Neural Network for Satellite Data Classification Using Tensorflow in Python

Deep Learning has taken over the majority of fields in solving complex problems, and the geospatial field is no exception. The title of the article interests you and hence, I hope that you are familiar with satellite datasets; for now, Landsat 5 TM. Little knowledge of how Machine Learning (ML) algorithms work, will help you grasp this hands-on tutorial quickly. For those who are unfamiliar with ML concept, in a nutshell, it is establishing the relationship between a few characteristics (features or Xs) of an entity with its other property (value or label or Y) -- we provide plenty of examples (labelled data) to the model so that it learns from it and then predicts values/ labels for the new data (unlabelled data). That is enough of theory brush-up for machine learning!