Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine
Recent studies have demonstrated the potential of using bidirectional reflectance distribution function (BRDF) signatures captured by multi-angle observation data to enhance land cover classification and retrieve vegetation architectures. Considering the diversity of crop architectures, we proposed...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-05-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/11/2761 |
_version_ | 1797596886301933568 |
---|---|
author | Zhijun Zhen Shengbo Chen Tiangang Yin Jean-Philippe Gastellu-Etchegorry |
author_facet | Zhijun Zhen Shengbo Chen Tiangang Yin Jean-Philippe Gastellu-Etchegorry |
author_sort | Zhijun Zhen |
collection | DOAJ |
description | Recent studies have demonstrated the potential of using bidirectional reflectance distribution function (BRDF) signatures captured by multi-angle observation data to enhance land cover classification and retrieve vegetation architectures. Considering the diversity of crop architectures, we proposed that crop mapping precision may be enhanced by using BRDF signatures. We compared the accuracy of four supervised machine learning classifiers provided by the Google Earth Engine (GEE), namely random forest (RF), classification and regression trees (CART), support vector machine (SVM), and Naïve Bayes (NB), using the moderate resolution imaging spectroradiometer (MODIS) nadir BRDF-adjusted reflectance data (MCD43A4 V6) and BRDF and albedo model parameter data (MCD43A1 V6) as input. Our results indicated that using BRDF signatures leads to a moderate improvement in classification results in most cases, compared to using reflectance data from a single nadir observation direction. Specifically, the overall validation accuracy increased by up to 4.9%, and the validation kappa coefficients increased by up to 0.092. Furthermore, the classifiers were ranked in order of accuracy, from highest to lowest: RF, CART, SVM, and NB. Our study contributes to the development of crop mapping and the application of multi-angle observation satellites. |
first_indexed | 2024-03-11T02:59:05Z |
format | Article |
id | doaj.art-e94b5d4598bd41e29e7fa7d11577f344 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T02:59:05Z |
publishDate | 2023-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-e94b5d4598bd41e29e7fa7d11577f3442023-11-18T08:28:20ZengMDPI AGRemote Sensing2072-42922023-05-011511276110.3390/rs15112761Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth EngineZhijun Zhen0Shengbo Chen1Tiangang Yin2Jean-Philippe Gastellu-Etchegorry3College of Geoexploration Science and Technology, Jilin University, Changchun 130026, ChinaCollege of Geoexploration Science and Technology, Jilin University, Changchun 130026, ChinaDepartment of Land Surveying and Geo-Informatics, The Hong Kong Polytechnic University, Hong Kong, ChinaCESBIO, CNES-CNRS-IRD-UPS, University of Toulouse, CEDEX 09, 31401 Toulouse, FranceRecent studies have demonstrated the potential of using bidirectional reflectance distribution function (BRDF) signatures captured by multi-angle observation data to enhance land cover classification and retrieve vegetation architectures. Considering the diversity of crop architectures, we proposed that crop mapping precision may be enhanced by using BRDF signatures. We compared the accuracy of four supervised machine learning classifiers provided by the Google Earth Engine (GEE), namely random forest (RF), classification and regression trees (CART), support vector machine (SVM), and Naïve Bayes (NB), using the moderate resolution imaging spectroradiometer (MODIS) nadir BRDF-adjusted reflectance data (MCD43A4 V6) and BRDF and albedo model parameter data (MCD43A1 V6) as input. Our results indicated that using BRDF signatures leads to a moderate improvement in classification results in most cases, compared to using reflectance data from a single nadir observation direction. Specifically, the overall validation accuracy increased by up to 4.9%, and the validation kappa coefficients increased by up to 0.092. Furthermore, the classifiers were ranked in order of accuracy, from highest to lowest: RF, CART, SVM, and NB. Our study contributes to the development of crop mapping and the application of multi-angle observation satellites.https://www.mdpi.com/2072-4292/15/11/2761bidirectional reflectance distribution function (BRDF)crop mappingGoogle Earth Engine (GEE)kernel-driven modelsupervised classification |
spellingShingle | Zhijun Zhen Shengbo Chen Tiangang Yin Jean-Philippe Gastellu-Etchegorry Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine Remote Sensing bidirectional reflectance distribution function (BRDF) crop mapping Google Earth Engine (GEE) kernel-driven model supervised classification |
title | Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine |
title_full | Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine |
title_fullStr | Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine |
title_full_unstemmed | Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine |
title_short | Improving Crop Mapping by Using Bidirectional Reflectance Distribution Function (BRDF) Signatures with Google Earth Engine |
title_sort | improving crop mapping by using bidirectional reflectance distribution function brdf signatures with google earth engine |
topic | bidirectional reflectance distribution function (BRDF) crop mapping Google Earth Engine (GEE) kernel-driven model supervised classification |
url | https://www.mdpi.com/2072-4292/15/11/2761 |
work_keys_str_mv | AT zhijunzhen improvingcropmappingbyusingbidirectionalreflectancedistributionfunctionbrdfsignatureswithgoogleearthengine AT shengbochen improvingcropmappingbyusingbidirectionalreflectancedistributionfunctionbrdfsignatureswithgoogleearthengine AT tiangangyin improvingcropmappingbyusingbidirectionalreflectancedistributionfunctionbrdfsignatureswithgoogleearthengine AT jeanphilippegastelluetchegorry improvingcropmappingbyusingbidirectionalreflectancedistributionfunctionbrdfsignatureswithgoogleearthengine |