A Method for Predicting Alfalfa Biomass Based on Multimodal Data and Ensemble Learning Model
Plants · 06.03.2026 · 15 (5) · 815
DOI: 10.3390/plants15050815 ↗Kurz gefasst
Fachartikel in der Zeitschrift Plants, online erschienen am 06.03.2026. Verfasst von Yuehua Zhang und 13 weiteren Autor:innen. Beteiligte Einrichtung: College of Grassland Science, Inner Mongolia Agricultural University, Hohhot 010018, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: major demonstration project “The Open Competition” for Seed Industry Science and Technology Innovation in Inner Mongolia.
Abstract (Originalsprache)
Accurate alfalfa biomass prediction is crucial for pasture management and sustainable livestock production. However, traditional methods often perform poorly under complex field conditions. To address the limited prediction accuracy of traditional methods under complex planting environments, this study proposes an alfalfa biomass prediction method combining multispectral and LiDAR data with ensemble learning model. Based on the multispectral images acquired by unmanned aerial vehicle (UAV) and airborne LiDAR data, the spectral features, three-dimensional structural features, and their interaction features are systematically extracted at the quadrat scale, and a high-quality modeling dataset is constructed by feature selection. Secondly, an ensemble model for alfalfa biomass prediction was constructed, which was composed of random forest, extra trees, and histogram gradient boosting. After model training, the coefficient of determination (R2) of the integrated model on the test set reached 0.813, and the root mean square error (RMSE) and mean absolute error (MAE) were 0.178 kg m−2 and 0.146 kg m−2, which were significantly better than those of similar single models. Under feature combinations, the fusion model was better than that of spectral indices only (R2 = 0.773) and LiDAR traits only (R2 = 0.576), and the model achieved the highest accuracy from bud emergence to early flowering (R2 = 0.917). The overall prediction error of the model was approximately normal distribution, and the absolute error of more than 65% of the samples was less than 0.2. However, there was still a trend of underestimation in the high biomass interval. This research showed that the multimodal data fusion and ensemble learning method could achieve high-precision prediction of alfalfa biomass, which provided reliable technical support for pasture resources monitoring and precision agriculture management.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Grassland Science, Inner Mongolia Agricultural University, Hohhot 010018, China.
- Technology R&D Center, M-Grass Ecology and Environment (Group) Co., Ltd., Hohhot 010010, China.
- Key Laboratory of Cultivated Land Capability Conservation and Improvement in Agro-Pastoral Ecotone Ministry of Agriculture and Rural Affairs of the People's Republic of China, Hohhot 010010, China.
- College of Agriculture, Nanjing Agricultural University, Nanjing 210095, China.
- Inner Mongolia Grass Digital Agricultural Ecology Co., Ltd., Hohhot 010010, China.
Förderung
- major demonstration project “The Open Competition” for Seed Industry Science and Technology Innovation in Inner Mongolia
Zitieren
APA
Zhang, Y., Wang, Z., Tian, Z., Deng, H., Gao, J., Chen, C., Zhao, W., Ma, X., Ding, X., Yan, H., Yang, L., Xie, H., Li, Q., & Shi, F. (2026). A Method for Predicting Alfalfa Biomass Based on Multimodal Data and Ensemble Learning Model. Plants, 15(5), 815. https://doi.org/10.3390/plants15050815
Vancouver
Zhang Y, Wang Z, Tian Z, Deng H, Gao J, Chen C, et al. A Method for Predicting Alfalfa Biomass Based on Multimodal Data and Ensemble Learning Model. Plants. 2026;15(5):815. doi:10.3390/plants15050815
BibTeX
@article{Zhang2026,
author = {Zhang, Yuehua and Wang, Zhaoming and Tian, Zhendong and Deng, Haotian and Gao, Jungang and Chen, Chen and Zhao, Wei and Ma, Xiaoping and Ding, Xueqin and Yan, Haoran and Yang, Liu and Xie, Hui and Li, Qing and Shi, Fengling},
title = {A Method for Predicting Alfalfa Biomass Based on Multimodal Data and Ensemble Learning Model},
journal = {Plants},
year = {2026},
volume = {15},
number = {5},
pages = {815},
doi = {10.3390/plants15050815}
}
EUVIMED