English

智能化农业装备学报(中英文) ›› 2024, Vol. 5 ›› Issue (3): 14-21.DOI: 10.12398/j.issn.2096-7217.2024.03.002

• • 上一篇    下一篇

基于BWO-ELM的水稻氮素无人机高光谱反演研究

李世隆1,2(), 许辰一1,2, 王楠1,2, 曹慧妮1,2, 于丰华1,2,3()   

  1. 1.沈阳农业大学信息与电气工程学院,辽宁 沈阳,110866
    2.国家数字农业区域创新分中心(东北),辽宁 沈阳,110866
    3.辽宁省智慧农业技术重点实验室,辽宁 沈阳,110866
  • 收稿日期:2024-05-15 修回日期:2024-07-20 出版日期:2024-08-15 发布日期:2024-08-15
  • 通讯作者: 于丰华
  • 作者简介:李世隆,男,2000年生,山东平度人,硕士研究生;研究方向为精准农业航空。E-mail: lishilong0725@163.com
  • 基金资助:
    国家自然科学基金青年项目(32201652);辽宁省自然科学基金面上项目(2023-MSLH-283);辽宁省“兴辽英才计划”项目(XLYC2203005)

Research on rice nitrogen unmanned aerial vehicle hyperspectral inversion based on BWO-ELM

LI Shilong1,2(), XU Chenyi1,2, WANG Nan1,2, CAO Huini1,2, YU Fenghua1,2,3()   

  1. 1.College of Information and Electrical Engineering,Shenyang Agricultural University,Shenyang 110866,China
    2.National Digital Agriculture Sub-center of Innovation (Northeast Region),Shenyang 110866,China
    3.Key Laboratory of Intelligent Agriculture in Liaoning Province,Shenyang 110866,China
  • Received:2024-05-15 Revised:2024-07-20 Online:2024-08-15 Published:2024-08-15
  • Contact: YU Fenghua

摘要:

氮素是水稻生长发育的重要元素之一,精准估测氮素浓度对指导水稻精准施肥、辅助氮高效品种选育是十分重要的。传统田间采样方式难以实时获取水稻氮素浓度,随着信息技术的快速发展,目前通过机器学习方法建立无人机高光谱数据与氮素浓度的关系,是作物氮素营养诊断的主要技术路线之一。研究以连续投影算法筛选的无人机冠层高光谱数据特征波段为输入,实测氮素浓度数据为输出构建反演模型。极限学习机(ELM)与同类型的机器学习方法相比,具有速度快、泛化能力强的优势,但由于其随机生成的连接权重和神经元阈值,导致其训练稳定性存在不足,且容易陷入局部最优解。白鲸优化算法(BWO)是一种以白鲸行为为灵感而设计的求解单模态和多模态优化问题的竞争算法,本研究通过白鲸优化算法对极限学习机的输入层与隐含层之间的连接权重、隐含层初始权重进行优化,构建BWO-ELM水稻氮素浓度无人机高光谱反演模型,实现对水稻氮素浓度的快速估测。研究结果表明:连续投影算法筛选出特征波段10个,分别为673、703、727、823、850、877、895、952、961和985 nm。基于BWO-ELM构建的氮素浓度反演模型训练集R2RMSE分别为0.742 5、0.382 6%,测试集R2RMSE分别为0.702 8、0.487 7%。预测能力优于基于ELM构建的氮素浓度反演模型。综上所述,基于BWO-ELM的水稻氮素浓度无人机高光谱反演模型可以快速准确获取水稻氮素浓度,为水稻营养监测提供新的方法。

关键词: 白鲸优化算法, 极限学习机, 氮素, 无人机, 高光谱, 水稻

Abstract:

Nitrogen is one of the important elements for the growth and development of rice, and accurate estimation of nitrogen concentration is crucial for guiding precise fertilization and assisting in the selection of nitrogen efficient varieties in rice. Traditional field sampling methods make it difficult to obtain real-time nitrogen concentration in rice. With the rapid development of information technology, establishing the relationship between unmanned aerial vehicle hyperspectral data and nitrogen concentration through machine learning methods is currently one of the main technical routes for crop nitrogen nutrition diagnosis. This study constructs an inversion model by using the feature bands of unmanned aerial vehicle canopy hyperspectral data selected by the continuous projection algorithm as input and the measured nitrogen concentration data as output. Extreme learning machine (ELM) has the advantages of fast speed and strong generalization ability compared to similar machine learning methods. However, due to its randomly generated connection weights and neuron thresholds, its training stability is insufficient and it is prone to falling into local optima. The beluga whale optimization (BWO) is a competitive algorithm inspired the behavior of beluga whales to solve single modal and multimodal optimization problems. In this study, the BWO-ELM rice nitrogen concentration unmanned aerial vehicle hyperspectral inversion model was constructed to achieve rapid estimation of rice nitrogen concentration by optimizing the connection weight between the input layer and the hidden layer of the ELM, as well as the initial weight of the hidden layer through the BWO. The research results show that the continuous projection algorithm filters out 10 feature bands, which are 673, 703, 727, 823, 850, 877, 895, 952, 961, and 985 nm, respectively. The training set R2 and RMSE of the nitrogen concentration inversion model constructed based on BWO-ELM are 0.742 5 and 0.382 6%, respectively, while the testing set R2 and RMSE are 0.702 8 and 0.487 7%, respectively. The predictive ability is superior to that of the nitrogen concentration inversion model constructed based on ELM. In summary, the rice nitrogen concentration unmanned aerial vehicle hyperspectral inversion model based on BWO-ELM can quickly and accurately obtain rice nitrogen concentration, providing a new method for rice nutrition monitoring.

Key words: beluga whale optimization, extreme learning machine, nitrogen, unmanned aerial vehicle, hyperspectral, rice

中图分类号: