Evaluation of Machine Learning Models for Estimating Grassland Pasture Yield Using Landsat-8 Imagery
Agronomy · 14.12.2024 · 14 (12) · 2984
DOI: 10.3390/agronomy14122984 ↗Kurz gefasst
Fachartikel in der Zeitschrift Agronomy, online erschienen am 14.12.2024. Verfasst von Linming Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Second Tibetan Plateau Scientific Expedition and Research Project.
Abstract (Originalsprache)
Accurate estimation of pasture yield in grasslands is crucial for the sustainable utilization of pasture resources and the optimization of grassland management. This study leveraged the capabilities of machine learning techniques, supported by Google Earth Engine (GEE), to assess pasture yield in the temperate grasslands of northern China. Utilizing Landsat-8 data, band reflectances, vegetation indexes (VIs), and soil water index (SWI) were extracted from 1000 field samples across Xilingol. These data, combined with field-measured pasture yields, were employed to construct models using four machine learning algorithms: elastic net regression (Enet), Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM). Among the models, XGBoost demonstrated the best performance for pasture yield estimation, with a coefficient of determination (R2) of 0.94 and a precision of 76.3%. Additionally, models that incorporated multiple VIs demonstrated superior prediction accuracy compared to those using individual VI, and including soil moisture data further enhanced predictive precision. The XGBoost model was subsequently applied to map the spatial patterns of pasture yield in the Xilingol grassland for the years 2014 and 2019. The estimated average annual pasture yield in the Xilingol grassland was 1042.38 and 1013.49 kg/ha in 2014 and 2019, respectively, showing a general decreasing trend from the northeast to the southwest. This study explored the effectiveness of common machine learning algorithms in predicting pasture yield of temperate grasslands utilizing Landsat-8 data and ground sample data and provided the valuable support for long-term historical monitoring of pasture resources. The findings also highlighted the importance of predictor selection in optimizing model performance, except for the reflectance and vegetation indices characterizing vegetation canopy information, the inclusion of soil moisture information could appropriately improve the accuracy of model predictions, especially for grasslands with relatively low vegetation cover.
Förderung
- National Key Research and Development Program of China
- National Natural Science Foundation of China
- Second Tibetan Plateau Scientific Expedition and Research Project
- Central Public-interest Scientific Institution Basal Research Fund
Zitieren
APA
Huang, L., Zhao, F., Hu, G., Ganjurjav, H., Wu, R., & Gao, Q. (2024). Evaluation of Machine Learning Models for Estimating Grassland Pasture Yield Using Landsat-8 Imagery. Agronomy, 14(12), 2984. https://doi.org/10.3390/agronomy14122984
Vancouver
Huang L, Zhao F, Hu G, Ganjurjav H, Wu R, Gao Q. Evaluation of Machine Learning Models for Estimating Grassland Pasture Yield Using Landsat-8 Imagery. Agronomy. 2024;14(12):2984. doi:10.3390/agronomy14122984
BibTeX
@article{Huang2024,
author = {Huang, Linming and Zhao, Fen and Hu, Guozheng and Ganjurjav, Hasbagan and Wu, Rihan and Gao, Qingzhu},
title = {Evaluation of Machine Learning Models for Estimating Grassland Pasture Yield Using Landsat-8 Imagery},
journal = {Agronomy},
year = {2024},
volume = {14},
number = {12},
pages = {2984},
doi = {10.3390/agronomy14122984}
}
EUVIMED