Land Cover Information Extraction Based on Daily NDVI Time Series and Multiclassifier Combination

Abstract

A timely and accurate understanding of land cover change has great significance in management of area resources. To explore the application of a daily normalized difference vegetation index (NDVI) time series in land cover classification, the present study used HJ-1 data to derive a daily NDVI time series by pretreatment. Different classifiers were then applied to classify the daily NDVI time series. Finally, the daily NDVI time series were classified based on multiclassifier combination. The results indicate that support vector machine (SVM), spectral angle mapper, and classification and regression tree classifiers can be used to classify daily NDVI time series, with SVM providing the optimal classification. The classifiers of -means and Mahalanobis distance are not suited for classification because of their classification accuracy and mechanism, respectively. This study proposes a method of dimensionality reduction based on the statistical features of daily NDVI time series for classification. The method can be applied to land resource information extraction. In addition, an improved multiclassifier combination is proposed. The classification results indicate that the improved multiclassifier combination is superior to different single classifier combinations, particularly regarding subclassifiers with greater differences.

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

“…Another related study proposed a new method for classifying daily NDVI time series data based on a combination of multi-classifiers ( Zhao et al, 2017 ). In this study, the HJ–CCD satellite was used as data for compiling an NDVI time series model with S–G filtering and spatial interpolation.…”

Urban land use land cover mapping in tropical savannah using Landsat-8 derived normalized difference vegetation index (NDVI) threshold

“…Several studies have revealed that multi-temporal remotely sensed data provide the distinctions between similar spectral of different land cover types (de Bie et al 2011;Miomir et al 2018;Usman et al 2015). Generally, NDVI values range from -1 to +1 (La et al 1987;Zhao et al 2017), where surface features like water, snow and cloud reflect more in the visible band than in the near-infrared band, thus represented as negative NDVI values.…”

Regional Land Cover Monitoring System for Hindu Kush Himalaya

“…Once the process of image correction was completed, 80 covariates were generated based on the Landsat annual composites, and SRTM DEM was then used as input to supervise the classification. Thus, the image indices collectively provided a critical parameter for classifying land cover, and this has a noticeable correlation with the particular land cover association (Zhao et al 2017;da Silva et al 2019).…”