Estimating soil moisture over winter wheat fields during growing season using machine-learning methods
Estimating soil moisture over winter wheat fields during growing season using machine-learning methods
Simple item page
Full item details
- creativework.keywords - en
- Soil moisture--Measurement
- Crop yields
- Crops--Growth
- Machine learning
- Polarimetric remote sensing
- Synthetic aperture radar
- creativework.keywords - fr
- Sols--Humidité--Mesure
- Cultures--Rendement
- Cultures--Croissance
- Apprentissage automatique
- Télédétection polarimétrique
- Radar à synthèse d'ouverture
- dc.contributor.author
- Chen, Lin
- Xing, Minfeng
- He, Binbin
- Wang, Jinfei
- Shang, Jiali
- Huang, Xiaodong
- Xu, Min
- dc.date.accepted
- 2021-03-12
- dc.date.accessioned
- 2025-01-13T13:53:47Z
- dc.date.available
- 2025-01-13T13:53:47Z
- dc.date.issued
- 2021-03-23
- dc.date.submitted
- 2020-12-31
- dc.description.abstract - en
- Soil moisture is vital for the crop growth and directly affects the crop yield. The conventional synthetic aperture radar (SAR) based soil moisture monitoring is often influenced by vegetation cover and surface roughness. The machine-learning methods are not constrained by physical parameters and have high nonlinear fitting capabilities. In this study, machine-learning methods were applied to estimate soil moisture over winter wheat fields during its growing season. RADARSAT-2 data with quad polarizations and 240 sample plots in the study area were acquired and collected, respectively. In addition to the four linear polarization channels, polarimetric decomposition parameters were extracted to expand the SAR feature space. Three advanced machine-learning models were selected and compared, which were support vector regression, random forests (RF), and gradient boosting regression tree. To improve the performances of the models, three feature-selection methods were compared, which were based on Pearson correlation, support vector machine recursive feature elimination, and RF, respectively. The coefficient of determination (R2) and root-mean-square error (RMSE) were used to compare and assess the performances of those models. The results revealed that polarimetric decomposition parameters were effective in estimating soil moisture, and RF model obtained the highest prediction accuracy (training set: RMSE = 2.44 vol.% and R2 = 0.94; and validation set: RMSE = 4.03 vol.%, and R2 = 0.79). This study finally concluded that using polarimetric decomposition parameters combined with machine-learning and feature-selection methods could effectively estimate soil moisture at a high accuracy, which helps monitor soil moisture across the agricultural field during its growing season.
- dc.identifier.citation
- Chen, L., Xing, M., He, B., Wang, J., Shang, J., Huang, X., & Xu, M. (2021). Estimating soil moisture over winter wheat fields during growing season using machine-learning methods. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 3706-3718, Article 9384159. https://doi,org/10.1109/JSTARS.2021.3067890
- dc.identifier.doi
- https://doi.org/10.1109/JSTARS.2021.3067890
- dc.identifier.issn
- 1939-1404
- 2151-1535
- dc.identifier.uri
- https://open-science.canada.ca/handle/123456789/3307
- dc.language.iso
- en
- dc.publisher - en
- Institute of Electrical and Electronics Engineers Inc.
- dc.rights - en
- Creative Commons Attribution 4.0 International (CC BY 4.0)
- dc.rights - fr
- Creative Commons Attribution 4.0 International (CC BY 4.0)
- dc.rights.openaccesslevel - en
- Gold
- dc.rights.openaccesslevel - fr
- Or
- dc.rights.uri - en
- https://creativecommons.org/licenses/by/4.0/
- dc.rights.uri - fr
- https://creativecommons.org/licenses/by/4.0/deed.fr
- dc.subject - en
- Soil quality
- Crops
- Radar
- Remote sensing
- dc.subject - fr
- Qualité des sols
- Cultures
- Radar
- Télédétection
- dc.subject.en - en
- Soil quality
- Crops
- Radar
- Remote sensing
- dc.subject.fr - fr
- Qualité des sols
- Cultures
- Radar
- Télédétection
- dc.title - en
- Estimating soil moisture over winter wheat fields during growing season using machine-learning methods
- dc.type - en
- Article
- dc.type - fr
- Article
- local.acceptedmanuscript.articlenum
- 9384159
- local.article.journaltitle - en
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- local.article.journalvolume
- 14
- local.pagination
- 3706-3718
- local.peerreview - en
- Yes
- local.peerreview - fr
- Oui
- local.requestdoi
- No
Download(s)
Original bundle
1 - 1 of 1
Name: EstimatingSoilMoistureOverWinterWheatFieldsDuringGrowingSeasonUsingMachineLearningMethods_2021.pdf
Size: 3.6 MB
Format: PDF
Collection(s)