Forest data visualization and land mapping using support vector machines and decision trees

Autor: Sujatha Radhakrishnan, Jyotir Moy Chatterjee, Aarthy Seshadri Lakshminarayanan, D. Jude Hemanth
Rok vydání: 2020
Předmět:
Zdroj: Earth Science Informatics. 13:1119-1137
ISSN: 1865-0481
1865-0473
Popis: Forests play a vital role in the regulation of climate, absorption of carbon dioxide, hydrological cycle, conservation of water, soil and biodiversity and help mitigate natural disasters. With the help of various remote sensors, high-resolution satellite images are being collected nowadays, which helps in tackling the global challenges of forest mapping in remote areas. Each landscape will grow different types of trees and in turn substantiate a part of the country’s economy. This paper uses visualization and machine learning (ML) processes to classify the forest land on the terrain dataset composed of the advanced spaceborne thermal emission and reflection radiometer (ASTER) imaging instrument to get the insight of the cumulated data by using Box Plot and Heat Map. The accuracy obtained by utilizing different machine learning techniques like Support Vector Machine (SVM) gives 95.4%, Logistic Regression (LR) gives 94.5%, K-Nearest Neighbor (K-NN) gives 93.7%, Decision Tree (DT) with 89.5%, Stochastic Gradient Descendent (SGD) with 92.4% and CN2 Rule Induction (RI) gives 85.3% are allied which gives appreciable results in forest mapping substantiated the same with confusion matrix and ROC. We also obtained the DT and rules for the considered dataset.
Databáze: OpenAIRE
Externí odkaz: