[1]鲁金金 余 玲 李 宁 何 文 谢少少 黄 玲.广西喀斯特区典型植被叶片叶绿素含量高光谱反演研究[J].大众科技,2023,25(1):31-34.
 Study on Hyperspectral Inversion of Chlorophyll Content in Leaves of Typical Vegetation in Karst Area of Guangxi[J].Popular Science & Technology,2023,25(1):31-34.
点击复制

广西喀斯特区典型植被叶片叶绿素含量 高光谱反演研究()
分享到:

《大众科技》[ISSN:1008-1151/CN:45-1235/N]

卷:
25
期数:
2023年1
页码:
31-34
栏目:
资源与环境
出版日期:
2023-01-20

文章信息/Info

Title:
Study on Hyperspectral Inversion of Chlorophyll Content in Leaves of Typical Vegetation in Karst Area of Guangxi
作者:
鲁金金1 余 玲1 李 宁2 何 文3 谢少少1 黄 玲1 
(1.南宁理工学院,广西 桂林 541006;2.桂林航天工业学院,广西 桂林 541004; 3.广西喀斯特植物保育与恢复生态学重点实验室/广西壮族自治区中国科学院广西植物研究所,广西 桂林 541006)
关键词:
喀斯特植物叶绿素高光谱反演光谱指数PLSR-BP神经网络
Keywords:
Karst plant chlorophyll hyperspectral inversion spectral index PLSR-BP neural network
文献标志码:
A
摘要:
研究基于光谱指数法和偏最小二乘回归-BP神经网络模型(PLSR-BP)反演广西喀斯特区植被叶片叶绿素含量。结果表明:(1)基于光谱指数法建立的反演模型均难以达到理想的效果,模型的决定系数(R2)在0.04~0.25之间;(2)基于PLSR-BP神经网络模型反演喀斯特区植被叶片叶绿素含量精度较好,训练样本的R2均高于0.80,验证样本的R2为0.38~0.77,其中基于二阶导数光谱所建立的PLSR-BP神经网络模型精度最高,训练样本和验证样本的R2分别为0.89和0.77。研究结果可为喀斯特区植被生长监测和管理提供科学依据。
Abstract:
This study is based on spectral index method and partial least squares regression BP neural network model (PLSR-BP) to retrieve the chlorophyll content of vegetation leaves in karst areas of Guangxi. The results show that: (1) the inversion models based on spectral index method are difficult to achieve ideal results, and the determination coefficient (R2) of the models is between 0.04~0.25 (2) The PLSR-BP neural network model has a good accuracy in retrieving the chlorophyll content of vegetation leaves in karst areas. The R2 of training samples is higher than 0.80, and the R2 of validation samples is 0.38~0.77. The PLSR-BP neural network model based on the second derivative spectrum has the highest accuracy. The R2 of training samples and validation samples is 0.89 and 0.77 respectively. The results can provide scientific basis for monitoring and management of vegetation growth in karst areas.

参考文献/References:

[1] 李粉玲,常庆瑞. 基于连续统去除法的冬小麦叶片全氮含量估算[J]. 农业机械学报,2017,48(7): 174-179. [2] 何桂芳,吴见,彭建,等. 基于高光谱的石楠叶片叶绿素含量估算模型[J]. 西北林学院学报,2022,37(1): 25-32. [3] SONOBE R,WANG Q. Towards a universal hyperspectral index to assess chlorophyll content in deciduous forests[J]. Remote Sensing, 2017, 9(3): 191. [4] QI H, ZHU BY, KONG L G, et al. Hyperspectral inversion model of chlorophyll content in peanut leaves[J]. Applied Sciences, 2020, 10(7): 2259. [5] 王冰,何金有,张鹏杰,等. 基于高光谱的内蒙古大兴安岭白桦叶片叶绿素含量估算[J]. 西部林业科学,2022,51(4): 11-18. [6] 温云梦,张冬冬,王家强,等. 不同地下水埋深区域胡杨叶片叶绿素含量的光谱估测研究[J]. 西部林业科学,2022,51(4): 87-95. [7] 李颖. 干旱胁迫对不同土壤类型中南天竹(Nandina domestica)渗透调节物质的影响[J]. 重庆: 西南大学,2006. [8] 李合生. 植物生理生化试验原理与技术[M]. 北京: 高等教育出版社,2000. [9] PANAGOU E Z, MOHAREB F R, ARGYRI A A, et al. A comparison of artificial neural networks and partial least squares modelling for the rapid detection of the microbial spoilage of beef fillets based on Fourier transform infrared spectral fingerprints[J]. Food Microbiology, 2011, 28(4): 782-790. [10] 郭云开,刘宁,刘磊,等. 土壤Cu含量高光谱反演的BP神经网络模型[J]. 测绘科学,2018,43(1): 135-139. [11] 王凯龙,熊黑钢,张芳. 基于PLSR-BP复合模型的绿洲土壤pH高光谱反演[J]. 干旱区研究,2014,31(6): 1005-1009. [12] HE W, LI Y Q, WANG J Y, et al. Using field spectroradiometer to estimate the leaf N/P ratio of mixed forest in a Karst area of southern China: a combined model to overcome overfitting[J]. Remote Sensing, 2021, 13(17): 3368.

相似文献/References:

[1]方贵彪.浅谈喀斯特地貌尾矿库施工阶段质量控制的监理工作要点[J].大众科技,2020,22(04):16.
 Discussion on the Key Points of Supervision of Quality Controlin the Construction Stage of Karst Landform Tailings Reservoir[J].Popular Science & Technology,2020,22(1):16.

备注/Memo

备注/Memo:
【收稿日期】2022-10-28 【基金项目】广西高校中青年教师科研基础能力提升项目(2020KY58008);广西科学院基本科研业务费(2019YJJ1009);广西自然科学基金(2019GXNSFBA245036)。 【作者简介】鲁金金(1983-),女,南宁理工学院副教授,硕士,研究方向为地理信息数据采集及处理。 【通信作者】余玲,女,南宁理工学院讲师,博士,研究方向为生态遥感。
更新日期/Last Update: 2023-03-30