Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/94279
PIRA download icon_1.1View/Download Full Text
Title: Automated soybean mapping based on canopy water content and chlorophyll content using Sentinel-2 images
Authors: Huang, Y
Qiu, B
Chen, C
Zhu, X 
Wu, W
Jiang, F
Lin, D
Peng, Y
Issue Date: May-2022
Source: International journal of applied earth observation and geoinformation, May 2022, v. 109, 102801
Abstract: Accurate and timely spatiotemporal distribution information of soybean is vital for sustainable agriculture development. However, it is challenging to establish a phenology-based automated crops mapping algorithm at large spatial domains by simply applying vegetation index temporal profile. This study developed a Phenology-based automatic Soybean mapping algorithm through combined Canopy water and Chlorophyll variations (PSCC). Three phenology-based indices were designed: the ratio of change magnitudes of vegetation index to water stress index during the late growth stage (T1), the mean concentration of chlorophyll during the whole growth period (T2), and the accumulated variations of chlorophyll before and after heading date (T3). Soybean was distinguished by lower T1 and T3 and higher T1 due to higher senescence water loss and chlorophyll content. The PSCC method was validated in Northeast China from 2017 to 2021 and in four states (Missouri, Illinois, Indiana, and Ohio) of the United States (US) in 2020 using Sentinel-2 datasets. Soybean planting areas obtained by PSCC were consistent with the corresponding agricultural statistical area (R2 > 0.83). The soybean maps were evaluated using 5702 reference data, and the overall accuracy and kappa coefficient were 91.99% and 0.8338, respectively. The overall accuracy for soybean mapping was improved by 16.07% compared with using only canopy water variation. The result showed that our method could be applied to large spatial domains and multi-years without retraining. The soybean planting area in Northeast China expanded substantially 25,867 km2 (by 89.10%) during the period 2015–2020 and decreased slightly 7,535 km2 (by 13.73%) from 2020 to 2021. Soybean expansion occurred mainly in ever-planted regions. Northeast China contributed about 60% to the national soybean revitalization goal in 2020. This study provided information on the soybean spatiotemporal changes in Northeast China, which was significant for agricultural policymakers to formulate soybean production plans to achieve national soybean revitalization.
Keywords: Phenology-based algorithm
Soybean
Sentinel-2
Time-series analysis
Spatiotemporal changes
Publisher: Elsevier
Journal: International journal of applied earth observation and geoinformation 
ISSN: 1569-8432
EISSN: 1872-826X
DOI: 10.1016/j.jag.2022.102801
Rights: © 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
The following publication Huang, Y., Qiu, B., Chen, C., Zhu, X., Wu, W., Jiang, F., ... & Peng, Y. (2022). Automated soybean mapping based on canopy water content and chlorophyll content using Sentinel-2 images. International Journal of Applied Earth Observation and Geoinformation, 109, 102801 is available at https://doi.org/10.1016/j.jag.2022.102801
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
1-s2.0-S1569843222000036-main.pdf12.22 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Version of Record
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page views

60
Last Week
1
Last month
Citations as of May 5, 2024

Downloads

55
Citations as of May 5, 2024

SCOPUSTM   
Citations

14
Citations as of Apr 26, 2024

WEB OF SCIENCETM
Citations

13
Citations as of May 2, 2024

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.