CGIAR Crop Yield Prediction Challenge
$3,000 USD
Can you predict maize yields on East African farms using satellite data?
281 data scientists enrolled, 63 on the leaderboard
AgriculturePredictionComputer VisionUnstructuredImageSatelliteSDG2
21 October—7 February 2021
Ends in 2 months
NDVI values
published 3 Nov 2020, 09:32

Hi everybody, does anyone get adequate NDVI values, beckause for different monthes I got normal distribution near 0 with negative values, but NDVI should be between [0, 1], and they are not far from 0.1. it is very strange.

to calc it I used [20, 20] pixel for every image, with next formula

NDVI = (NIR - Red)/(NIR + Red)


Hi Danil, NDVI values shouldn't be between (0,1) as you said. They are always between [-1,1] where values greater than 0.2 are considered vegetation, 0 usuallly for bare soils, while clouds and snow fields will be characterized by negative values of this index.

Your values are ok but you have to be careful with pixel with clouds (S2_QA60 band)

I hope it helps