Standardization of layers formula

It is difficult to give a direct answer, it depends on your data, the first thing is to be clear about the basics.

The first thing you should do is an exploratory data analysis (ESDA)

• The first formula: (x - mean) / stdv is a standardization, that is, you will bring your layer values to a scale defined by the standard deviation and centered around the mean. Your new values will represent how far around the mean that value is.

In this case you are assuming that the mean and standard deviation are a good descriptor of the distribution of your data. This is ideal, if your data has a normal distribution. This is true even if your data deviates from the normal distribution, due to the Cheviched theorem and the Central Limit theorem.

• The second formula ( x - min(x) ) / ( max(x) - min(x) ): you are simply scaling the values to a range of 0 to 1.
• If you want to have the benefits of standardization but some of your layers have very irregular distributions you can consider a third option, standardizing by considering the median (instead of the mean) and the interquartile range (instead of the standard deviation).

This approach tends to fit better with any distribution. The transformed value will represent in units the interquartile range that is so far from the median.