您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

CatBoost algorithm for estimating maize above-ground biomass using unmanned aerial vehicle-based multi-source sensor data and SPAD values

文献类型： 外文期刊

作者： Zhai, Weiguang 1 ; Li, Changchun 2 ; Fei, Shuaipeng 3 ; Liu, Yanghua 4 ; Ding, Fan 1 ; Cheng, Qian 1 ; Chen, Zhen 1 ;

作者机构： 1.Chinese Acad Agr Sci, Inst Farmland Irrigat, Xinxiang 453002, Peoples R China

2.Henan Polytech Univ, Sch Surveying & Land Informat Engn, Jiaozuo 454003, Peoples R China

3.China Agr Univ, Coll Land Sci & Technol, Beijing 100193, Peoples R China

4.Piesat Informat Technol Co Ltd, Beijing 100095, Peoples R China

关键词： Above-ground biomass; Maize; Unmanned aerial vehicle; SPAD values; CatBoost

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.3； 五年影响因子：8.3 ）

ISSN： 0168-1699

年卷期： 2023 年 214 卷

页码：

收录情况： SCI

摘要： The rapid and accurate estimation of maize above-ground biomass (AGB) is pivotal for precise agricultural management. The rapid evolution of unmanned aerial vehicles (UAVs) and sensor technology has introduced a novel method for obtaining AGB information. Nevertheless, individual sensors may lack comprehensive data, leading to reduced AGB estimation accuracy in certain scenarios. This study collected UAV multi-spectral (MS) and thermal infrared (TIR) data, alongside soil and plant analyzer development (SPAD) values, from maize across multiple growth stages (jointing, trumpet, and big trumpet) during 2022 and 2023. Diverse data fusion programs were devised to explore the potential of combining multi-source sensor data with SPAD values to estimate AGB. The efficacy of CatBoost was evaluated and benchmarked against Support Vector Regression (SVR) and Random Forest Regression (RFR) algorithms. For the entire growth, findings reveal that the fusion of multi-source sensor data (MS + TIR) can mitigate the data insufficiency in single-sensor estimations. The resulting R2 values range from 0.608 to 0.817. Optimal estimation outcomes were achieved by the fusion of multi-source sensor data with SPAD values (MS + TIR + SPAD), yielding R2 values ranging from 0.685 to 0.872. For a single growth stage, there are variations in the estimation accuracy across different growth stages. From the jointing stage to the big trumpet stage, the estimation accuracy consistently increases, with the highest accuracy observed during the big trumpet stage, with R2 ranging from 0.721 to 0.901. Additionally, in alignment with the results for the entire growth stage, the fusion of multi-source sensor data with SPAD values still yields the highest estimation accuracy during different growth stages. In a comparison of different machine learning algorithms, for both the entire growth stage and single growth stages, SVR, RFR, and CatBoost achieved R2 values ranging from 0.305 to 0.824, 0.368 to 0.881, and 0.451 to 0.901, respectively. Notably, the CatBoost algorithm exhibited heightened esti-mation accuracy. The fusion of multi-source sensor data with SPAD values combined with the CatBoost algorithm results in accurate and reliable maize AGB estimation accuracy. This high-throughput approach to crop phe-notyping is characterized by speed and accuracy and serves as a valuable reference for rapidly acquiring AGB information in this geographical region.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台