数字农科院2.0

The research on enhancing LA estimation accuracy across domains for small sample data based on data augmentation and data transfer integration optimization system

文献类型： 外文期刊

作者： Ai Dong Wang;Rui Jie Li;Xiang Qian Feng;Zi Qiu Li;Wei Yuan Hong;Hua Xing Wu;Dan Ying Wang;Song Chen

作者机构：

关键词： Data augmentation;Integrated optimization;Leaf area estimation;Machine learning;Small sample data;Transfer learning

期刊名称： Smart Agricultural Technology

ISSN： 2772-3755

年卷期： 2025 年 12 卷

页码：

收录情况： ESCI（2025版）

摘要： Context: The efficient and precise monitoring of rice leaf area (LA) is essential for variety selection and agricultural management. At present, LA estimation models based on high-throughput phenotyping technologies primarily depend on homogenized large sample datasets. These models encounter generalization challenges when applied to heterogeneous scenarios with small sample sizes. Objective: In this research, our goal is to develop a novel framework to mitigate prediction biases in LA caused by sample limitations and data heterogeneity. This framework integrates machine learning models to establish a universal solution for cross-domain LA estimation in data-scarce situations. Methods: This research utilizes canopy image data acquired from the 2023–2024 rice full-cycle multi-view RGB imaging system (with dual front and side camera positions). Fourteen morphological feature parameters are constructed, and the leaf area values are measured through destructive sampling, together forming the dataset. A comprehensive comparison of six algorithms (linear regression, support vector regression, random forest, XGBoost, CatBoost, and K-nearest neighbors) is conducted, assessing their performance under a combined strategy of data augmentation (noise injection, generative adversarial networks, Gaussian mixture model, variational autoencoders) and transfer learning (random, clustering, and hierarchical parameter transfer). Results and conclusions: The results demonstrate that the integrated optimization system (Gaussian Mixture Model Generation-Cluster-Based Transfer, GMM-CBT) achieved optimal performance when combined with XGBoost (validation R2=0.85, test R2=0.85), outperforming both standalone approaches: data augmentation (validation R2=0.87, test R2=-0.37) and transfer learning (validation R2=0.84, test R2=0.84). The framework clusters heterogeneous data based on morphological features (such as size, compactness, and roundness) and constructs a transfer sample library with feature coverage. Significance: The proposed methodology advances precision agriculture by enabling single-plant LA monitoring, with potential extensions to other crops and trait-phenotyping applications.

分类号：

  • 相关文献

[1]Enhancing leaf area index and biomass estimation in maize with feature augmentation from unmanned aerial vehicle-based nadir and cross-circling oblique photography. Shuaipeng Fei,Shunfu Xiao,Qing Li,Meiyan Shu,Weiguang Zhai,Yonggui Xiao,Zhen Chen,Helong Yu,Yuntao Ma. 2023

[2]Early detection of dark-affected plant mechanical responses using enhanced electrical signals. Hongping Li,Nikou Fotouhi,Fan Liu,Hongchao Ji,Qian Wu. 2024

[3]Review of GNSS-R Technology for Soil Moisture Inversion. Yang C.,Mao K.,Guo Z.,Shi J.,Bateni S.M.,Yuan Z.. 2024

[4]Improved random patches and model transfer for deriving leaf mass per area across multispecies from spectral reflectance. Shuaipeng Fei,Shunfu Xiao,Demin Xu,Meiyan Shu,Hong Sun,Puyu Feng,Yonggui Xiao,Yuntao Ma. 2024

[5]Semantic Segmentation Based on Temporal Features: Learning of Temporal-Spatial Information From Time-Series SAR Images for Paddy Rice Mapping. Yang, Lingbo,Huang, Ran,Huang, Jingfeng,Lin, Tao,Wang, Limin,Mijiti, Ruzemaimaiti,Wei, Pengliang,Tang, Chao,Shao, Jie,Li, Qiangzi,Du, Xin. 2021

[6]OVERSAMPLING METHOD FOR ENVIRONMENTAL MONITORING DATA AUGMENTATION IN CADMIUM -POLLUTED PADDY FIELD. Hao, Peitong,Li, Yue,Xu, Weiman,Li, Cong,Huo, Mingzhu,Zhang, Xiaoyu,An, Yi. 2022

[7]Predicting the reaction rates between flavonoids and methylglyoxal by combining molecular properties and machine learning. Hongkai Zhu,Jingyuan Liu,Mogens L. Andersen,Günther H.J. Peters,Marianne N. Lund. 2023

[8]High-quality images and data augmentation based on inverse projection transformation significantly improve the estimation accuracy of biomass and leaf area index. Yingpu Che,Qing Wang,Ziwen Xie,Shilin Li,Jinyu Zhu,Baoguo Li,Yuntao Ma. 2023

[9]Rep-ViG-Apple: A CNN-GCN Hybrid Model for Apple Detection in Complex Orchard Environments. Bo Han,Ziao Lu,Jingjing Zhang,Rolla Almodfer,Zhengting Wang,Wei Sun,Luan Dong. 2024

[10]Efficient Triple Attention and AttentionMix: A Novel Network for Fine-Grained Crop Disease Classification. Yanqi Zhang,Ning Zhang,Jingbo Zhu,Tan Sun,Xiujuan Chai,Wei Dong. 2025

[11]GAN-MAML strategy for biomass energy production: Overcoming small dataset limitations. Yi Zhang,Yanji Hao,Yu Fu,Yijing Feng,Yeqing Li,Xiaonan Wang,Junting Pan,Yongming Han,Chunming Xu. 2025

[12]Multi-Indicator Prediction of Kiwifruit Quality integrating Hyperspectral Analysis and WGAN-GP-MMoE Framework. 刘子涵,陈谦,李佳利,刘浩松,帅博宇,欧阳凌欢,卞子晗,王君怡,于家斌,钱建平. 2025

[13]Cotton Yield Prediction with Gaussian Distribution Sampling and Variational AutoEncoder. Yaqi Lan,Xiudong Wang,Lei Gao,Xiaoliang Chen. 2025

[14]Multi-Label Classification of Chinese Rural Poverty Governance Texts Based on XLNet and Bi-LSTM Fused Hierarchical Attention Mechanism. Xin Wang,Leifeng Guo. 2023

[15]Cotton disease identification method based on pruning. Zhu D.,Feng Q.,Zhang J.,Yang W.. 2022

[16]Identification method of vegetable diseases based on transfer learning and attention mechanism. Xue Zhao,Kaiyu Li,Yunxia Li,Juncheng Ma,Lingxian Zhang. 2022

[17]Attention-optimized DeepLab V3+for automatic estimation of cucumber disease severity. Li, Kaiyu,Zhang, Lingxian,Li, Bo,Li, Shufei,Ma, Juncheng. 2022

[18]ResNetKhib: a novel cell type-specific tool for predicting lysine 2-hydroxyisobutylation sites via transfer learning. Xiaoti Jia,Pei Zhao,Fuyi Li,Zhaohui Qin,Haoran Ren,Junzhou Li,Chunbo Miao,Quanzhi Zhao,Tatsuya Akutsu,Gensheng Dou,Zhen Chen,Jiangning Song. 2023

[19]Protein-protein interaction and site prediction using transfer learning. Tuoyu Liu,Han Gao,Xiaopu Ren,Guoshun Xu,Bo Liu,Ningfeng Wu,Huiying Luo,Yuan Wang,Tao Tu,Bin Yao,Feifei Guan,Yue Teng,Huoqing Huang,Jian Tian. 2023

[20]VGNet: A Lightweight Intelligent Learning Method for Corn Diseases Recognition. Xiangpeng Fan,Zhibin Guan. 2023

作者其他论文 更多>>