Assistant Research Scientist specializing in physics-informed AI architectures for Earth observation systems. Delivered operational frameworks reducing permafrost carbon feedback uncertainty by 39% and achieving 96.4% detection accuracy across 345,000+ validation events by designing distributed multi-GPU training infrastructure processing 54+ million observations. Managed circumarctic analyses at 30m-1km resolution supporting strategic mission planning for NASA satellite programs. Collaborative leader bridging physical sciences and systems engineering to advance quantitative climate prediction capabilities informing policy-critical carbon budget assessments.
Assistant Research Scientist
Greenbelt, Maryland, US
→
Summary
Leads advanced research in AI-driven Earth observation and climate modeling, developing and deploying high-performance computing solutions for critical environmental assessments.
Highlights
Architected and deployed AI/ML frameworks across NASA's 32-GPU distributed computing infrastructure, accelerating global methane emission reconciliation by 40% and delivering operational 1km-resolution greenhouse gas flux estimation by integrating 7 diverse satellite datasets.
Developed GeoCryoAI physics-informed transfer learning framework, reducing permafrost carbon feedback prediction uncertainty by 39% (RMSE from 1.997cm to 1.007cm) and achieving 96.4% detection accuracy across billions of observations.
Quantified permafrost zero-curtain phenomena, revealing its control over up to 40% of the remaining carbon budget for the 1.5°C warming limit by processing 54+ million observations on a 32-GPU distributed infrastructure.
Designed a scalable data engineering framework for NASA's NISAR satellite mission, establishing operational circumarctic monitoring with 30m resolution and enabling 3-6 month forecasts from multi-billion-row geospatial databases.
NASA Postdoctoral Program Fellow
Pasadena, California, US
→
Summary
Conducted advanced research on Arctic methane emissions and permafrost dynamics, developing novel algorithms and accelerating satellite mission readiness.
Highlights
Developed a novel L-band SAR algorithm for lake ebullition quantification, enabling 7-order-of-magnitude spatial scaling (10m to 10,000km) of Arctic methane emissions with successful cross-platform validation across Alaska.
Accelerated operational readiness for 5 future NASA/ESA methane monitoring missions (NISAR, SBG, CHIME, MERLIN, CO2-M) by synthesizing airborne campaign data and delivering landscape-scale flux estimation methodologies.
Managed international multi-agency Arctic monitoring coordination as a NASA-ESA Arctic Methane Permafrost Challenge Leadership Team member, harmonizing heterogeneous observational platforms for circumpolar permafrost analysis.
SIBBORK-TTE Modeler | Permafrost Calibration/Validation Scientist
Greenbelt, Maryland, US
→
Summary
Improved permafrost thaw prediction and Arctic vegetation response modeling, contributing to critical climate change research.
Highlights
Improved permafrost thaw prediction fidelity by 25% (RMSE reduction to 0.316±0.106m) against field observations across four Alaska subdomains through an enhanced spatially-explicit individual-based model.
Enabled first sub-hectare resolution projections of Arctic vegetation response across a 1.5 million km² domain by deploying an integrated forest-tundra model, quantifying nonlinear permafrost-vegetation feedbacks under future warming conditions.
→
Ph.D.
Earth Systems and Geoinformation Sciences
Courses
Dissertation: Investigating High-Latitude Permafrost Carbon Dynamics with Artificial Intelligence and Earth System Data Assimilation
→
M.Sc.
Environmental Sciences and Policy
Courses
Thesis: Quantifying Wildfire Dynamics in Galicia with Remote Sensing, Modeling, and Artificial Intelligence
→
B.Sc.
Biology
Awarded By
American Geophysical Union (AGU)
Convened the AGU 2025 session on 'The Resilience and Vulnerability of Arctic and Boreal Ecosystems to Climate Change I-VI'.
Awarded By
NASA HQ/JPL, California Institute of Technology, NSF NEON Science
Recognized for significant research contributions and impact, highlighted across multiple prestigious scientific platforms in 2024/2025.
Awarded By
NASA-ESA
Led the NASA-ESA RECAPP3 Reconciliation Challenge and contributed to the NASA-ESA Arctic Methane Permafrost Challenge (AMPAC) Leadership Team.
Awarded By
AMPAC
Served as an instructor for the AMPAC Summer School, teaching in situ harmonization, numerical modeling, and AI for Arctic Research in Svalbard.
Awarded By
NASA ROSES
Served as a panelist for NASA ROSES (FINESST, CMS) proposal reviews in 2024 and 2025.
Awarded By
George Mason University
Recognized for outstanding research contributions and academic distinction.
Awarded By
USPA
Received for exceptional achievements in education and academic pursuits.
Published by
Nature Climate Change
Summary
This publication focuses on integrating multi-modal Earth observation data to reconcile bottom-up and top-down greenhouse gas estimates, currently in preparation.
Published by
Nature Machine Intelligence
Summary
This work explores the resolution of circumarctic zero-curtain phenomena through AI-integrated Earth observations, currently under review.
PyTorch, TensorFlow, Keras, Physics-Informed Neural Networks, Continuous Thought Machines, Diffusion Transformers, Transfer Learning, 32-GPU Distributed Training, NASA NCCS Discover/ADAPT, NCAR Cheyenne/Derecho, AWS Earthdata Cloud.
SAR Polarimetry (UAVSAR, NISAR, Sentinel-1), L-band Radiometry (SMAP), Thermal Infrared (Landsat 8/9), Hyperspectral (AVIRIS-NG), Lidar (GEDI, ICESat-2), Interferometric Processing, Multimodal Harmonization, Synthetic Aperture Radar, Thermal Remote Sensing, Hyperspectral Remote Sensing, Optical Remote Sensing.
Earth System Models (ESM), Carbon Cycle Modeling, Permafrost Physics, CMIP6 Climate Scenarios, Model Benchmarking, Earth System Modeling, Carbon Cycle Dynamics, Subsurface Mechanics.
Parquet/Zarr/NetCDF, DuckDB Analytics, Python, C, JavaScript, PostGIS, MongoDB, Neo4J, Git, CI/CD, Multimodal Data Harmonization, Distributed Supercomputing, Geospatial Analytics at Scale.