It depends on the location of the area surveyed by the satellite. In addition, it depends on the temporal resolution (revisit time), and above all the purpose of using the image after classification.
I.e.
Coastal water shoreline detection requires one time image with no clouds, no rains. ans calm shoreline (no high waves or tides) . In India for example the best time is March, April and May.
The best months to teach accurate pictures are the months where there are no green spots that do not hide the ground. Of course, you don't have to see the period of fogs and clouds, which complicate the process of shooting and subsequent measurement. For each latitude this shooting period is different and this feature must be taken into account. Climate data can be gleaned from the internet of scientific journals and Google. Over the last 30 years, the data has been quite detailed. Wishing you success in research.
It depends of the kind of satellite you are planning to use. If you try to use a synthetic aperture radar for recognition of the shore line, the weather conditions are not important.
Alaor Dall'Antonia, thank you for your valuable suggestion. I am using Sentinel 2 image.
Abdlesemed Kedir My study area is southern coast of Bnagladesh. The purpose of doing classification is to detect the shore line. Prior to ditection I need to perform image classification
Use of synthetic aperture radar for recognition of Coastal Geomorphological Features, land-use assessment and shoreline changes in Bragança coast, Pará, Northern Brazil