Visit Google Scholar for the full list of research and scientific publications.
SIMOC — A hi-fidelity simulation of off-world, human habitation and bioregenerative life support as a platform for citizen scientists and virtual classrooms , July 14, 2021
Kai Staats, Tyson Brown, Ezio Melotti, Pete Barnes, Gretchen Hollingsworth, Michael Pope
As published and presented at ICES 2021, the Scalable, Interactive Model of an Off-World Community (SIMOC) is a research-grade agent-based model, platform for education, and NGSS aligned curricula. As of June 2020 National Geographic is hosting SIMOC at the NGS Education Resource Library, a web-based repository of more than 4000 curricular assets for K-12+. This publication presents the results of a world-wide engagement of SIMOC, with specific examples of how SIMOC was integrated into virtual classrooms during the COVID pandemic for an iterative exploration of the scientific method. Available from Texas Tech University
Scaled Automated Pressure Regulation System for Analog Moon and Mars Habitat, July 12, 2021
Meghan Marlowe, Ahmed Alraeesi, Gustavo Velez, James Marlar, Arfan Wibisono, Coby Scheidemantel, Kai Staats, John Adams
As humans look to travel off-world, sealed habitats will be essential for life support in long-duration missions. The Space Analog for the Moon and Mars (SAM) at Biosphere 2 is a habitat analog that melds mechanical and bioregenerative life support systems. A team of six engineering students at the University of Arizona worked with the executive team at SAM and Biosphere 2 to design and prototype the Automated Pressure Regulation System (APRS) for the SAM crew quarters. The system will maintain a positive pressure in relation to the outside environment, preventing potential biocontaminants from entering. This paper discusses the overall mechanical system, software design, and test validation procedures proposed for the APRS. Available from Texas Tech University
Evolving Antennas for Ultra-High Energy Neutrino Detection , May 15, 2020
Julie Rolla, Amy Connolly, Kai Staats, Stephanie Wissel, Dean Arakaki, Ian Best, Adam Blenk, Brian Clark, Maximillian Clowdus, Suren Gourapura, Corey Harris, Hannah Hasan, Luke Letwin, David Liu, Carl Pfendner, Jordan Potter, Cade Sbrocco, Tom Sinha, Jacob Trevithick
The GENETIS collaboration is developing genetic algorithms for designing antennas that are more sensitive to ultra-high energy neutrino induced radio pulses than current designs. There are three aspects of this investigation: to evolve simple wire antennas to test the concept and different algorithms; optimize antenna response patterns for a given array geometry; evolve antennas sensitivity to neutrino detection as a measure of fitness. Available at the Arxiv.
Enhancing Gravitational-Wave Science with Machine Learning, May 7, 2020
Elena Cuoco, Jade Powell, Marco Cavaglià, … Kai Staats, et al
Machine learning has emerged as a popular and powerful approach for solving problems in astrophysics. We review applications of machine learning techniques for the analysis of ground-based gravitational-wave detector data. Examples include techniques for improving the sensitivity of Advanced LIGO and Advanced Virgo gravitational-wave searches, methods for fast measurements of the astrophysical parameters of gravitational-wave sources, and algorithms for reduction and characterization of non-astrophysical detector noise. These applications demonstrate how machine learning techniques may be harnessed to enhance the science that is possible with current and future gravitational-wave detectors. Available at the Arxiv.
World Ships: Feasibility and Rationale, April 11, 2020
A.M. Hein, C. Smith, F. Marin, and K. Staats
World ships are hypothetical, large, self-contained spacecraft for crewed interstellar travel, taking centuries to reach other stars. Due to their crewed nature, size and long trip times, the feasibility of world ships faces an additional set of challenges compared to interstellar probes. In part, we explore the application of SIMOC to world ship design. Acta Futura 12 (2020) 75-104
Improving the background of gravitational-wave searches for core collapse supernovae: a machine learning approach, February 4, 2020
Marco Cavaglia, Sergio Gaudio, Travis Hansen, Kai Staats, Marek Szczepanczyk, Michele Zanolin
We present a novel machine learning method to perform single-interferometer supernova searches based on the standard LIGO-Virgo coherent WaveBurst pipeline. We show that the method may be used to discriminate Galactic gravitational-wave supernova signals from noise transients, decrease the false alarm rate of the search, and improve the supernova detection reach of the detectors. Published in Machine Learning: Science and Technology, Mach. Learn.: Sci. Technol.1 015005. Available at the Arxiv.
