End-To-End Machine Learning Applications Framework for Earth Science
No abstract available
Freitag, Brian↗
Engineering topics
Ramasubramanian, M.
Publications and source records attributed to Ramasubramanian, M..
Pixel-Based Smoke Detection with Neural Network
Exposure to biomass burning has been linked to respiratory and cardiovascular illnesses in humans. Traditional satellite based visual and multispectral smoke detection methods are not scalable to capabilities of new generations of remote sensing platforms. We develop a scalable, deep learning based detection model capable of identifying smoke pixels using GOES-16 shortwave reflectance data and present a operational web-based tool to visualize smoke predictions.
Ramasubramanian, M.↗
Pixel-Based Model For High Latitude Dust Detection
Dust has implications on the energy budget, ocean biodiversity, and economy at regional and global scales. Dust detection relies on spectral sensitivity at visible (RGB) and infrared wavelengths. Radiative properties of high latitude dust and the background surface albedo in these regions (>40°N, >40°S) complicate current dust detection methods. Leveraging supervised machine learning (ML) methods, we propose a new method accounting for regional differences of dust occurrence.
High latitude dust↗