Mining Land Cover Information Using Multilayer Perceptron and Decision Tree from MODIS Data

Abstract

Land cover (LC) changes play a major role in global as well as at regional scale patterns of the climate and biogeochemistry of the Earth system. LC information presents critical insights in understanding of Earth surface phenomena, particularly useful when obtained synoptically from remote sensing data. However, for developing countries and those with large geographical extent, regular LC mapping is prohibitive with data from commercial sensors (high cost factor) of limited spatial coverage (low temporal resolution and band swath). In this context, free MODIS data with good spectrotemporal resolution meet the purpose. LC mapping from these data has continuously evolved with advances in classification algorithms. This paper presents a comparative study of two robust data mining techniques, the multilayer perceptron (MLP) and decision tree (DT) on different products of MODIS data corresponding to Kolar district, Karnataka, India. The MODIS classified images when compared at three different spatial scales (at district level, taluk level and pixel level) shows that MLP based classification on minimum noise fraction components on MODIS 36 bands provide the most accurate LC mapping with 86% accuracy, while DT on MODIS 36 bands principal components leads to less accurate classification (69%).

Data Mining Techniques for Separation of Summer Crop Based on Satellite Images

“…Similar results were found by Nonato & Oliveira (2013) in the identification of areas of sugarcane and Kumar et al (2010) in soil cover.…”

Hyperspectral Images Classification Based on Fusion Features Derived From 1d and 2d Convolutional Neural Network

“…Although the classification efficiency is improved, to a certain extent, rich feature information lost, resulting in low classification accuracy. On the other hand, compared with the traditional Maximum Likelihood Classification (MLC), Spectral Angle Mapper (SAM) and other algorithms (Kumar et al, 2010), although the performance of some new algorithms such as Support Vector Machine (SVM) (Mountrakis et al, 2011) and Random Forest (RF) is continuously improving, extracting limited spectral information with single classifier can not meet the needs of high precision classification. How to make full use of spectral information and spatial information of hyperspectral images data and combine with multi-model classification is the * Corresponding author research trend.…”

Land Use Classification and Analysis Using Radar Data Mining in Ethiopia

“…Decision trees yield a set of rules which are easy to interpret and suitable for deriving a physical understanding of the classification process (DeFries and Chan, 2000). In decision tree, a minimum error or entropy is used as a threshold to select each class (Kumar et al, 2010).…”

“…Neural networks use less statistical assumptions than maximum likelihood algorithms and makes no prior assumptions of normal distribution A research study by Yuan et al (2009), recommends that in complex land use mapping applications, supervised MLP networks may be used to derive detailed and more accurate image classification. The difficulties in conventional classification can be improved using Neural Network (NN) (Kumar et al, 2010). According to Idol et al (2015), classification algorithms such as NN are important for radar data classification.…”