties in predicting their occurrence, create huge logistic problems for both governmental and non-governmental agencies. Worldwide, floods cost in excess of 40 Billion dollars per year, impacting property, agriculture and the health of individuals.
In particular, this whitepaper looks at the problems of predicting the flood susceptibility of an area and predicting the time taken for a river to reach its peak height after a rainfall event. Kdb+ is used to manage and preprocess the time-series data, while Random Forest and XGBoost models are deployed via embedPy and the ML-Toolkit.
The white paper is accessible on this link
Please visit code.devweb.kx.com for a complete archive of valuable kdb+ technical whitepapers.