Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods
The Remote Sensing and machine learning techniques are cost-effective ways of mapping land use and cover, especially forestry areas. This is essential for the management and planning of such resources. The purpose of this study was to identify which classifier (Random Forest or Support Vector Machi...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universidade Federal de Uberlândia
2023-12-01
|
Series: | Revista Brasileira de Cartografia |
Subjects: | |
Online Access: | https://seer.ufu.br/index.php/revistabrasileiracartografia/article/view/67769 |
_version_ | 1797372284402401280 |
---|---|
author | Andressa Kossmann Ferla Fabio Marcelo Breunig Rafaelo Balbinot Ricardo Dal'Agnol da Silva |
author_facet | Andressa Kossmann Ferla Fabio Marcelo Breunig Rafaelo Balbinot Ricardo Dal'Agnol da Silva |
author_sort | Andressa Kossmann Ferla |
collection | DOAJ |
description |
The Remote Sensing and machine learning techniques are cost-effective ways of mapping land use and cover, especially forestry areas. This is essential for the management and planning of such resources. The purpose of this study was to identify which classifier (Random Forest or Support Vector Machine) reach the best accuracy in land use and cover classification and determine which is the best season of year for Pinus spp. forest mapping. PlanetScope multispectral image was used with 3.7 m of spatial resolution, collected over the coastal region of Rio Grande do Sul state. The input variables for the classifiers were the four spectral bands: RGB and NIR, and the NDVI vegetation index. In both classifiers, high accuracy values were obtained, as well as for all seasons of the year.
The Random Forest classifier obtained better results in the spring and summer seasons, while in the autumn and winter seasons there was no significant difference between the classifiers for the classification of Pinus spp. forests. The results reached an adequate precision to be used for the management and monitoring of the land use and cover in the municipality of São José do Norte, RS.
|
first_indexed | 2024-03-08T18:32:36Z |
format | Article |
id | doaj.art-4b1baa23f2524634b37792d88374d3cd |
institution | Directory Open Access Journal |
issn | 0560-4613 1808-0936 |
language | English |
last_indexed | 2024-03-08T18:32:36Z |
publishDate | 2023-12-01 |
publisher | Universidade Federal de Uberlândia |
record_format | Article |
series | Revista Brasileira de Cartografia |
spelling | doaj.art-4b1baa23f2524634b37792d88374d3cd2023-12-29T18:22:49ZengUniversidade Federal de UberlândiaRevista Brasileira de Cartografia0560-46131808-09362023-12-01750aMapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning MethodsAndressa Kossmann Ferla0Fabio Marcelo BreunigRafaelo BalbinotRicardo Dal'Agnol da SilvaUFSM The Remote Sensing and machine learning techniques are cost-effective ways of mapping land use and cover, especially forestry areas. This is essential for the management and planning of such resources. The purpose of this study was to identify which classifier (Random Forest or Support Vector Machine) reach the best accuracy in land use and cover classification and determine which is the best season of year for Pinus spp. forest mapping. PlanetScope multispectral image was used with 3.7 m of spatial resolution, collected over the coastal region of Rio Grande do Sul state. The input variables for the classifiers were the four spectral bands: RGB and NIR, and the NDVI vegetation index. In both classifiers, high accuracy values were obtained, as well as for all seasons of the year. The Random Forest classifier obtained better results in the spring and summer seasons, while in the autumn and winter seasons there was no significant difference between the classifiers for the classification of Pinus spp. forests. The results reached an adequate precision to be used for the management and monitoring of the land use and cover in the municipality of São José do Norte, RS. https://seer.ufu.br/index.php/revistabrasileiracartografia/article/view/67769MappingPineMachine LearningGISRemote Sensing |
spellingShingle | Andressa Kossmann Ferla Fabio Marcelo Breunig Rafaelo Balbinot Ricardo Dal'Agnol da Silva Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods Revista Brasileira de Cartografia Mapping Pine Machine Learning GIS Remote Sensing |
title | Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods |
title_full | Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods |
title_fullStr | Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods |
title_full_unstemmed | Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods |
title_short | Mapping Pinus spp. Forestry and Land Cover Classes Using High-resolution PlanetScope Satellite Data: Experimenting Images from Different Seasons and Machine Learning Methods |
title_sort | mapping pinus spp forestry and land cover classes using high resolution planetscope satellite data experimenting images from different seasons and machine learning methods |
topic | Mapping Pine Machine Learning GIS Remote Sensing |
url | https://seer.ufu.br/index.php/revistabrasileiracartografia/article/view/67769 |
work_keys_str_mv | AT andressakossmannferla mappingpinussppforestryandlandcoverclassesusinghighresolutionplanetscopesatellitedataexperimentingimagesfromdifferentseasonsandmachinelearningmethods AT fabiomarcelobreunig mappingpinussppforestryandlandcoverclassesusinghighresolutionplanetscopesatellitedataexperimentingimagesfromdifferentseasonsandmachinelearningmethods AT rafaelobalbinot mappingpinussppforestryandlandcoverclassesusinghighresolutionplanetscopesatellitedataexperimentingimagesfromdifferentseasonsandmachinelearningmethods AT ricardodalagnoldasilva mappingpinussppforestryandlandcoverclassesusinghighresolutionplanetscopesatellitedataexperimentingimagesfromdifferentseasonsandmachinelearningmethods |