基于人工神经网络的大豆叶面积高光谱反演研究

中国农业科学 ›› 2006, Vol. 39 ›› Issue (06): 1138-1145 .

基于人工神经网络的大豆叶面积高光谱反演研究

宋开山,张柏,王宗明,张渊志,刘焕军

收稿日期:2005-08-10 修回日期:2006-02-13 出版日期:2006-06-10 发布日期:2006-06-10

Soybean LAI Estimation with in-situ Collected Hyperspectral Data Based on BP-Neural Networks

,,,,

Received:2005-08-10 Revised:2006-02-13 Online:2006-06-10 Published:2006-06-10

摘要/Abstract

摘要： 【目的】探索不同高光谱模型监测大豆叶面积指数LAI的精度。【方法】实测不同水肥耦合作用下，大豆冠层的高光谱反射率与叶面积指数（Leaf Area Index）数据，对二者进行相关分析；采用敏感波段(801nm,670nm)构建RVI, NDVI, SAVI, OSAVI 和MTVI2植被指数，建立大豆LAI估算模型；最后采用相关系数较大的波段作为神经网络模型的输入变量进行大豆LAI的估算。【结果】大豆LAI与光谱反射率在可见光波段呈负相关、近红外波段呈正相关、红边处相关系数由负变正；微分光谱在三边处与大豆LAI关系密切，在红边处取得最大回归确定性系数（R2 = 0.86）。植被指数可以较为精确反演大豆LAI，确定性系数R2>0.84。人工神经网络模型可以大大提高大豆LAI的估算水平，当隐藏层节点数为2时，R2为0.92，随着隐藏层节点数的增加，R2可高达0.96；在没有黄熟期数据干扰的情况下，神经网络可以进一步提高大豆LAI的反演精度，R2可高达0.99。【结论】与基于植被指数建立的模型相比，神经网络模型可以有效避免因LAI过高而出现的过饱和现象，大大提高了LAI的反演精度。

关键词: 高光谱, 大豆LAI, 植被指数, BP神经网络

Abstract: 【Objective】An experiment was carried out to evaluate the precision of hyperspectral reflectance model for monitoring soybean leaf area index (LAI).【Method】Soybean canopy reflectance data collected with ASD spectroradiometers (350- 1 050nm), which were cultivated in water-fertilizer coupled control conditions, and soybean LAI were collected simultaneously with LI-COR LAI-2000. Firstly, correlation between reflectance, derivative reflectance against soybean LAI were conducted; secondly, five vegetation indices with reflectance at bands 801nm and 670nm were applied to regress against soybean LAI; finally, ANN-BP was established for soybean LAI estimation with changeable nodes in hidden layers. 【Result】It was found that soybean canopy reflectance showed a negative correlation with soybean LAI, while it showed a positive correlation with soybean LAI in near infrared region. Reflectance derivative had an intimate Co relation with soybean LAI in blue, green and red edge spectral region, and got maximum correlation coefficient in red edge region. All five vegetation indices had an intimate correlation with soybean LAI, with regression determination coefficient R2 ranged from 0.84 to 0.88. ANN-BP model could greatly improve soybean LAI estimation accuracy. Determination coefficient (R2 = 0.92) obtained with 2 nodes in hidden layers, however, R2 still can be improved with nodes in hidden layers increasing, and R2 = 0.96 with 8 nodes in hidden layers. Still, it should be noticed that without indecent phonological soybean data participate model establishing, ANN-BP model could improve estimation accuracy with large room, and Determination coefficient (R2 = 0.99) could be obtained with 8 nodes in hidden layers. 【Conclusion】By above analysis, it is concluded that ANN-BP model could be applied to in-situ collected hyperspectral data for vegetation LAI estimation with quite accurate prediction, and in the future, ANN-BP model still should be applied to hyperspectral data for other vegetation biophysical and biochemical parameters estimation.

Key words: Hyperspectral, Soybean LAI, Vegetation index, ANN-BP

宋开山,张柏,王宗明,张渊志,刘焕军. 基于人工神经网络的大豆叶面积高光谱反演研究[J]. 中国农业科学, 2006, 39(06): 1138-1145 .

