Novel approach of association rule mining for tree canopy assessment
Abstract
The evolution of technology and availability of voluminous satellite images are bringing a new scenario in satellite image classification were a novel method for predictive analysis of satellite images for land cover classification needs to be devised. The predictive analysis of these rapidly changing, voluminous data requires a performance efficient method to assess tree canopy in urban areas. Tree canopy assessment depends on weather condition as well as it varies with geographical region. As urban areas are growing at the faster rate, special attention needs to be given to solve tree canopy assessment in urban areas. The satellite images have spectral, spatial and temporal information available with them. Vegetation indices are calculated from spectral information of satellite images. Literature shows that vegetation indices play an important role in tree canopy assessment. Hundreds of such vegetation indices are available to detect vegetation from a satellite image. The contribution of this paper is designing an improved Apriori algorithm for to select optimal number of vegetation indices for tree canopy assessment. Soin this research paper, we propose a novel computational approach that allows the improvement of results than the existing techniques. It selects optimal combination of vegetation indices and further applies principal component analysis (PCA) on it. It uses a greedy approach based on modified association rule mining. This study emphasizes on assessment of tree canopy using GPU-enabled environment for performance-efficient tree canopy assessment and analysis. The results achieved from the novel method are comparable to state-of-the-art techniques, with an accuracy of 96%. The research paper has considered four years data for the Mumbai region of India. This research can be used by Green India Mission of India to assess tree canopy of fast changing geographical region.
Keywords
Google earth engine, High performance computing, Tree canopy, PCA, Sentinel 2 dataset, SVM classifier
DOI: http://doi.org/10.11591/ijai.v10.i3.pp%25p
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.