About
I am a PhD candidate in Earth & Environment at Boston University working at the intersection of Climate AI, Earth observation, and carbon cycle science.
My research focuses on developing integrated modeling frameworks that combine satellite time series, ecological data, and energy system analysis to quantify the climate impacts of land-use change associated with renewable energy deployment. In particular, I study how utility-scale solar development interacts with forest carbon dynamics and long-term emissions trajectories.
I am especially interested in multi-modal environmental modeling approaches that connect remote sensing, carbon accounting, and uncertainty analysis to support data-driven climate mitigation and energy planning.
Research Areas
Selected Publications
-
Detecting utility-scale solar installations and associated land cover changes using spatiotemporal segmentation of Landsat imagery
Science of Remote Sensing, 2025.Developed a spatial–temporal framework integrating Landsat time-series modeling and object-based segmentation to identify utility-scale solar development and associated land cover change. -
Disaggregation of Landsat-8 thermal data using guided SWIR imagery on the scene of a wildfire
Remote Sensing, 2018.Developed a thermal downscaling approach using guided SWIR imagery to improve spatial representation of wildfire-related surface temperature patterns.
Projects
- Developed a satellite-based monitoring workflow for utility-scale solar expansion and associated forest disturbance using Landsat time series and SNIC segmentation.
- Distinguished solar development with and without forest conversion from other land-cover changes.
- Built reproducible geospatial workflows in Google Earth Engine and conducted post-processing and statistical accuracy assessment in R.
- Developed a carbon bookkeeping framework to estimate emissions associated with forest conversion for utility-scale solar development.
- Incorporated biomass variability, decay pathways, and uncertainty from both area estimation and carbon stocks.
- Implemented Monte Carlo simulations in R to estimate annual and cumulative emissions with confidence intervals.
Skills
Technical
- Programming & data science: R, Python (NumPy, pandas, scikit-learn, PyTorch), MATLAB, JavaScript, C++
- Earth observation & geospatial AI: Google Earth Engine, satellite time-series modeling (CCDC), object-based image analysis, spatial analysis
- Modeling & scientific computing: multivariate and non-linear regression, machine learning, carbon bookkeeping, life-cycle assessment, Bayesian inference, uncertainty analysis (Monte Carlo, bootstrapping)
CV & Contact
I am interested in collaborations related to Climate AI, Earth observation, environmental modeling, and energy transition research.
- Email: kangjoon@bu.edu
- GitHub: github.com/chris099
- Google Scholar: scholar.google.com/citations?user=hj-QD1YAAAAJ&hl=en
- LinkedIn: linkedin.com/in/kangjooncho