Using Machine Learning for Land Suitability Classification

Abstract

Artificial intelligence and machine learning methods can be used to automate the land suitability classification. Multiple Classifier System (MCS) or ensemble methods are rapidly growing and receiving a lot of attention and proved to be more accurate and robust than an excellent single classifier in many fields. In this study a dataset based land suitability classification is addressed. It is done using a newly proposed ensemble classifier generation technique referred to as RotBoost, which is constructed by combining Rotation Forest and AdaBoost, and it is known to be the first time that RotBoost has been applied for suitability classification. The experiments conducted with the study area, Shavur plain, lies in the northern of Khuzestan province, southwest of Iran. It should be noted that suitability classes for the input data were calculated according to FAO method. This provides positive evidence for the utility of machine learning methods in land suitability classification especially MCS methods. The results demonstrate that RotBoost can generate ensemble classifiers with significantly higher prediction accuracy than either Rotation Forest or AdaBoost, which is about 99% and 88.5%, using two different performance evaluation measures.