基于高光谱变换的枸杞冠层含水率预测模型

doi:10.13733/j.jcam.issn.2095‑5553.2024.11.026

摘要/Abstract

摘要： 为实现枸杞冠层水分信息的快速无损监测，以“宁杞7号”枸杞为试验对象，测定枸杞冠层叶片光谱和叶片含水率，对原始光谱进行一阶微分和连续统去除2种数学变换，将获取的原始光谱(OS)、一阶微分光谱(FDS)及连续统去除光谱(CRS)与含水率进行相关性分析，筛选出敏感波长并构建预测含水率的随机森林回归模型(RFRM)、偏最小二乘回归模型(PLSRM)、岭回归模型(RRM)及一元回归模型(URM)，最后对模型的精度进行检验与评价。结果表明：从敏感波长分析，基于FDS构建的模型，其拟合度为0.716~0.938；基于CRS构建的模型，其拟合度为0.710~0.920；基于OS构建的模型，其拟合度为0.710~0.874；可见，基于FDS和CRS构建的模型，拟合度均高于基于OS构建的模型。从模型类型分析，RFRM的拟合度最高(0.874~0.938)，其次为PLSRM(0.826~0.866)和RRM(0.737~0.889)，URM的拟合度最低(0.710~0.730)。综合分析，基于一阶微分光谱构建的随机森林回归模型(FDS+RFRM)预测效果最优，其训练集和测试集的拟合度分别为0.938和0.893，检验集[R2、RMSE、MAE及RPD]分别为0.872、0.561、0.466和2.156。研究将光谱变换与机器学习相结合，开发一套适用于枸杞冠层叶片含水率的且预测精度很高的高光谱探测模型，为枸杞冠层含水率的监测提供适宜高效的方法。

关键词: 含水率, 枸杞, 高光谱, 偏最小二乘回归模型, 随机森林回归模型, 岭回归模型

Abstract: In order to achieve rapid and nondestructive monitoring of leaf water content in the canopy of Lyceum barbarum tree, Ningqi No.7 was taken as the research object to measure the spectra and water content of Lyceum barbarum canopy leaves. Two mathematical transformations (first‑derivative and continuum removal) were carried out on the original spectra. Based on the correlation analysis between the original spectrum (OS), first‑derivative spectra (FDS), continuum removal spectrum (CRS) and water content, sensitive wavelengths were selected. Random forest regression models (RFRM), partial least squares regression models (PLSRM), ridge regression models (RRM) and univariate regression models (URM) were constructed. Subsequently, the accuracy of these models was tested and evaluated. The results indicate that the fitting degrees of the FDS‑based models and CRS‑based models range from 0.716 to 0.938 and from 0.710 to 0.920, respectively, while OS‑based models range from 0.710 to 0.874. It is evident that FDS‑based and CRS‑based models have a higher fitting degree than OS‑based ones. From the analysis of model types, the random forest regression models (RFRM) exhibit the best fitting degree at 0.874-0.938 , followed by partial least squares regression models (PLSRM) at 0.826-0.866 and ridge regression models (RRM) at 0.737-0.889, then the univariate regression models (URM) at 0.710-0.730 with the worst fit . A comprehensive analysis reveals that the random forest regression model based on first‑derivative spectra (FDR+RFRM) has the best prediction effect. The fitting degree of the training datasets and the test datasets are 0.938 and 0.893, respectively, and the R2, RMSE, MAE and RPD of validation datasets are 0.872, 0.561, 0.466 and 2.156, respectively. It is concluded that a hyperspectral detection model with high prediction accuracy is developed by combining spectral transformation with machine learning, which is suitable for monitoring the water content of Lyceum barbarum canopy leaves. This provides a suitable and efficient method for monitoring the water content of Lyceum barbarum canopy.

Key words: water content, Lyceum barbarum, hyperspectral, partial least squares regression model, random forest regression model, ridge regression model

中图分类号:

S127

李永梅, 王浩, 赵红莉, 张立根, 张鹏程. 基于高光谱变换的枸杞冠层含水率预测模型[J]. 中国农机化学报, 2024, 45(11): 165-171.

