Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai
Soil organic matter (SOM) plays an important role in the field of climate change and terrestrial ecosystems. SOM in large areas, especially in urban areas, is difficult to monitor and estimate by traditional methods. Urban land structure is complex, and soil is a mixture of organic and inorganic con...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2021-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9432852/ |
_version_ | 1811266106841628672 |
---|---|
author | Xinxin Wang Jigang Han Xia Wang Huaiying Yao Lang Zhang |
author_facet | Xinxin Wang Jigang Han Xia Wang Huaiying Yao Lang Zhang |
author_sort | Xinxin Wang |
collection | DOAJ |
description | Soil organic matter (SOM) plays an important role in the field of climate change and terrestrial ecosystems. SOM in large areas, especially in urban areas, is difficult to monitor and estimate by traditional methods. Urban land structure is complex, and soil is a mixture of organic and inorganic constituents with different physical and chemical properties. Previous studies showed that remote sensing techniques that provide diverse data in the visible-near-infrared (VNIR)-shortwave infrared (SWIR) spectral range, are promising in the prediction of SOM content on a large scale. Sentinel-2 covers the important spectral bands (VNIR-SWIR) for SOM prediction with a short revisit time. Thus, this article aimed to evaluate the capacity of Sentinel-2 for SOM prediction in an urban area (i.e., Shanghai). 103 bare soil samples filtrated from 398 soil samples at a depth of 20 cm were selected. Three methods, partial least square regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The root mean square error (RMSE) of modelling (mRMSE) and the coefficient of determination (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>) of modelling <inline-formula> <tex-math notation="LaTeX">$(mR^{2})$ </tex-math></inline-formula> were used to reflect the accuracy of the model. The results show that PLSR has the poorest performance. ANN has the highest modelling accuracy (mRMSE = 7.387 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$mR^{2}=0.446$ </tex-math></inline-formula>). The ANN prediction accuracy of RMSE (pRMSE) is 4.713 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula> and the prediction accuracy of <inline-formula> <tex-math notation="LaTeX">$R^{2}~(pR^{2})$ </tex-math></inline-formula> is 0.723. For SVR, the pRMSE is 4.638 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula>, and the <inline-formula> <tex-math notation="LaTeX">$pR^{2}$ </tex-math></inline-formula> is 0.732. The prediction accuracy of SVR is slightly higher than that of ANN. The spatial distribution of SOM demonstrates that the value obtained by ANN is the closest to the range of the bare soil samples, and ANN performs better in vegetation-covered areas. Therefore, Sentinel-2 can be used to estimate SOM content in urban areas, and ANN is a promising method for SOM estimation. |
first_indexed | 2024-04-12T20:36:08Z |
format | Article |
id | doaj.art-8840340e04c947dca0ded6d647a6ca85 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T20:36:08Z |
publishDate | 2021-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-8840340e04c947dca0ded6d647a6ca852022-12-22T03:17:35ZengIEEEIEEE Access2169-35362021-01-019782157822510.1109/ACCESS.2021.30806899432852Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in ShanghaiXinxin Wang0https://orcid.org/0000-0002-1525-1019Jigang Han1Xia Wang2Huaiying Yao3Lang Zhang4Research Center for Environmental Ecology and Engineering, School of Environmental Ecology and Biological Engineering, Wuhan Institute of Technology, Wuhan, ChinaKey Laboratory of National Forestry and Grassland Administration on Ecological Landscaping of Challenging Urban Sites, Shanghai Engineering Research Center of Landscaping on Challenging Urban Sites, Shanghai Academy of Landscape Architecture Science and Planning, Shanghai, ChinaResearch Center for Environmental Ecology and Engineering, School of Environmental Ecology and Biological Engineering, Wuhan Institute of Technology, Wuhan, ChinaResearch Center for Environmental Ecology and Engineering, School of Environmental Ecology and Biological Engineering, Wuhan