Mapping of Shorea robusta Forest Using Time Series MODIS Data

Mapping forest types in a natural heterogeneous forest environment using remote sensing data is a long-standing challenge due to similar spectral reflectance from different tree species and significant time and resources are required for acquiring and processing the remote sensing data. The purpose...

Mô tả chi tiết

Lưu vào:
Hiển thị chi tiết
Tác giả chính: Ghimire, B.R.
Định dạng: BB
Ngôn ngữ:eng
Thông tin xuất bản: 2020
Chủ đề:
Truy cập trực tuyến:http://tailieuso.tlu.edu.vn/handle/DHTL/4812
Từ khóa: Thêm từ khóa bạn đọc
Không có từ khóa, Hãy là người đầu tiên gắn từ khóa cho biểu ghi này!
id oai:localhost:DHTL-4812
record_format dspace
spelling oai:localhost:DHTL-48122020-03-30T02:14:16Z Mapping of Shorea robusta Forest Using Time Series MODIS Data Ghimire, B.R. Ghimire, B.R. support vector machine (SVM) normalized differential vegetation index (NDVI) enhanced vegetation index (EVI) Sal forest Random forest Image reduction Boruta algorithm Phenology Mapping forest types in a natural heterogeneous forest environment using remote sensing data is a long-standing challenge due to similar spectral reflectance from different tree species and significant time and resources are required for acquiring and processing the remote sensing data. The purpose of this research was to determine the optimum number of remote sensing images and map the Sal forest through the analysis of Vegetation Index (VI) signatures. We analyzed the eight days’ composite moderate resolution imaging spectroradiometer (MODIS) time series normalized differential vegetation index (NDVI), and enhanced vegetation index (EVI) for the whole year of 2015. Jeffries-Matusita (J-M) distance was used for the separability index. Performance of EVI and NDVI was tested using random forest (RF) and support vector machine (SVM) classifiers. Boruta algorithm and statistical analysis were performed to identify the optimum set of imageries. We also performed data level five-fold cross validation of the model and field level accuracy assessment of the classification map. The finding confirmed that EVI with SVM (F-score of Sal 0.88) performed better than NDVI with either SVM or RF. The optimum 12 images during growing and post monsoon season significantly decreased processing time (to one-fourth) without much deteriorating accuracy. Accordingly, we were able to map the Sal forest whose area is accounted for about 36% of the 82% forest cover in the study area. The proposed methodology can be extended to produce a temporal forest type classification map in any other location. https://www.mdpi.com/1999-4907/8/10/384/htm 2020-02-18T02:27:51Z 2020-02-18T02:27:51Z 2017 20191023101625.0 130605s2017 BB Forests8 (2017)10, article no. 384, 18 p http://tailieuso.tlu.edu.vn/handle/DHTL/4812 eng
institution Trường Đại học Thủy Lợi
collection DSpace
language eng
topic support vector machine (SVM)
normalized differential vegetation index (NDVI)
enhanced vegetation index (EVI)
Sal forest
Random forest
Image reduction
Boruta algorithm
Phenology
spellingShingle support vector machine (SVM)
normalized differential vegetation index (NDVI)
enhanced vegetation index (EVI)
Sal forest
Random forest
Image reduction
Boruta algorithm
Phenology
Ghimire, B.R.
Ghimire, B.R.
Mapping of Shorea robusta Forest Using Time Series MODIS Data
description Mapping forest types in a natural heterogeneous forest environment using remote sensing data is a long-standing challenge due to similar spectral reflectance from different tree species and significant time and resources are required for acquiring and processing the remote sensing data. The purpose of this research was to determine the optimum number of remote sensing images and map the Sal forest through the analysis of Vegetation Index (VI) signatures. We analyzed the eight days’ composite moderate resolution imaging spectroradiometer (MODIS) time series normalized differential vegetation index (NDVI), and enhanced vegetation index (EVI) for the whole year of 2015. Jeffries-Matusita (J-M) distance was used for the separability index. Performance of EVI and NDVI was tested using random forest (RF) and support vector machine (SVM) classifiers. Boruta algorithm and statistical analysis were performed to identify the optimum set of imageries. We also performed data level five-fold cross validation of the model and field level accuracy assessment of the classification map. The finding confirmed that EVI with SVM (F-score of Sal 0.88) performed better than NDVI with either SVM or RF. The optimum 12 images during growing and post monsoon season significantly decreased processing time (to one-fourth) without much deteriorating accuracy. Accordingly, we were able to map the Sal forest whose area is accounted for about 36% of the 82% forest cover in the study area. The proposed methodology can be extended to produce a temporal forest type classification map in any other location.
format BB
author Ghimire, B.R.
Ghimire, B.R.
author_facet Ghimire, B.R.
Ghimire, B.R.
author_sort Ghimire, B.R.
title Mapping of Shorea robusta Forest Using Time Series MODIS Data
title_short Mapping of Shorea robusta Forest Using Time Series MODIS Data
title_full Mapping of Shorea robusta Forest Using Time Series MODIS Data
title_fullStr Mapping of Shorea robusta Forest Using Time Series MODIS Data
title_full_unstemmed Mapping of Shorea robusta Forest Using Time Series MODIS Data
title_sort mapping of shorea robusta forest using time series modis data
publishDate 2020
url http://tailieuso.tlu.edu.vn/handle/DHTL/4812
work_keys_str_mv AT ghimirebr mappingofshorearobustaforestusingtimeseriesmodisdata
AT ghimirebr mappingofshorearobustaforestusingtimeseriesmodisdata
_version_ 1787739979903926272