An agent-based model for high-fidelity ECLSS and bioregenerative simulation, July 2019
Kai Staats, Iurii Milovanov, John Adams, Gregory Schoberth, Thomas Curry, Katherine Morgan, Jason Deleeuw, Gene Giacomelli
As published and presented at ICES 2019, in collaboration with the Biosphere 2, SIMOC was configured to approximate the non-linear functions of CO2 and biomass production in a real-world plant growth study conducted at the Biosphere 2. This publication sees the results of the first application of this novel approach to modeling a real-world plant study, where data generated by the SIMOC model is compared to data collected for the duration of the experiment, and then compared. Available from Texas Tech University
Finding the origin of noise transients in LIGO data with machine learning, December 2018
Marco Cavaglia, Kai Staats, Teerth Gill
We present two machine learning methods, based on random forest and genetic programming algorithms, that can be used to determine the origin of non-astrophysical transients in the LIGO detectors. While the data sets described in this paper are specific to LIGO, … the code bases and means by which they were applied … are completely portable to any number of instruments in which noise is believed to be generated through mechanical couplings. Published in Communications in Computational Physics, volume 25, pp. 963-987. Available at the Arxiv.
TensorFlow Enabled Genetic Programming, July 2017
Kai Staats, Edward Pantridge, Marco Cavaglia, Iurii Milovanov, Arun Aniyan
Genetic Programming, a kind of evolutionary computation and machine learning algorithm, is shown to benefit significantly from the application of vectorized data and the TensorFlow numerical computation library on both CPU and GPU architectures. Published in the proceedings of the Genetic and Evolutionary Computation Conference (GECCO) Companion, ACM 2017, pp. 1872-1879. Available at the Arxiv.
Genetic Programming Applied to RFI Mitigation in Radio Astronomy, December 2016
Kai Staats, with supervisor Bruce Bassett and co-supervisor Arun Aniyan
The MSc thesis for Kai Staats, University of Cape Town, South Africa. At the time of this research, the application of machine learning to radio astronomy was relatively new. Genetic Programming had never been applied, and as such, was a novel approach to this challenging arena. Foundational to this body of research, the application Karoo GP was developed and tasked with the classification of signal verus radio frequency interference (RFI). The training data was derived from the output of an observation run of the KAT-7 radio telescope array built by the South African Square Kilometre Array (SKA-SA).
SPIE Proceedings, July 15, 2016
S. B. Potter, Kai Staats, Encarni Romero-Colmenero
Genetically optimized weather predictions built upon the Southern African Large Telescope (SALT) weather monitoring database. This remarkably simple approach developed principally by head astronomer Stephen Potter derives a functional weather predictor in order to prepare dome environment conditions for night time operations or plan, prioritize and update weather dependent observing queues. SPIE: International Society of Optics and Photonics, conference proceedings.
Mobile Robotic Platform Deployment as Part of a Martian Mission Simulation, June 17-19, 2014
E.Reid, P.Iles, N.Cristello, M.Labrie, M.Musilova, K.Staats
In January of 2014 a seven-person crew of analogue astronauts (Crew134) conducted a two week, high-fidelity Mars mission simulation at the Mars Society’s Mars Desert Research Station (MDRS) in the high altitude Utah desert. Part of the mission simulation included testing of a mobile robotic platform and a stereo camera system (SCS). This paper summarizes the results of this testing and provides lessons learned and recommendations for future analogue deployments and flight systems design. International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS)