Alyssa Schubert

Alyssa Schubert

By |

Alyssa is interested in drinking water research at the intersection of science and policy, including equitable access to quality drinking water and science communication. While at MIDAS, she will use sensors and machine learning techniques to generate data-driven models designed to advance real-time decision-making in drinking water and further the protection of public health. In her spare time, Alyssa enjoys reading, weightlifting, playing tennis, and hiking with her dog. 

  • Ph.D., Environmental Engineering, University of Michigan
  • AI Mentor: Bryan Goldsmith, Chemical Engineering, College of Engineering
  • Science Mentor: Mark Burns, Chemical Engineering, College of Engineering
  • Research Theme: AI for sensor data analysis for water quality monitoring
Jacob Berv

Jacob Berv

By |

As a Schmidt AI in Science Fellow, Jake will investigate applications of AI and machine learning approaches to basic questions in ecology and evolutionary biology. Initially, Jake will study a neural network system trained to generate high-throughput measurements from museum specimens in order to understand the evolution of the avian skeleton. Longer term, Jake aspires to lead an independent research group and continue to make contributions to the field of evolutionary biology.

  • AI Mentor: David Fouhey, Computer Science and Engineering, College of Engineering
  • Science Mentor: Brian Weeks, Environment and Sustainability, School of Environment and Sustainability
  • Research Theme: ML models for avian evolution
Vital Fernández

Vital Fernández

By |

My research involves the analysis of emission line spectra. The captivating and colourful images obtained from the cosmos are primarily composed of photons emitted by particles heated by stars. A spectrum is a plot that depicts the number of photons observed as a function of their wavelength/colour. This tool provides a reliable fingerprint to quantify the physical conditions and composition of the universe. Building on these principles, my astrophysics PhD conducted at the INAOE in Mexico, focused on measuring the amount of helium the universe was born with. My work at the University of Michigan Ann Arbor involves developing new tools, utilizing neural networks, to explore the complex chemo-dynamic parameter space of Big Data astronomical observations. 

  • AI Mentor: Xun Huan, Mechanical Engineering, College of Engineering
  • Science Mentor: Sally Oey, Astronomy, LSA
  • Research Theme: Deep Learning for spectral analysis for distant galaxies
Christin Salley

Christin Salley

By |

Dr. Christin Salley’s dissertation revolved around mitigating natural hazards through crisis detection and communications, enhancing accessibility to emergency management response systems. Her research aimed to ultimately assess social systems related to disasters and develop proactive measures to enhance community resilience. She earned her PhD in Civil Engineering (with a concentration in Construction and Infrastructure Systems) from the Georgia Institute of Technology, her MSE in Civil Engineering from the Johns Hopkins University, and her BS in Fire Protection Engineering from the University of Maryland.

She is also personally passionate about pathways of engineering (investigating pursuits of engineering at different educational levels) and desires to train, mentor, and teach the next generation of engineers while conducting research that benefits various communities. In her free time, she enjoys spending time with family and friends, traveling, and trying new restaurants.

During the Schmidt AI in Science Postdoctoral Fellowship, she will focus on developing equitable infrastructure systems and services within urban environments to continue studying enhancing community resilience. Specifically, her work will center on understanding societal systems and addressing ethical considerations, particularly concerning vulnerable populations, through investigations on disaster and crisis management using AI. Employing a transdisciplinary and sociotechnical approach, she will integrate data science methods for information processing and associated analyses. Her overarching goal is to make a positive impact on society through her research, fostering innovation and advancing responsible research practices. She will be working under the mentorship of Dr. Sabine Loos (Science Mentor) and Dr. Lu Wang (AI Mentor).

  • AI Mentor: Lu Wang, Computer Science and Engineering, College of Engineering
  • Science Mentor: Sabine Loos, Civil and Environmental Engineering, College of Engineering
  • Research Theme: Analysis of equitable social and infrastructure systems and services with AI applications

Weichi Yao

By |

Recent years have seen significant advancements in artificial intelligence (AI) and machine learning (ML), evidenced by their empirical success. However, many scientific applications still rely on traditional statistical methods for several reasons. One issue is the data inefficiency of ML models, which is a universal challenge across scientific domains due to the high costs to collect high quality data. Additionally, ML models often struggle to produce generalizable results and are difficult to interpret, commonly referred to as “black box” models. My research focuses on addressing these challenges. Indeed, scientific applications always motivate and inspire new AI models and algorithms. Broadly, I am interested in developing ML methodologies that can provide accurate, reliable, and trustworthy solutions to scientific problems and support decision making in critical domains. I am a firm believer in “AI for Science and Science for AI.”

