Smart Techniques for LULC Micro Class Classification Using Landsat8 Imagery

Wheat species play important role in the price of products and wheat production estimation. There are several mathematical models used for the estimation of the wheat crop but these models are implemented without considering the wheat species which is an important independent variable. The task of wheat species identification is challenging both for human experts as well as for computer vision-based solutions. With the use of satellite remote sensing, it is possible to identify and monitor wheat species on a large scale at any stage of the crop life cycle. In this work, nine popular wheat species are identified by using Landsat8 operational land imager (OLI) and thermal infrared sensor (TIRS) data. Two thousand samples of each wheat crop species are acquired every fifteen days with a temporal resolution of ten multispectral bands (band two to band eleven). This study employs random forest (RF), artificial neural network, support vector machine, Naïve Bayes, and logistic regression for nine types of wheat classification. In addition, deep neural networks are also developed. Experimental results indicate that RF shows the best performance of 91% accuracy while DNN obtains a 90.2% accuracy. Results suggest that remotely sensed data can be used in wheat type estimation and to improve the performance of the mathematical models.