search

ai4er-cdt / WildfireDistribution

AI4EO GTC 2021/2. Private repository for group 1: determining wildfire distribution in visible remote sensing imagery.
MIT License
6 stars 0 forks source link

What to do with 'not-observed' MODIS data classification? #18

Open Hamish-Cam opened 2 years ago

Hamish-Cam commented 2 years ago

We had a discussion on making sure our output is a binary 1/0 (burned/not-burned). The main question is how do we deal with cloud-cover etc where burns may occur and don't see them or it may just be regular cloud cover. There is also the issue of potential "clouds" actually being caused by fires (e.g ash clouds).

For now we will classify it as 'no burn', however, this is an issue we intend to revisit later on.

graceebc9 commented 2 years ago

review other satellites- noah . sentinel. to chekc for a few examples to see if we can get a sense of burn or not