Li Yongmei, , Wang Hao, , Zhao Hongli, Zhang Ligen, Zhang Pencheng. Prediction model for the water content of Lyceum barbarum tree canopy based on hyperspectral transformation [J]. Journal of Chinese Agricultural Mechanization, 2024, 45(11): 165-171.

参考文献

[ 1 ] 哈布热, 张宝忠, 李思恩, 等. 基于冠层光谱特征的冬小麦植株含水率诊断研究[J]. 灌溉排水学报, 2018, 37(10): 9-15.
Ha Bure, Zhang Baozhong, Li Si'en, et al. Estimating water content of winter wheat canopy based on its spectral characteristics [J]. Journal of Irrigation and Drainage, 2018, 37(10): 9-15.
[ 2 ] 冀荣华, 郑立华, 邓小蕾, 等. 基于反射光谱的苹果叶片叶绿素和含水率预测模型[J]. 农业机械学报, 2014, 45(8): 269-275.
Ji Ronghua, Zheng Lihua, Deng Xiaolei, et al. Forecasting chlorophyll content and moisture of apple leaves in different tree growth period based on spectral reflectance [J]. Transactions of the Chinese Society for Agricultural Machinery, 2014, 45(8): 269-275.
[ 3 ] 李永梅, 王浩, 赵勇, 等. 基于连续统去除法的枸杞叶片含水率高光谱估算[J]. 浙江农业学报, 2022, 34(4): 781-789.
Li Yongmei, Wang Hao, Zhao Yong, et al. Hyperspectral estimation of leaf water content of Lycium barbarum based on continuum‑removed method [J]. Acta Agriculturae Zhejiangensis, 2022, 34(4): 781-789.
[ 4 ] 代秋芳, 廖臣龙, 李震, 等. 基于CARS-CNN的高光谱柑橘叶片含水率可视化研究[J]. 光谱学与光谱分析, 2022, 42(9): 2848-2854.
[ 5 ] 冯先伟, 陈曦, 包安明, 等. 水分胁迫条件下棉花生理变化及其高光谱响应分析[J]. 干旱区地理, 2004(2): 250-255.
[ 6 ] Thomas J R, Namken L N, Oether G F, et al. Estimating leaf water content by reflectance measurement [J]. Agronomy Journal, 1971, 63: 845-847.
[ 7 ] Danson F M, Steven M D, Malthus T J, et al. High‑spectral resolution data for determining leaf water concentration [J]. International Journal of Remote Sensing, 1992, 13: 461-470.
[ 8 ] 杨玉清, 张甜甜, 李军会, 等. 近红外高光谱的活体玉米叶片水分成像研究[J]. 光谱学与光谱分析, 2018, 38(12): 3743-3747.
[ 9 ] Peng Zhigong, Lin Shaozhe, Zhang Baozhong, et al. Winter wheat canopy water content monitoring based on spectral transforms and "Three‑edge" parameters [J]. Agricultural Water Management, 2020, 240(1): 1-11.
[10] 张君, 蔡振江, 张东方, 等. 基于机器学习与光谱技术的油菜叶片含水率估测研究[J]. 河北农业大报, 2021, 44(6): 122-127.
Zhang Jun, Cai Zhenjiang, Zhang Dongfang, et al. Estimation of water content in rape leaves by spectral reflectance combined with machine learning [J]. Journal of Hebei Agricultural University, 2021, 44(6): 122-127.
[11] Clark R N, Roush T L. Reflectance spectroscopy: Quantitative analysis techniques for remote sensing application [J]. Journal of Geographical Research, 1984, 89(7): 6329-6340.
[12] 潘月, 曹宏鑫, 齐家国, 等. 基于高光谱和数据挖掘的油菜植株含水率定量监测模型[J]. 江苏农业学报, 2022, 38(6): 1550-1558.
[13] Knipling E B. Physical and physiological basis for the reflectance of visible and near‑infrared radiation from vegetation [J]. Remote Sensing of Environment, 1970, 1(3): 155-159.
[14] Liu Liangyun, Wang Jihua, Huang Wenjiang, et al. Estimating winter wheat plant water content using red edge parameters [J]. International Journal of Remote Sensing, 2004, 25(17): 1688-1691.
[15] 贺可勋, 赵书河, 来建斌, 等. 水分胁迫对小麦光谱红边参数和产量变化的影响[J]. 光谱学与光谱分析, 2013, 33(8): 2143-2147.
[16] 段丁丁, 何英彬, 罗善军, 等. 不同高光谱特征参数区分马铃薯品种的优劣势分析[J]. 光谱学与光谱分析, 2018, 38(10): 3215-3220.
[17] 田安红, 熊黑钢, 赵俊三, 等. 分数阶微分对盐渍土野外光谱预处理精度提升的机理分析[J]. 光谱学与光谱分析, 2019, 39(8): 2495-2500.
[18] Moros J. Vibrational spectroscopy provides a green tool for multi‑component analysis [J]. Trends in Analytical Chemistry, 2009, 29(7): 578-591.

