Enhanced Estimation of Rice Leaf Nitrogen Content via the Integration of Hybrid Preferred Features and Deep Learning Methodologies
文献类型： 外文期刊
作者： Peng, Yiping 1 ; Zhong, Wenliang 1 ; Peng, Zhiping 1 ; Tu, Yuting 1 ; Xu, Yanggui 1 ; Li, Zhuxian 1 ; Liang, Jianyi 1 ; Huang, Jichuan 1 ; Liu, Xu 4 ; Fu, Youqiang 5 ;
作者机构： 1.Guangdong Acad Agr Sci, Inst Agr Resources & Environm, Guangzhou 510640, Peoples R China
2.Minist Agr, Key Lab Plant Nutr & Fertilizer South Reg, Guangzhou 510640, Peoples R China
3.Guangdong Key Lab Nutrient Cycling & Farmland Cons, Guangzhou 510640, Peoples R China
4.Guangdong Acad Agr Sci, Inst Agr Econ & Informat, Guangzhou 510640, Peoples R China
5.Guangdong Acad Agr Sci, Rice Res Inst, Guangzhou 510640, Peoples R China
关键词： UAV hyperspectral; leaf nitrogen content (LNC); feature optimization; deep learning
期刊名称：AGRONOMY-BASEL （ 影响因子：3.3； 五年影响因子：3.7 ）
ISSN：
年卷期： 2024 年 14 卷 6 期
页码：
收录情况： SCI
摘要： Efficiently obtaining leaf nitrogen content (LNC) in rice to monitor the nutritional health status is crucial in achieving precision fertilization on demand. Unmanned aerial vehicle (UAV)-based hyperspectral technology is an important tool for determining LNC. However, the intricate coupling between spectral information and nitrogen remains elusive. To address this, this study proposed an estimation method for LNC that integrates hybrid preferred features with deep learning modeling algorithms based on UAV hyperspectral imagery. The proposed approach leverages XGBoost, Pearson correlation coefficient (PCC), and a synergistic combination of both to identify the characteristic variables for LNC estimation. We then construct estimation models of LNC using statistical regression methods (partial least-squares regression (PLSR)) and machine learning algorithms (random forest (RF); deep neural networks (DNN)). The optimal model is utilized to map the spatial distribution of LNC at the field scale. The study was conducted at the National Agricultural Science and Technology Park, Guangzhou, located in Baiyun District of Guangdong, China. The results reveal that the combined PCC-XGBoost algorithm significantly enhances the accuracy of rice nitrogen inversion compared to the standalone screening approach. Notably, the model built with the DNN algorithm exhibits the highest predictive performance and demonstrates great potential in mapping the spatial distribution of LNC. This indicates the potential role of the proposed model in precision fertilization and the enhancement of nitrogen utilization efficiency in rice cultivation. The outcomes of this study offer a valuable reference for enhancing agricultural practices and sustainable crop management.
- 相关文献
作者其他论文 更多>>
-
Optimized nitrogen management improves grain yield of rice by regulating panicle architecture in South China
作者：Hu, Xiangyu;Liu, Yanzhuo;Zhong, Xuhua;Hu, Rui;Li, Meijuan;Peng, Bilin;Pan, Junfeng;Liang, Kaiming;Fu, Youqiang;Huang, Nongrong
关键词：Optimized nitrogen management; Panicle architecture; Rachis branch and floret; Differentiation; Degeneration
-
Arbuscular Mycorrhizal Fungi Mediate the Acclimation of Rice to Submergence
作者：Xu, Yanggui;Tu, Yuting;Peng, Zhiping;Peng, Yiping;Huang, Jichuan;Xu, Yanggui;Tu, Yuting;Peng, Zhiping;Peng, Yiping;Huang, Jichuan;Xu, Yanggui;Tu, Yuting;Peng, Zhiping;Peng, Yiping;Huang, Jichuan;Feng, Jiayi
关键词：carbohydrates; lipids; fungal perception; root morphological traits; flooding stress; submergence-related genes
-
Determining nitrogen topdressing rates in accordance with actual seedling density and crop nitrogen status in direct-seeded rice
作者：Peng, Bilin;Wang, Xinyu;Hu, Xiangyu;Liu, Yanzhuo;Liang, Kaiming;Fu, Youqiang;Hu, Rui;Li, Meijuan;Ye, Qunhuan;Yin, Yuanhong;Pan, Junfeng;Zhong, Xuhua;Peng, Bilin;Wang, Xinyu;Hu, Xiangyu;Liu, Yanzhuo;Liang, Kaiming;Fu, Youqiang;Hu, Rui;Li, Meijuan;Ye, Qunhuan;Yin, Yuanhong;Pan, Junfeng;Zhong, Xuhua
关键词：direct-seeded rice; maximum tiller number; nitrogen management; plant nitrogen status; actual seedling density
-
Evaluating Rice Varieties for Suitability in a Rice-Fish Co-Culture System Based on Lodging Resistance and Grain Yield
作者：Li, Meijuan;Hu, Xiangyu;Hu, Rui;Liang, Kaiming;Zhong, Xuhua;Pan, Junfeng;Fu, Youqiang;Liu, Yanzhuo;Wang, Xinyu;Ye, Qunhuan;Yin, Yuanhong
关键词：rice-fish co-culture system; rice varieties; lodging resistance; grain yield; paddy field screening
-
Mitigation of environmental N pollution and greenhouse gas emission from double rice cropping system with a new alternate wetting and drying irrigation regime coupled with optimized N fertilization in South China
作者：Liang, Kaiming;Zhong, Xuhua;Fu, Youqiang;Hu, Xiangyu;Li, Meijuan;Pan, Junfeng;Liu, Yanzhuo;Hu, Rui;Ye, Qunhuan
关键词：Nitrogen loss; Greenhouse gas emissions; Water saving irrigation; Water productivity; South China
-
Improving grain yield and nitrogen use efficiency of direct-seeded rice with simplified and nitrogen-reduced practices under a double-cropping system in South China
作者：Fu, Youqiang;Huang, Nongrong;Zhong, Xuhua;Liu, Yanzhuo;Liang, Kaiming;Pan, Junfeng;Hu, Xiangyu;Hu, Rui;Li, Meijuan;Ye, Qunhuan;Zhong, Xuhua;Liang, Kaiming;Mai, Guoxun;Pan, Huarong;Xu, Haoqi;Xiao, Jie
关键词：grain yield; nitrogen use efficiency; simplified and nitrogen-reduced practice; direct-seeded rice
-
Combining organic and inorganic fertilization increases rice yield and soil nitrogen and carbon: dissolved organic matter chemodiversity and soil microbial communities
作者：Xu, Yanggui;Peng, Zhiping;Tu, Yuting;Huang, Jichuan;Xu, Yanggui;Peng, Zhiping;Tu, Yuting;Huang, Jichuan;Xu, Yanggui;Peng, Zhiping;Tu, Yuting;Huang, Jichuan
关键词：Paddy field; Fertilization treatment; Dissolved organic matter composition; Bacterial communities; Net nitrogen mineralization; Yield
