Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network
Recently, due to the acceleration of global warming, an accurate understanding and management of forest carbon stocks, such as forest aboveground biomass, has become very important. The vertical structure of the forest, which is the internal structure of the forest, was mainly investigated by field...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/5/797 |
| _version_ | 1798017121197752320 |
|---|---|
| author | Yong-Suk Lee Sunmin Lee Won-Kyung Baek Hyung-Sup Jung Sung-Hwan Park Moung-Jin Lee |
| author_facet | Yong-Suk Lee Sunmin Lee Won-Kyung Baek Hyung-Sup Jung Sung-Hwan Park Moung-Jin Lee |
| author_sort | Yong-Suk Lee |
| collection | DOAJ |
| description | Recently, due to the acceleration of global warming, an accurate understanding and management of forest carbon stocks, such as forest aboveground biomass, has become very important. The vertical structure of the forest, which is the internal structure of the forest, was mainly investigated by field surveys that are labor intensive. Recently, remote sensing techniques have been actively used to explore large and inaccessible areas. In addition, machine learning techniques that could classify and analyze large amounts of data are being used in various fields. Thus, this study aims to analyze the forest vertical structure (number of tree layers) to estimate forest aboveground biomass in Jeju Island from optical and radar satellite images using artificial neural networks (ANN). For this purpose, the eight input neurons of the forest related layers, based on remote sensing data, were prepared: normalized difference vegetation index (NDVI), normalized difference water index (NDWI), NDVI texture, NDWI texture, average canopy height, standard deviation canopy height and two types of coherence maps were created using the Kompsat-3 optical image, L-band ALOS PALSAR-1 radar images, digital surface model (DSM), and digital terrain model (DTM). The forest vertical structure data, based on field surveys, was divided into the training/validation and test data and the hyper-parameters of ANN were trained using the training/validation data. The forest vertical classification result from ANN was evaluated by comparison to the test data. It showed about a 65.7% overall accuracy based on the error matrix. This result shows that the forest vertical structure map can be effectively generated from optical and radar satellite images and existing DEM and DTM using the ANN approach, especially for national scale mapping. |
| first_indexed | 2024-04-11T16:01:42Z |
| format | Article |
| id | doaj.art-a11bcb3dec7844f2910c91ffe8c674b4 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-04-11T16:01:42Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-a11bcb3dec7844f2910c91ffe8c674b42022-12-22T04:14:57ZengMDPI AGRemote Sensing2072-42922020-03-0112579710.3390/rs12050797rs12050797Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural NetworkYong-Suk Lee0Sunmin Lee1Won-Kyung Baek2Hyung-Sup Jung3Sung-Hwan Park4Moung-Jin Lee5Department of Geoinformatics, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, KoreaDepartment of Geoinformatics, University of Seoul, 163 Seoulsiripdaero, Dongdaemun-gu, Seoul 02504, KoreaCenter for Environmental Assessment Monitoring, Environmental Assessment Group, Korea Environment Institute (KEI), 370 Sicheong-daero, Sejong-si 30147, KoreaRecently, due to the acceleration of global warming, an accurate understanding and management of forest carbon stocks, such as forest aboveground biomass, has become very important. The vertical structure of the forest, which is the internal structure of the forest, was mainly investigated by field surveys that are labor intensive. Recently, remote sensing techniques have been actively used to explore large and inaccessible areas. In addition, machine learning techniques that could classify and analyze large amounts of data are being used in various fields. Thus, this study aims to analyze the forest vertical structure (number of tree layers) to estimate forest aboveground biomass in Jeju Island from optical and radar satellite images using artificial neural networks (ANN). For this purpose, the eight input neurons of the forest related layers, based on remote sensing data, were prepared: normalized difference vegetation index (NDVI), normalized difference water index (NDWI), NDVI texture, NDWI texture, average canopy height, standard deviation canopy height and two types of coherence maps were created using the Kompsat-3 optical image, L-band ALOS PALSAR-1 radar images, digital surface model (DSM), and digital terrain model (DTM). The forest vertical structure data, based on field surveys, was divided into the training/validation and test data and the hyper-parameters of ANN were trained using the training/validation data. The forest vertical classification result from ANN was evaluated by comparison to the test data. It showed about a 65.7% overall accuracy based on the error matrix. This result shows that the forest vertical structure map can be effectively generated from optical and radar satellite images and existing DEM and DTM using the ANN approach, especially for national scale mapping.https://www.mdpi.com/2072-4292/12/5/797forest vertical structurekompsat-3alos palsar-1artificial neural network |
| spellingShingle | Yong-Suk Lee Sunmin Lee Won-Kyung Baek Hyung-Sup Jung Sung-Hwan Park Moung-Jin Lee Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network Remote Sensing forest vertical structure kompsat-3 alos palsar-1 artificial neural network |
| title | Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network |
| title_full | Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network |
| title_fullStr | Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network |
| title_full_unstemmed | Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network |
| title_short | Mapping Forest Vertical Structure in Jeju Island from Optical and Radar Satellite Images Using Artificial Neural Network |
| title_sort | mapping forest vertical structure in jeju island from optical and radar satellite images using artificial neural network |
| topic | forest vertical structure kompsat-3 alos palsar-1 artificial neural network |
| url | https://www.mdpi.com/2072-4292/12/5/797 |
| work_keys_str_mv | AT yongsuklee mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork AT sunminlee mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork AT wonkyungbaek mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork AT hyungsupjung mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork AT sunghwanpark mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork AT moungjinlee mappingforestverticalstructureinjejuislandfromopticalandradarsatelliteimagesusingartificialneuralnetwork |