I am MohammadReza EskandariNasab (Sam), a PhD candidate in Computer Science at Utah State
University in Logan, Utah. My research centers on generative modeling for time-series data,
including diffusion models, generative adversarial networks, and adversarial autoencoders, with
publications at IEEE ICDM, SIAM SDM, IEEE BigData, and IEEE ICMLA. My current work extends this
research into multimodal learning through an NSF-funded project (Award No. 2530946), generating
and translating across images, text, vector data, and time series through the proposed UNISON
framework.
Alongside this, I build machine-learning pipelines that forecast solar flares, solar energetic
particle events, and coronal mass ejections. This work has been published in The Astrophysical
Journal Supplement Series and presented at IEEE ICDM 2025, with three
additional manuscripts currently in submission. I have also led the development of
FlaPLeT.org, an NSF-funded (Award No. 2305781) no-code platform for training and
evaluating space-weather machine learning models, published in SoftwareX.
My work focuses on developing robust AI methods for scientific discovery, with particular emphasis
on generative models, multimodal data fusion, and predictive modeling for complex spatiotemporal
systems, as I pursue a tenure-track Assistant Professor position in computer science.