Faculty Research Collaborations with Junior Researchers – List of AI Proposals

Click any of the AI proposal summaries below for more information and to apply as a Junior Researcher.

Your deadline to apply is June 16.

Return to the complete list of available research opportunities.


Enhancing Satellite Deformation Measurements using Deep Learning (Christelle Wauthier)

Using AI deep learning approaches to maximize the output of satellite deformation measurements using realistic atmospheric models is still in its infancy. (Learn more and apply)


Geodetic inversion and optimization using physics-based FEMs models and AI (Christelle Wauthier)

We will develop and apply AI and computational modeling methods to volcanic processes that will have broader impacts on forecasting. (Learn more and apply)


Forecasting volcanic eruptions using data fusion (Christelle Wauthier)

We will develop and apply data sciences and AI methods to volcanic hazards processes and hope to improve eruption forecasting globally. (Learn more and apply)


Using AI to learn and generate physically consistent and realistic landscape topography and fluvial river bathymetry (Xiaofang Liu)

The objectives of the project are: (1) to investigate the inherent structural relationships between topography, river bathymetry, physiography, climate, precipitation, and river discharge. (2) to develop AI and ML models capable of generating synthetic, physically realistic landscape topography and river bathymetry. (Learn more and apply)


Transfer Learning for Predicting Local Atomic Order in Multi-Principal Element Alloys (Mia Jin)

This project aims to develop a machine learning framework that leverages transfer learning from binary alloy datasets to predict chemical short-range order (CSRO) in multi-principal element alloys (MPEAs), such as high-entropy alloys (HEAs), where data are scarce. (Learn more and apply)


Normalizing flows for Bayesian Model Comparison: Detecting Extrasolar Planets (Eric Ford)

This project compares the robustness and efficiency of different computational methods for performing Bayesian uncertainty quantification and model comparison to improve the sensitivity and robustness of surveys to discover and characterize low-mass planets. (Learn more and apply)


Improving economic outcomes via AI-powered bank monitoring and risk management (Nonna Sorokina)

By integrating expertise in finance, economics, regulatory policy, and artificial intelligence, the initiative aims to build an AI-powered monitoring framework for banking risk management—particularly vital in today’s volatile interest rate environment. (Learn more and apply)


De-risking the commercialization of advanced nuclear reactors through innovative financing vehicles (Nonna Sorokina)

By developing innovative financial mechanisms—including pooled investment models, securitization strategies, and CDS-like instruments—this research synthesizes technical reactor design considerations with sophisticated computational modeling of risk and return. (Learn more and apply)


Your next-door neighbor, nuclear reactor: real estate and societal readiness (Nonna Sorokina)

By examining real estate dynamics around nuclear power plants and incorporating novel measures of public sentiment and societal readiness, the research brings together expertise from economics, urban planning, nuclear engineering, and computational social science. (Learn more and apply)


LLM-Augmented Digital Twin Framework for Building Material Reuse and Recycling Assessment (Yuqing Hu)

This project proposes to develop a digital twin framework powered by large language models (LLMs) and large vision models (LVMs) to support component-level material reuse and recycling assessment. (Learn more and apply)


Privacy-Preserving Linear Regression and Synthetic Data for Reproducible Social Science Research (Aleksandra Slavkovic)

This project aims to develop a novel method for DP linear regression that enables valid statistical inference and supports synthetic data generation. (Learn more and apply)


Linking Multidimensional Sleep Health to Cognitive Function in Older Adults Using Machine Learning (Sayed Reza)

This project will evaluate the relationship between sleep health and cognitive function in older adults by leveraging wearable device time series data and applying interpretable AI/ML techniques. (Learn more and apply)


Non-Invasive Turkey Body Weight Monitoring and Prediction via Deep Visual Time Series Analysis (Enrico Casella)

This project aims to develop a novel hybrid deep learning model that leverages longitudinal visual data, potentially combined with historical flocklevel time series information, to estimate current body weight, predict future body weight trajectories, and ultimately forecast final carcass weight in turkeys. (Learn more and apply)