,,,,. Soybean LAI Estimation with in-situ Collected Hyperspectral Data Based on BP-Neural Networks[J]. Scientia Agricultura Sinica, 2006, 39(06): 1138-1145 .

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/

https://www.chinaagrisci.com/CN/Y2006/V39/I06/1138

[1]	蔡苇荻,张羽,刘海燕,郑恒彪,程涛,田永超,朱艳,曹卫星,姚霞. 基于成像高光谱的小麦冠层白粉病早期监测方法[J]. 中国农业科学, 2022, 55(6): 1110-1126.
[2]	谭先明,张佳伟,王仲林,谌俊旭,杨峰,杨文钰. 基于PLS的不同水氮条件下带状套作玉米产量预测[J]. 中国农业科学, 2022, 55(6): 1127-1138.
[3]	周萌,韩晓旭,郑恒彪,程涛,田永超,朱艳,曹卫星,姚霞. 基于参数化和非参数化法的棉花生物量高光谱遥感估算[J]. 中国农业科学, 2021, 54(20): 4299-4311.
[4]	费帅鹏,禹小龙,兰铭,李雷,夏先春,何中虎,肖永贵. 基于高光谱遥感和集成学习方法的冬小麦产量估测研究[J]. 中国农业科学, 2021, 54(16): 3417-3427.
[5]	李朋磊,张骁,王文辉,郑恒彪,姚霞,朱艳,曹卫星,程涛. 基于高光谱和激光雷达遥感的水稻产量监测研究[J]. 中国农业科学, 2021, 54(14): 2965-2976.
[6]	周珂,柳乐,张俨娜,苗茹,杨阳. GEE支持下的河南省冬小麦面积提取及长势监测[J]. 中国农业科学, 2021, 54(11): 2302-2318.
[7]	李美炫,朱西存,白雪源,彭玉凤,田中宇,姜远茂. 基于无人机影像阴影去除的苹果树冠层氮素含量遥感反演[J]. 中国农业科学, 2021, 54(10): 2084-2094.
[8]	项方林,李鑫格,马吉锋,刘小军,田永超,朱艳,曹卫星,曹强. 基于冠层时序植被指数的冬小麦单产预测[J]. 中国农业科学, 2020, 53(18): 3679-3692.
[9]	周龙飞, 顾晓鹤, 成枢, 杨贵军, 孙乾, 束美艳. 倒伏胁迫下玉米抽雄期叶面积密度光谱诊断[J]. 中国农业科学, 2019, 52(9): 1518-1528.
[10]	张卓,龙慧灵,王崇倡,杨贵军. 冬小麦叶片光合特征高光谱遥感估算模型的比较研究[J]. 中国农业科学, 2019, 52(4): 616-628.
[11]	马岩川,刘浩,陈智芳,张凯,余轩,王景雷,孙景生. 基于高光谱指数的棉花冠层等效水厚度估算[J]. 中国农业科学, 2019, 52(24): 4470-4483.
[12]	王君杰,陈凌,王海岗,曹晓宁,刘思辰,田翔,秦慧彬,乔治军. 糜子叶片氮含量和籽粒蛋白质含量高光谱监测研究[J]. 中国农业科学, 2019, 52(15): 2593-2603.
[13]	张彪,刘璇,毕金峰,吴昕烨,金鑫,李旋,李潇. 基于BP人工神经网络算法的苹果制干适宜性评价[J]. 中国农业科学, 2019, 52(1): 129-142.
[14]	陈鹏飞，李刚，石雅娇，徐志涛，杨粉团，曹庆军. 一款无人机高光谱传感器的验证及其在玉米叶面积指数反演中的应用[J]. 中国农业科学, 2018, 51(8): 1464-1474.
[15]	张春兰，杨贵军，李贺丽，汤伏全，刘畅，张丽妍. 基于随机森林算法的冬小麦叶面积指数遥感反演研究[J]. 中国农业科学, 2018, 51(5): 855-867.