Analysis of Ring Galaxies Detected Using Deep Learning with Real and Simulated Data

Overview

Understanding the formation and evolution of ring galaxies, galaxies with an atypical ring-like structure, will improve understanding of black holes and galaxy dynamics as a whole. Current catalogs of rings are extremely limited: manual analysis takes months to accumulate an appreciable sample of rings and existing computational methods are vastly limited in terms of accuracy and detection rate. Without a sizeable sample of rings, further research into their properties is severely restricted. This project investigates the usage of a convolutional neural network (CNN) to identify rings from unclassified samples of galaxies. A CNN was trained on a sample of 100,000 simulated galaxies, transfer learned to a sample of real galaxies and applied to a previously unclassified dataset to generate a catalog of rings which was then manually verified. Data augmentation with a generative adversarial network (GAN) to simulate images of galaxies was also used. A catalog of 1151 rings was extracted with 7.4 times the precision and 15.4 times the detection rate of conventional algorithms. The properties of these galaxies were then estimated from their photometry and com-pared to the Galaxy Zoo 2 catalog of rings. With upcoming surveys such as the Vera Rubin Observatory Legacy Survey of Space and Time obtaining images of billions of galaxies, similar models could be crucial in classifying large populations of rings to better understand the peculiar mechanisms by which they form and evolve. Biomimicry of Boxfish: A Computational Analysis and Wind Tunnel Study of the Aerodynamic Drag Reduction of Class 8 Heavy Vehicle Trailers Vedant Srinivas Eastlake High School, Sammamish, WA In August 2021, the Environmental Protection Agency (EPA), through its Clean Truck Plan, proposed new standards to promote clean air and reduce pollution from heavy-duty vehicles starting in model year 2027. One of the recommended approaches is for heavy-duty vehicles to improve fuel economy by 40% by the year 2027. Class 8 trucks achieve fuel economy in the range of 6-8 miles per gallon of diesel. At speeds of 70 mph, 65% of the energy is spent in overcoming aerodynamic drag (McCallen et al., 1999), making aero-drag the largest opportunity for improving efficiency. A truck consists of a cab in front and a trailer in the back. Cab aerodynamics is well understood and modeled as is evident with the near-airplane-looking cabs on the roads with aero hoods, aerodynamic bumpers, streamlined mirrors, and roof extenders. The trailer has remained as cubical containers that are designed more for stacking and storage than being aerodynamic. Inspired by the Boxfish hydrodynamics, different add-on shapes were used in CFD simulations to provide a streamlined shape to the trailer and its corresponding drag measured. A 3D-printed model of the cab and trailer with add-on attachments was tested in a wind tunnel to validate the simulation. When comparing the bio-inspired to a standard trailer, a drag reduction of 13.8% in computational and 16.7% in the wind tunnel experiments was achieved. These results translate to 14%-16% efficiency gains of Class-8 trailers by bio- mimicking the Boxfish. WEST VIRGINIA

Competition history

• JSHS 2023 Category not listed

Resources

• National JSHS abstract book ↗

Related projects

Closest projects by meaning, across every fair and year in the corpus.