Evaluating Generative AI Tools for Qualitative Analysis (Tim Brick)

The goal of this project is to develop a pipeline that can leverage zero-shot and few-shot learning with Retrieval Augmented Generation (RAG) in Large Language Models (LLMs) to partially automate qualitative coding of conversational transcript data. (Learn more and apply)


Millions of Galaxies but No Time: Rapid Inference of Galaxy Properties with Neural Density Estimators (Joel Leja)

We seek an ICDS Junior Researcher who will perform the first, pioneering application of our SBI++algorithm to millions of galaxies from the Hobby-Eberly Telescope Dark Energy Experiment (HETDEX), in which Penn State has a leadership role. (Learn more and apply)


Classifying Weakly Detected Gamma-ray Transients (James DeLaunay)

This project will consist of finding the optimal way to perform classification on these weakly detected gamma-ray transients, by exploring different AI techniques, inputs, and training data. (Learn more and apply)


Interpreting the biological concepts learned by neural networks in genomic predictive tasks (Shaun Mahony)

In this project, we aim to develop an alternative approach for feature interpretation in genomics neural networks. Our goal is to implement and test the Testing with Concept Activation Vectors approach to assess how genomic “concepts” are used by neural networks as opposed to focusing on individual DNA element features.(Learn more and apply)


Mapping Language Model Failures Through Community Experience: A Study of Multilingual Researchers (Dana Calacci)

This project investigates how English as a Second Language (ESL) graduate students interact with Large Language Models (LLMs) like ChatGPT, focusing on how language proficiency shapes their experience of model failures, biases, and harms. (Learn more and apply)


PolliSense: AI-powered Habitat Quality Assessment and Biodiversity Improvement (Mehrdad Mahdavi)

The long-term vision for this project is to create an accessible, user-friendly tool that empowers land managers, farmers, and conservationists to quickly and easily assess their landscapes, make informed decisions, and collaborate on creating environments that support both human and ecological health.(Learn more and apply)


Predicting genomic regulatory elements across species using domain adaptive neural networks (Shaun Mahony)

In this project, our goal is to implement additional domain adaptation strategies to enable accurate crossspecies gene regulatory predictions. We are particularly interested in the multi-source training scenario, where we have labeled training data from multiple genomes/domains. (Learn more and apply)


Machine learning techniques to identify ‘state-changing’ and anomalous behavior in astrophysical time series (Charlotte Ward)

In this project, we aim to identify the architectures most capable of identifying ‘state changes’ in time series, whether they be outlier detection techniques or extensions of methods that learn and predict time series behavior. (Learn more and apply)


Algorithmic Affidavits and Automation Bias: Empirical Evaluation of Generative AI in Police Report Writing (Dana Calacci)

This project investigates the full lifecycle of hype surrounding generative AI technologies in policing—from exaggerated capability claims by vendors, to procurement by law enforcement agencies, to courtroom use of AI-generated evidence. (Learn more and apply)


Deciphering systemic biological networks through AI-driven multi-omic integration (Gustavo Nader)

We will integrate publicly available multi-organ, multi-omic dataset to investigate the molecular hierarchies that establish organ cross-talk and optimal organismal physiological adaptations and function. (Learn more and apply)


Analyzing Human and Social Dynamics Through Social Sensing (Xi Gong)

This project aims to expand the current study using social sensing for understanding spatial social networks and public perspectives on controversial social topics, also exploring dealing with the challenges inherited in social sensing research. (Learn more and apply)


Embedding Intelligence in 3D Modeling Workflows: An Approach for Large  Language Models to Assist Users in Modeling Using Natural Language (Felicia Ann Davis)

This research proposes the development of an AI-augmented interface that enables users to interact with 3D modeling applications through natural language. The project seeks to reimagine how designers engage with complex software systems by embedding large language models (LLMs) within the modeling environment. (Learn more and apply)


Enhancing Road Safety Through Real-Time AI-Powered Drowsiness Detection and Alert system Using EEG Eye-Blink Artifacts (Daniel Otchere)

This proposal seeks to develop an innovative AI-powered system for detecting driver drowsiness through real-time analysis of EEG eye-blink artifacts. (Learn more and apply)


Application of Transformer-Based Machine Learning Models to Whole Organism Computational Phenomics (Keith Cheng)

To enable the first 3-dimensional whole-organism phenotyping that encompasses all cell types and organ systems, we propose to develop and optimize Transformer-based machine learning (ML) models capable of automatically segmenting and labeling regions of interest from high-resolution 3D micro-CT scans at unprecedented resolutions. (Learn more and apply)


Benchmarking for Quantum Machine Learning (Mahmut Taylan Kandemir)

The goal of QML benchmarking is to establish a rigorous, standardized, and practical (easy to use) framework for systematically evaluating and comparing QML systems—spanning algorithms, hardware systems, and application domains. (Learn more and apply)


AI-Supported Cyber Safety Curriculum for Youth: Design, Development, and Evaluation (Ellen Wenting Zou)

Project objectives include the design and prototyping of four interactive curriculum modules, the development of AI-powered learning scenarios, and initial user testing with middle and high school students to refine both content and interface. (Learn more and apply)


Building Digital Twins of Personalized Models for Alzheimer’s Disease Prevention and Treatment (Zi-Kui Liu)

The proposed project aims to develop a Zentropy-Enhanced Neural Network (ZENN) that learns the configurations, total energy, and entropy of brain states using data related to Alzheimer’s disease (AD). (Learn more and apply)


Predicting HIV care loss-to-follow-up using machine learning (Kathryn Risher)

Our project aims to develop an ML model to predict patient LTFU from HIV care, trained on data from PLHIV in the Penn State Comprehensive Care Clinic and TriNetX. (Learn more and apply)


AI-Enabled System for UAV Precision Descent and Touchdown (Dhananjay Singh)

Combining data from onboard cameras and inertial measurement units (IMUs), the proposed system will integrate computer vision, artificial intelligence/ML algorithms, and sensor fusion approaches. (Learn more and apply)


Adaptive Smart Homes for the Elderly: AI, VR, and IoT for Independent Living (Dhananjay Singh)

The project will present a functional prototype evaluated in a simulated environment by the end of the year, proving how artificial intelligence may improve aged care, lower healthcare costs, and advance well-being. (Learn more and apply)


Better Left Unsaid: Preventing Hallucinations by Learning Abstention (Dongwon Lee)

The project aims to explore a few ideas and produce a prototype with preliminary results. The participating junior researchers will have an opportunity to contribute to scientific publications in top AI venues, while PI aims to use the preliminary findings to pursue an external grant program at the NSF. (Learn more and apply)


Exoplanet Demographics Combining Multiple Detection Method (Eric Ford)

This project aims to develop simulation-based inference (SBI) tools for characterizing the intrinsic distribution of exoplanets while combining observational constraints from multiple exoplanet detection techniques. (Learn more and apply)


Neural-Network based optimization of wave functions of interacting electrons (Jainendra Jain)

In this project, we will initialize our model on CF trial wavefunctions and fine-tune to capture only the residual LL mixing effects—a transfer-learning strategy that slashes parameter requirements and opens the door to much larger systems. (Learn more and apply)


Development of Data-based AI-driven Toolkits for Energy Industry Using Distributed Fiberoptic Sensing (Shimin Liu)

In this project, we aim to develop and optimize a robust data analytics pipeline tailored specifically for high-volume DAS datasets generated from industry generated data set in mining and oil and gas fields. (Learn more and apply)


Predict Arctic Sea Ice Variability from Atmospheric River Activities and the Time of Arrival of Ice-free Arctic (Laifang Li)

In this project we propose to apply deep-learning models (e.g., convolutional neural networks; CNN) to predict Arctic sea ice variability based on the life cycle of ARs. (Learn more and apply)


Designing Adaptive Reservoir Operations Using Multi-Objective Reinforcement Learning (Hadjimichael)

This project will develop dynamically adaptive and state-aware reservoir operation policies for the Conowingo Dam that explicitly address saltwater intrusion while balancing other management objectives under deeply uncertain future climate conditions. (Learn more and apply)