Vegetation indices’ spatial prediction based novel algorithm for determining tsunami risk areas and risk values

• Published in: PeerJ. Computer science Vol. 8; p. e935
• Main Authors: Hartomo, Kristoko Dwi, Nataliani, Yessica, Hasibuan, Zainal Arifin
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 28.03.2022; PeerJ, Inc; PeerJ Inc
• Subjects: Algorithms; Algorithms and Analysis of Algorithms; Atmospheric correction; Atmospheric models; Classification; Climate change; Comparative analysis; Data Mining and Machine Learning; Disasters; Earthquakes; Machine learning; Methods; Neural networks; Prediction models; Remote sensing; Risk; Risk areas; Risk values; Spatial; Spatial and Geographic Information Systems; Support vector machines; Tsunami; Tsunamis; Vegetation; Vegetation index; Indonesia; Tsunami; Risk values; Risk areas; Vegetation index; Spatial
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.935

This paper aims to propose a new algorithm to detect tsunami risk areas based on spatial modeling of vegetation indices and a prediction model to calculate the tsunami risk value. It employs atmospheric correction using DOS1 algorithm combined with k -NN algorithm to classify and predict tsunami-affected areas from vegetation indices data that have spatial and temporal resolutions. Meanwhile, the model uses the vegetation indices ( i.e ., NDWI, NDVI, SAVI), slope, and distance. The result of the experiment compared to other classification algorithms demonstrates good results for the proposed model. It has the smallest MSEs of 0.0002 for MNDWI, 0.0002 for SAVI, 0.0006 for NDVI, 0.0003 for NDWI, and 0.0003 for NDBI. The experiment also shows that the accuracy rate for the prediction model is about 93.62%.