Author: CSDN @ _Yakult_
This article will introduce the code to extract a specified proportion (50% in this example) of sample data in each category on the Google Earth Engine (GEE) platform to obtain a new vector data. This process is stratified sampling. This method can be used in machine learning classification to reduce errors, improve efficiency, reduce computing resources, and increase sample representativeness.
The result is shown in the figure below,
The distribution of sample points before stratified sampling is shown in the figure below.
The distribution of sample points after stratified sampling is shown in the figure below.
