Image Classification Using Machine Learning Algorithms in Google Earth Engine Environment

In this paper it is proposed to classify an image using a Machine Learning approach inside the Google Earth Engine platform and Jupyter Notebook: feeding the computer with training data (in our case being points/pixels having a label which represent the land-cover type), it will learn to recognize the type of pixel through a model built on the technique called supervised learning. Even if the reader is not so familiar with the GEE environment and with GEE data structures and data types (like image, image Collections, features, feature Collections, geometry etc.), we’ll try to guide him step by step in this modern exercise of building a machine learning model which, having the intelligence to guess the land-cover for each pixel, it will finally create a the-matic map, very useful for scientist and specialists. This is actually what it’s called Artificial In-telligence and the model built here can be re-used with new data, new images.