News
The College of Arts and Sciences is welcoming four new tenure-track assistant professors this academic year whose research sits at the intersection of Earth observation, AI, and machine learning —…
The Observatory is profiled in ASCENT 2026, the College of Arts and Sciences flagship publication, in a feature on how the College is shaping the future of AI in research and learning…
An all-day inaugural workshop at Mendenhall Laboratory brought together OSU faculty and students from across the College of Arts & Sciences, Engineering, and SENR for 16 short talks and afternoon…
New paper From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2 presented at the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2025).
Read the…
BuckAI modeling study on H₂–water VLE using a Cubic-Plus-Association Equation-of-State is now available in PLOS ONE, supporting natural hydrogen reservoir research.
Read the research
The Observatory's dedicated collaboration and visualization space officially opens, providing a hub for weekly research seminars, GPU-powered analysis, and visitor demos.
Read the…
The BuckAI Observatory is officially launched as OSU's interdisciplinary center for AI-powered Earth observation, with five-year seed funding (2025–2030) from the College of Arts and Sciences.
Three-year collaborative grant to develop AI satellite tools for tracking deforestation and agroforestry in Sub-Saharan Africa, in partnership with the CGIAR Standing Panel on Impact Assessment.
As efforts to transition away from fossil fuels strengthen the hunt for new sources of low-carbon energy, scientists have developed a deep learning model to scan the Earth for surface expressions…
Semantic segmentation of 'fairy circles' (semicircular depressions) using SAM + Sentinel-2 + Copernicus DEM presented at AGU.
Covered by New Scientist, EurekAlert, and 10+…
Broad international media pickup of the natural hydrogen prospecting work, with coverage in science news outlets across North America, Europe, and Asia.
Fully convolutional neural networks applied to WorldView/QuickBird commercial imagery (30 cm) achieve >90% precision and recall for river mapping, enabling tracking of Arctic river dynamics.