I am analyzing time series data of NDVI within an AOI. Ultimately, I would like to plot the average monthly data in a box-and-whisker diagram.
Here is the problem. The number of months with significantly low data due to cloud masks, because of the optical satellite. (There are years where the number of data in February is 2 and the number of data in September is 8.)
We use several methods for smoothing time series data based on the following references. (Li, Shuang, et al.,2021)
However, it is incorrect to incorporate the data after the smoothing process into the average, right? I would like to know if there are any good data processing methods.