Seasonal Multi-temporal Pixel Based Crop Types and Land Cover Classification for Satellite Images using Convolutional Neural Networks

Abstract

Nowadays, Satellite images have become a major source of data for many aspects of development. Land and crops classification using satellite images is a recent important subject. From the other side, Deep Convolutional Neural Networks (DCNNs) is a powerful technique for understanding images. This paper describes a pixel based crops and land cover classification originating from one source satellite imagery represented by Sentinel satellite and based on several dates for the same agricultural season. We propose a DCNN architecture based on multi-temporal data that was fed to a one-dimension (1-D DCNN). The proposed architecture is compared with other methods of satellite image classification algorithms; such as Support Vector Machines (SVMs), Random Forests (RFs) and k-Nearest Neighbors (k-NNs). Experiments are conducted for the mutual experiment of major crops and land cover classification for Al-Fayoum governorate in Egypt. The 1-D DCNN achieves about 89% accuracy using 10 spectral bands from Sentinel-2 satellite imagery database for the area of interest. The proposed architecture although it outperforms other methods, needs further research to optimize the memory usage.