The Geo-ICT Blog

Tutorials/Post - Remote Sensing, GIS, Earth System, Geo-AI/ML


Data Drive Landslide Hazard Assessment (LHASA) Model for the Mekong Region

In this presentation, Dr. Nishan Kumar Biswas, Dr. Pukar Amatya, and Dr. Thomas Stanley from the Goddard Space Flight Center presented the data-driven Landslide Hazard Assessment (LHASA) Model for the Lower Mekong Region. The LHASA uses the SALaD (Semi-Automatic Landslide Detection) landslide mapping system and the XGBoost algorithm to derive the hazard assessment layer.


How many abstracts can an American Geophysical Union (AGU) session get?

I am helping a colleague here at the NASA-SERVIR Science Coordination Office (SCO) in Huntsville, Alabama, to organize a session on Machine Learning (titled Addressing environmental challenges and sustainable development through Earth science applications utilizing Machine Learning). The session got a massive 44 abstracts. I was curious to see how many abstracts a session … CONTINUE READING

Deep Learning Approach for Monitoring Trees outside of Forests

John Brandt, a Data Science Associate at the World Research Institute (WRI), discusses the methodology and implications of his paper “A global method to identify trees outside of closed-canopy forests with medium resolution satellite imagery.”

View the presentation slides here. Read the paper here.… CONTINUE READING

Marine Debris Detection Using Planet Data

This presentation walks through the use of Machine Learning and Artificial Intelligence to detect marine debris using planet data. Thanks to Lillianne Thomas from Development Seed and Ankur Shah from Climate Engine for the presentation. Thanks to the entire project team, especially Muthukumaran Ramasubramanian from the University of Alabama in Huntsville, George Priftis from the … CONTINUE READING

Surface Water Detected by the BCE Algorithm

Deep Learning approach for Sentinel-1 Surface Water Mapping leveraging Google Earth Engine

Satellite remote sensing plays an important role in mapping the location and extent of surface water. A variety of approaches are available for mapping surface water, but deep learning approaches are not commonplace as they are ’data hungry’ and require large amounts of computational resources. However, with the availability of various satellite sensors and rapid … CONTINUE READING

Page 1 of 16

Powered by WordPress & Theme by Anders Norén