[GIS] Differentiating Cloud and Snow in unsupervised classification of mountaneous terrain

classificationremote sensing

I am doing unsupervised classification of a mountaneous terrain and I have used 500 classes to classify the land use.

In my result, cloud and the snow are categorized in the same class.

How do I differentiate them?

I want to eliminate the cloud but not the snow.

Best Answer

First of all I should mention that this question is addressing very limited space, though important question too.

The first thing that comes to my mind on this subject that you can consider temporal information in short time interval. if certain values are changed in certain areas, it may be easier to detect snow.

and second solution is here from National Operational Hydrologic Remote Sensing Center (NOHRSC). they use a supervised image classification algorithm to map snow and clouds.

Snow Can be Distinguished From Cloud at 1.6 m

The 1.6 m wavelength allows significantly improved discrimination between snow and clouds. At 1.6 m, snow has very low reflectance, while the reflectance of clouds remains high (Figure 1). Therefore, both cirrus and optically thick clouds can be directly classified and distinguished from snow at the 1.6 m wavelength (Warren, 1982). This has been clearly demonstrated using the operational Landsat Thematic Mapper satellite, which has a channel centered near 1.6 m (channel 5; 1.57-1.78 m) (Dozier, 1987; Baglio, 1989).

and this image from the same place which shows Satellite channel wavelengths in microns (m), and typical reflectance spectra for snow and clouds.

snowandcloud

And results they get:

result

Related Question