Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning

Preparing regular time series optical remote sensing data is a difficult task due to the influences of frequently cloudy and rainy days. The irregular data and their forms severely limit the data’s ability to be analyzed and modeled for vegetation classification. However, how irregular time series d...

Full description

Saved in:
Bibliographic Details
Main Authors: Ming Zhang, Dengqiu Li, Guiying Li, Dengsheng Lu
Format: Article
Language:English
Published: Taylor & Francis Group 2025-01-01
Series:Geo-spatial Information Science
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/10095020.2024.2336604
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763241489596416
author Ming Zhang
Dengqiu Li
Guiying Li
Dengsheng Lu
author_facet Ming Zhang
Dengqiu Li
Guiying Li
Dengsheng Lu
author_sort Ming Zhang
collection DOAJ
description Preparing regular time series optical remote sensing data is a difficult task due to the influences of frequently cloudy and rainy days. The irregular data and their forms severely limit the data’s ability to be analyzed and modeled for vegetation classification. However, how irregular time series data affect vegetation classification in deep learning models is poorly understood. To address these questions, this research preprocessed the 2019–2021 time series of Sentinel-2 in both unequal and equal intervals, and transformed them into an image through recurrence plot for each pixel. The initial one-dimension time series (1DTS) and recurrence plot data were then used as input data for three deep learning methods (i.e. Conv1D model based on one-dimensional convolution, GoogLeNet model based on two-dimensional convolution, and CGNet model which fused Conv1D and GoogLeNet) for vegetation classification, respectively. The class separability of the features generated by each model was evaluated and the importance of spectral and temporal features was further examined through gradient backpropagation. The equal-interval time series data significantly improved the classification accuracy with 0.04, 0.13, and 0.09 for Conv1D, GoogLeNet, and CGNet, respectively. The CGNet achieved the highest classification accuracy, indicating that the information from 1DTS and recurrence plot can be a good complementary for vegetation classification. The importance of spectral bands and time showed that the Sentinel-2 red edge-1 spectral band played a critical role in the identification of eucalyptus, loquat, and honey pomelo, but the importance order of bands varied in different vegetation types in GoogLeNet. The time importance varied across different vegetation types but is similar in these deep learning models. This study quantified the impacts of organizational form (1DTS and recurrence plot) of time series data on different models. This research is valuable for us to choose appropriate data structures and efficient deep learning models for vegetation classification.
format Article
id doaj-art-6259072ba5bd4fa8bdfa3220db16099f
institution DOAJ
issn 1009-5020
1993-5153
language English
publishDate 2025-01-01
publisher Taylor & Francis Group
record_format Article
series Geo-spatial Information Science
spelling doaj-art-6259072ba5bd4fa8bdfa3220db16099f2025-08-20T03:05:27ZengTaylor & Francis GroupGeo-spatial Information Science1009-50201993-51532025-01-0128114516310.1080/10095020.2024.2336604Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learningMing Zhang0Dengqiu Li1Guiying Li2Dengsheng Lu3Institute of Geography, Fujian Normal University, Fuzhou, ChinaInstitute of Geography, Fujian Normal University, Fuzhou, ChinaInstitute of Geography, Fujian Normal University, Fuzhou, ChinaInstitute of Geography, Fujian Normal University, Fuzhou, ChinaPreparing regular time series optical remote sensing data is a difficult task due to the influences of frequently cloudy and rainy days. The irregular data and their forms severely limit the data’s ability to be analyzed and modeled for vegetation classification. However, how irregular time series data affect vegetation classification in deep learning models is poorly understood. To address these questions, this research preprocessed the 2019–2021 time series of Sentinel-2 in both unequal and equal intervals, and transformed them into an image through recurrence plot for each pixel. The initial one-dimension time series (1DTS) and recurrence plot data were then used as input data for three deep learning methods (i.e. Conv1D model based on one-dimensional convolution, GoogLeNet model based on two-dimensional convolution, and CGNet model which fused Conv1D and GoogLeNet) for vegetation classification, respectively. The class separability of the features generated by each model was evaluated and the importance of spectral and temporal features was further examined through gradient backpropagation. The equal-interval time series data significantly improved the classification accuracy with 0.04, 0.13, and 0.09 for Conv1D, GoogLeNet, and CGNet, respectively. The CGNet achieved the highest classification accuracy, indicating that the information from 1DTS and recurrence plot can be a good complementary for vegetation classification. The importance of spectral bands and time showed that the Sentinel-2 red edge-1 spectral band played a critical role in the identification of eucalyptus, loquat, and honey pomelo, but the importance order of bands varied in different vegetation types in GoogLeNet. The time importance varied across different vegetation types but is similar in these deep learning models. This study quantified the impacts of organizational form (1DTS and recurrence plot) of time series data on different models. This research is valuable for us to choose appropriate data structures and efficient deep learning models for vegetation classification.https://www.tandfonline.com/doi/10.1080/10095020.2024.2336604Sentinel-2time seriesrecurrence plotconvolutional neural network (CNN)vegetation classificationsubtropical ecosystem
spellingShingle Ming Zhang
Dengqiu Li
Guiying Li
Dengsheng Lu
Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
Geo-spatial Information Science
Sentinel-2
time series
recurrence plot
convolutional neural network (CNN)
vegetation classification
subtropical ecosystem
title Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
title_full Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
title_fullStr Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
title_full_unstemmed Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
title_short Vegetation classification in a subtropical region with Sentinel-2 time series data and deep learning
title_sort vegetation classification in a subtropical region with sentinel 2 time series data and deep learning
topic Sentinel-2
time series
recurrence plot
convolutional neural network (CNN)
vegetation classification
subtropical ecosystem
url https://www.tandfonline.com/doi/10.1080/10095020.2024.2336604
work_keys_str_mv AT mingzhang vegetationclassificationinasubtropicalregionwithsentinel2timeseriesdataanddeeplearning
AT dengqiuli vegetationclassificationinasubtropicalregionwithsentinel2timeseriesdataanddeeplearning
AT guiyingli vegetationclassificationinasubtropicalregionwithsentinel2timeseriesdataanddeeplearning
AT dengshenglu vegetationclassificationinasubtropicalregionwithsentinel2timeseriesdataanddeeplearning