Institute of Technology, Wuhan, ChinaKey Laboratory of National Forestry and Grassland Administration on Ecological Landscaping of Challenging Urban Sites, Shanghai Engineering Research Center of Landscaping on Challenging Urban Sites, Shanghai Academy of Landscape Architecture Science and Planning, Shanghai, ChinaSoil organic matter (SOM) plays an important role in the field of climate change and terrestrial ecosystems. SOM in large areas, especially in urban areas, is difficult to monitor and estimate by traditional methods. Urban land structure is complex, and soil is a mixture of organic and inorganic constituents with different physical and chemical properties. Previous studies showed that remote sensing techniques that provide diverse data in the visible-near-infrared (VNIR)-shortwave infrared (SWIR) spectral range, are promising in the prediction of SOM content on a large scale. Sentinel-2 covers the important spectral bands (VNIR-SWIR) for SOM prediction with a short revisit time. Thus, this article aimed to evaluate the capacity of Sentinel-2 for SOM prediction in an urban area (i.e., Shanghai). 103 bare soil samples filtrated from 398 soil samples at a depth of 20 cm were selected. Three methods, partial least square regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The root mean square error (RMSE) of modelling (mRMSE) and the coefficient of determination (<inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula>) of modelling <inline-formula> <tex-math notation="LaTeX">$(mR^{2})$ </tex-math></inline-formula> were used to reflect the accuracy of the model. The results show that PLSR has the poorest performance. ANN has the highest modelling accuracy (mRMSE = 7.387 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula>, <inline-formula> <tex-math notation="LaTeX">$mR^{2}=0.446$ </tex-math></inline-formula>). The ANN prediction accuracy of RMSE (pRMSE) is 4.713 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula> and the prediction accuracy of <inline-formula> <tex-math notation="LaTeX">$R^{2}~(pR^{2})$ </tex-math></inline-formula> is 0.723. For SVR, the pRMSE is 4.638 g kg<inline-formula> <tex-math notation="LaTeX">$^{-1}$ </tex-math></inline-formula>, and the <inline-formula> <tex-math notation="LaTeX">$pR^{2}$ </tex-math></inline-formula> is 0.732. The prediction accuracy of SVR is slightly higher than that of ANN. The spatial distribution of SOM demonstrates that the value obtained by ANN is the closest to the range of the bare soil samples, and ANN performs better in vegetation-covered areas. Therefore, Sentinel-2 can be used to estimate SOM content in urban areas, and ANN is a promising method for SOM estimation.https://ieeexplore.ieee.org/document/9432852/Soil organic matter estimationShanghaisentinel-2indexesartificial neural networksupport vector machine |
spellingShingle | Xinxin Wang Jigang Han Xia Wang Huaiying Yao Lang Zhang Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai IEEE Access Soil organic matter estimation Shanghai sentinel-2 indexes artificial neural network support vector machine |
title | Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai |
title_full | Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai |
title_fullStr | Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai |
title_full_unstemmed | Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai |
title_short | Estimating Soil Organic Matter Content Using Sentinel-2 Imagery by Machine Learning in Shanghai |
title_sort | estimating soil organic matter content using sentinel 2 imagery by machine learning in shanghai |
topic | Soil organic matter estimation Shanghai sentinel-2 indexes artificial neural network support vector machine |
url | https://ieeexplore.ieee.org/document/9432852/ |
work_keys_str_mv | AT xinxinwang estimatingsoilorganicmattercontentusingsentinel2imagerybymachinelearninginshanghai AT jiganghan estimatingsoilorganicmattercontentusingsentinel2imagerybymachinelearninginshanghai AT xiawang estimatingsoilorganicmattercontentusingsentinel2imagerybymachinelearninginshanghai AT huaiyingyao estimatingsoilorganicmattercontentusingsentinel2imagerybymachinelearninginshanghai AT langzhang estimatingsoilorganicmattercontentusingsentinel2imagerybymachinelearninginshanghai |