  • AI Mentor: Yixin Wang, Statistics, LSA
  • Science Mentor: Bryan Goldsmith, Chemical Engineering, College of Engineering
  • Research Theme: Causal reasoning in materials science

Nanta Sophonrat

By |

ML with chemist-in-the-loop to find reaction conditions for plastic recycling.

Plastic pollution is a huge environmental problem. Without viable, cost-effective, and environmentally friendly pathways for recycling and upcycling, there is little incentive to change the way we think about and handle plastic waste today. I have always been passionate about finding solutions to this problem. As an AI in Science fellow, I would like to learn and combine the chemical knowledge with machine learning to efficiently find experimental conditions for plastic recycling via electrochemical pathways.

  • AI Mentor: Ambuj Tewari, Statistics, LSA
  • Science Mentor: Anne McNeil, Chemistry, LSA
  • Research Theme: Chemist in the loop ML for plastics recycling

Yiluan Song

By |

I graduated from the National University of Singapore in 2016 with a Bachelor of Science in Life Sciences, specializing in Environmental Biology. I am currently a final-year ….and a visiting Ph.D. student in the School for Environment and Sustainability at the University of Michigan.

I am interested in conducting interdisciplinary research in vegetation responses to global changes using big data and quantitative methods. My PhD dissertation is focused on the interactions between climate change, plant phenology, and human society. Some of the highlights include a theoretical framework for changing ecological synchrony, a systematic quantification of phenological mismatch, characterization of pollen phenology using high-resolution remote sensing, and public perception of phenology on social media. In my postdoctoral research, I seek to develop a Bayesian process-guided machine learning framework to project changes in phenology under global changes, informing both near-term forecasting and long-term projections.

  • AI Mentor: Yang Chen, Statistics, LSA
  • Science Mentor: Kai Zhu, Environment and Sustainability, School of Environment and Sustainability
  • Research Theme: Projecting nature’s calendar under climate change

Elena Shrestha

By |

Elena is a Postdoctoral Fellow with the Robotics Department at U-M since August 2022. Her research interest is in developing autonomous unmanned vehicles that are capable of intelligent planning and decision-making. As a Schmidt AI in Science Fellow, she will continue working on developing model-based reinforcement learning algorithms that enable autonomous agents to generalize and adapt to unseen real-world environments. 

Prior to joining U-M, she was a Section Supervisor and Senior Professional Staff at the Johns Hopkins University Applied Physics Lab. Her dissertation was on modeling the system dynamics of the cyclocopter and developing control strategies for a novel transformer drone with ground, air, and surface modes of operation. 

  • AI Mentor: Katie Skinner, Robotics, College of Engineering
  • Science Mentor: Dimitra Panagou, Aerospace Engineering, College of Engineering
  • Research Theme: Intelligent visual and flow-based navigation for autonomous underwater vehicles

Matthew Andres Moreno

By |

Matthew works on “digital evolution. He will use ML to create low-dimensional representations of viable “digital organisms” and study how evolution happens in this reduced space. His research will shed light on the evolution of evolvability – when populations evolve to improve their ability to generate further adaptive variation.

  • AI Mentor: Kevin Wood, Biophysics
  • Science Mentor: Luis Zaman, Complex Systems; Ecology and Evolutionary Biology
  • Research Theme: Digital Evolution
Kevin Napier

Kevin Napier

By |

Kevin will develop a groundbreaking ML-based astronomical image stacker to combine images taken on multiple days and from multiple telescopes. This will bring fundamental changes to how we search for and study solar system minor planet populations, with the immediate application of discovering some of the faintest objects in the solar system – objects in the Kuiper belt that can be observable from NASA’s New Horizons (NH) spacecraft.

  • AI Mentor: Camille Avestruz, Physics
  • Science Mentor: Hsing-Wen Lin, Physics
  • Research Theme: Computer Vision Detecting the faintest objects in the Solar System