PlotToSat: A Tool for Generating Time-series Signatures from Sentinel-1 and Sentinel-2 at field-based plots for Machine Learning applications

Add to your list(s) Download to your calendar using vCal

• Dr Milto Miltiadou
• Tuesday 18 June 2024, 12:00-11:00
• Large Lecture Theatre, Department of Geography, Downing Site.

If you have a question about this talk, please contact nobody.

PlotToSat is a new open-source framework that uses the Python API of Google Earth Engine (GEE) to solve the problem of creating time-series of Earth Observation (EO) satellite data at multiple plot locations spread out within a landscape. Forest ecologists gather data from predetermined sites known as plots. Plots are usually circular, defined by their centre (latitude, longitude) and a radius. A plot network consists of a few to hundreds of thousands of plots, which are systematically placed to represent the forests of a region, e.g., a country. PlotToSat extracts time-series of multispectral and Synthetic Aperture Radar (SAR) data for a given year. By running it multiple times, the time-series can be extended. The first application of PlotToSat is tree genera classifications from space. PlotToSat is useful for any application requiring EO time-series data from multiple spatially disconnected locations.

This talk is part of the Department of Geography - other talks series.

This talk is included in these lists:

• AUB_Cambridge Seminars
• Department of Geography
• Large Lecture Theatre, Department of Geography, Downing Site

Note that ex-directory lists are not shown.