Deep Convolutional Neural Networks: Theory and Application in Geosciences

A new tool for Geoscientists to observe insights in geographical data that they have never seen before.

Image Source : University of Copenhagen

Introduction: Deep Convolutional Neural Networks (DCNN) is a Deep Learning (DL) Method which is different from normal Convolutional Neural Network (CNN) in terms of number of hidden layers usually more than 5 which are used to extract more features and increase the accuracy of the prediction .There are two kinds of DCNN, one is increasing the number of hidden layers or by increasing the number of nodes in the hidden layer. The DCNN method that has been widely and successfully applied to computer vision tasks including object localization, detection, and image classification is a supervised learning task that uses the raw data to determine the classification features, in contrast to other machine learning (ML) techniques that require pre-selection of the input features (or attributes). There are many types of DCNN are introduce in various studies which are following:

• LeNet
• AlexNet
• GoogLeNet / Inception
• VGG
• ResNets for ImageNet
• ResNets for CIFAR10
• DenseNets for ImageNet