[1]	樊宇航, 宋卫东, 王教领, 王明友, 丁天航, 周德欢. 人工神经网络在果蔬干燥领域应用进展[J]. 中国农机化学报, 2024, 45(8): 112-119.
[2]	潘健, 祁雁楠, 陈鲁威, 夏烨, 吕晓兰, . 基于可见/近红外高光谱成像技术的梨树叶部病害识别研究[J]. 中国农机化学报, 2024, 45(8): 162-169.
[3]	王雷, 钟康生, 郭小宝, 盛斌, 肖波, 荆磊. 基于机器视觉的陈皮热泵干燥含水率预测模型研究[J]. 中国农机化学报, 2024, 45(7): 97-103.
[4]	李彦晶, 胡忠强, 张亚萍, 王珺, 徐建恒. 枸杞机械化采收技术与装备研究进展[J]. 中国农机化学报, 2024, 45(5): 16-21.
[5]	周丹, 王应彪, 张兆顺, 张超宇, 王周梅, 刘梦迪. 漾濞核桃物理特性测定及分析[J]. 中国农机化学报, 2024, 45(3): 111-116.
[6]	冯树南, , 谭涛, , 尚静, , 温青纯, 孟庆龙, . 枇杷糖度无损检测及可视化研究[J]. 中国农机化学报, 2024, 45(2): 151-156.
[7]	白大昱, 史庆华, 王建全, 孙丰刚, 李宏伟, 兰鹏. 基于高光谱特征提取的甜瓜白粉病早期识别[J]. 中国农机化学报, 2024, 45(11): 172-177.
[8]	李震, 岳强, 张冬会, 李志强, 于跃, 李嘉楠. 基于离散元法的香菇菌渣颗粒仿真物理参数标定[J]. 中国农机化学报, 2024, 45(10): 170-176.
[9]	贾金豹, 朱成娟, 汪家全, 周鹏. 基于机器学习结合多因子组合的玉米估产研究[J]. 中国农机化学报, 2024, 45(10): 206-214.
[10]	陈远玲, 王梦乔, 金亚光, 侯怡, 李尚平. 基于离散元法的潮湿甘蔗复合肥参数标定[J]. 中国农机化学报, 2024, 45(1): 229-236.
[11]	尚静, 黄人帅, 张艳, 张书琴, 孟庆龙, . 高光谱成像结合模式识别无损检测猕猴桃成熟度[J]. 中国农机化学报, 2022, 43(8): 90-95.
[12]	高文强, 肖志云, . 基于Atrous-CDAE-1DCNN的紫丁香高光谱数据的叶绿素含量反演[J]. 中国农机化学报, 2022, 43(7): 158-166.
[13]	张燕斌, 杜健民, 王圆, 皮伟强, 高新超. 基于无人机高光谱遥感和3D-ResNet的荒漠草原地物分类[J]. 中国农机化学报, 2022, 43(4): 66-73.
[14]	段东瑶, 赵丽清, 殷元元, 郑映晖, 徐鑫, 孙颖. 绿茶加工过程含水率变化规律及预测模型研究[J]. 中国农机化学报, 2022, 43(3): 75-83.
[15]	蒋柏春, 李德仑, 韦克苏, 张富贵, 王杰, 刘红芸. 基于高光谱的烤烟叶绿素含量估算模型研究[J]. 中国农机化学报, 2022, 43(3): 104-110.