Thainara Lima
Remote Sensing, ecosystem changes, water quality, radiative transfer modeling, computer vision for Earth observation, and domain-specific foundational models.
I am a PhD student in Agricultural and Biosystems Engineering at Mississippi State University and a NASA Early Career Research Fellow. My research focuses on scalable AI pipelines for large-scale geospatial data on HPC/GPU infrastructure to monitor land and aquatic ecosystems and their responses to environmental changes. I combine multi-satellite imagery with field measurements to calibrate and evaluate bio-optical and deep learning models, leveraging Vision Transformers, semantic segmentation, and self-supervised learning to advance domain-aware foundation models for Earth observation. My broader research interests span AI-driven innovation, multimodal learning, and sustainable monitoring solutions that integrate satellite data, computer vision, and high-performance computing to address planetary-scale environmental challenges.
Mississippi State University Department of Agricultural and Biological Engineering Geospatial Computing for Earth Observation Research (GCER) Lab Starkville, Mississippi, USA
- tml411@msstate.edu
- Google Scholar (opens in a new tab)
- GitHub (opens in a new tab)
- LinkedIn (opens in a new tab)
News
-
Presented a three-minute thesis (3MT) at the Mississippi State University Graduate School: Scales of Observations: The Power of High-Resolution Sensors in Mapping Nearshore Seaweed in the Greater Antilles.
-
Presented the same work at the Fall 2026 Graduate Student Research Symposium, Mississippi State University.
-
Selected as one of 30 students for the IOCCG Summer Lecture Series on ocean optics and ocean colour science, Venice, Italy.
-
Presented a foundation vision model for aquatic systems at the ESA-NASA International Workshop on AI Foundation Models for Earth Observation, Huntsville.
-
New paper: preliminary analysis of PACE remote sensing reflectance over aquatic systems (opens in a new tab), ISPRS Journal of Photogrammetry and Remote Sensing.
-
Presented 30-m deep learning algal bloom mapping at the AGU Fall Meeting, New Orleans.