ANDRES HERNANDEZ-SERNA
“We are at the very beginning of time for the human race. It is not unreasonable that we grapple with problems. But there are tens of thousands of years in the future. Our responsibility is to do what we can, learn what we can, improve the solutions, and pass them on" Richard Feynman. 1918 - 1988
RESEARCH
As a Senior Faculty Specialist at the GLAD laboratory, my expertise in deep learning and its application in remote sensing and High-Performance Computing (HPC) is dedicated to advancing the field of spatial data analysis. My work involves processing and analyzing massive spatial data sets, with a specific focus on LiDAR and high-resolution spectral imaging. The scope and scale of my research are immense, dealing with petabyte-scale datasets for global analysis.
Key areas of my research include:
Advanced Remote Sensing Techniques: I develop algorithms to process and analyze satellite imagery, notably from NASA's Landsat missions and the Planet constellation. My aim is to create detailed time-series maps of urban areas, managing vast datasets with spatial resolutions as 3 meters and time series extending back to 1984 at 30 meters resolution.
Deep Learning in Spatial Data Analysis: I lead the development and implementation of cutting-edge deep learning frameworks for interpreting remote sensing data. This includes using Generative Adversarial Networks (GANs) and multi-GPU setups to enhance the precision and efficiency of satellite image analysis.
LiDAR Data Processing: I co-developed pyGEDI, a Python package for analyzing data from NASA's Global Ecosystem Dynamics Investigation (GEDI). Additionally, I utilize LiDAR-RIEGL data from drones to assess biomass and tree height in various ecosystems.
Comparative Analysis of Remote Sensing Data: I conduct evaluations on the effectiveness of combining Landsat and GEDI datasets for tree height measurement, covering a period from 2019 to the present.
Field Studies and Data Validation: I participate in fieldwork in diverse regions, including South America, Africa, and the US, to validate remote sensing data, especially in relation to agricultural expansion, forest change, and soybean cultivation.
My research, supported by HPC, represents the forefront of spatial data analysis. The ability to handle large, complex datasets at an unprecedented scale and resolution is vital for enhancing our understanding of environmental changes and aiding in informed decision-making for land management and conservation. The scale of data processing, extending to petabytes, is particularly significant for comprehensive global analyses at 3m resolution or time series from 1984 at 30m resolution.