基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发

doi:10.12133/j.smartag.2020.2.1.202002-SA004

Smart Agriculture ›› 2020, Vol. 2 ›› Issue (1): 87-98.doi: 10.12133/j.smartag.2020.2.1.202002-SA004

• 专题--农业遥感与表型信息获取分析 • 上一篇下一篇

基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发

刘守阳^1,^2,³(), 金时超^5,⁶, 郭庆华^5,⁶, 朱艳⁴, Baret Fred^1,^2,³()

^1.南京农业大学作物表型组学交叉研究中心，江苏南京 210095
^2.法国农业和环境科学研究院CAPTE实验室，阿维尼翁 210095，法国
^3.南京农业大学江苏省现代作物生产协同创新中心，江苏南京 210095
^4.南京农业大学国家信息农业工程技术中心/教育部智慧农业工程研究中心，江苏南京 210095
^5.中国科学院植物研究所植被与环境变化国家重点实验室，北京 100093
^6.中国科学院大学，北京 100049

收稿日期:2020-02-12 修回日期:2020-03-01 出版日期:2020-03-30
基金资助:
南京农业大学高层次引进人才经费(440-804005)
通信作者:

An algorithm for estimating field wheat canopy light interception based on Digital Plant Phenotyping Platform

Liu Shouyang^1,^2,³(), Jin Shichao^5,⁶, Guo Qinghua^5,⁶, Zhu Yan⁴, Baret Fred^1,^2,³()

^1.Plant Phenomics Research Centre, Nanjing Agricultural University, Nanjing 210095, China
^2.INRAE, EMMAH-CAPTE, Avignon 84914, France
^3.Jiangsu Collaborative Innovation Centre for Modern Crop Production, Nanjing Agricultural University, Nanjing 210095, China
^4.Nanjing Engineering and Technology Centre for Information Agriculture, Nanjing Agricultural University/Engineering Research Centre for Smart Agriculture, Ministry of Education, Nanjing 210095, China
^5.State Key Laboratory of Vegetation and Environmental Change, Institute of Botany, Chinese Academy of Sciences, Beijing 100093, China
^6.University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-02-12 Revised:2020-03-01 Online:2020-03-30

摘要/Abstract

摘要：

冠层光截获能力是反映作物品种间差异的重要功能性状，高通量表型冠层光截获对提高作物改良效率具有重要意义。本研究以小麦为研究目标，利用数字化植物表型平台（D3P）模拟生成了100种冠层结构不同的小麦品种在5个生育期的三维冠层场景，记录了从原始冠层结构中提取的绿色叶面积指数（GAI）、平均倾角（AIA）和散射光截获率（FIPAR_dif）信息作为真实值,进一步利用上述三维小麦场景开展了虚拟的激光雷达（LiDAR）模拟实验，生成了对应的三维点云数据。基于模拟的点云数据提取了其高度分位数特征（H）和绿色分数特征（GF）。最后，利用人工神经网络（ANN）算法分别构建了从不同LiDAR点云特征（H、GF和H+GF）输入到FIPAR_dif、GAI和AIA的反演模型。结果表明，对于GAI、AIA和FIPAR_dif，预测精度从高到低对应的点云特征输入为GF+H > H > GF。由此可见，H特征对提高目标表型特性的估算精度起到了重要作用。输入GF + H特征，在中等测量噪音（10%）情况下，FIPAR_dif和GAI的估算均获得了满意精度，R²分别为0.95和0.98，而AIA的估算精度（R²=0.20）还有待进一步提升。本研究基于D3P模拟数据开展，算法的实际表现还有待通过田间数据进一步验证。尽管如此，本研究验证了D3P协助表型算法开发的能力，展示了高通量LiDAR数据在估算田间冠层光截获和冠层结构方面的较高潜力。

关键词: 冠层光截获, 高通量表型, LiDAR, 数字化植物表型平台（D3P）, 小麦冠层

Abstract:

The capacity of canopy light interception is a key functional trait to distinguish the phenotypic variation over genotypes. High-throughput phenotyping canopy light interception in the field, therefore, would be of high interests for breeders to increase the efficiency of crop improvement. In this research, the Digital Plant Phenotyping Platform（D3P） was used to conduct in-silico phenotyping experiment with LiDAR scans over a wheat field. In this experiment virtual 3D wheat canopies were generated over 100 wheat genotypes for 5 growth stages, representing wide range of canopy structural variation. Accordingly, the actual value of traits targeted were calculated including GAI (green area index), AIA (average inclination angle) and FIPAR_dif (the fraction of intercepted diffuse photosynthetically activate radiation). Then, virtual LiDAR scanning were accomplished over all the treatments and exported as 3D point cloud. Two types of features were extracted from point cloud, including height quantiles (H) and green fractions (GF). Finally, an artificial neural network was trained to predict the traits targeted from different combinations of LiDAR features. Results show that the prediction accuracy varies with the selection of input features, following the rank as GF + H > H > GF. Regarding the three traits, we achieved satisfactory accuracy for FIPAR_dif (R²=0.95) and GAI (R²=0.98) but not for AIA (R²=0.20). This highlights the importance of H feature with respect to the prediction accuracy. The results achieved here are based on in-silico experiments, further evaluation with field measurement would be necessary. Nontheless, as proof of concept, this work further demonstrates that D3P could greatly facilitate the algorithm development. Morever, it highlights the potential of LiDAR measurement in the high-throuhgput phenopyting of canopy light interpcetion and structural traits in the field.

Key words: canopy light interception, high-throughput phenotyoing, LiDAR, Digital Plant Phenotyping Platform (D3P), wheat canopy

中图分类号:

TP391.4

刘守阳, 金时超, 郭庆华, 朱艳, Baret Fred. 基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发[J]. 智慧农业（中英文）, 2020, 2(1): 87-98.

Liu Shouyang, Jin Shichao, Guo Qinghua, Zhu Yan, Baret Fred. An algorithm for estimating field wheat canopy light interception based on Digital Plant Phenotyping Platform[J]. Smart Agriculture, 2020, 2(1): 87-98.

参考文献

1	Godfray H C, Beddington J R, Crute I R, et al. Food security: The challenge of feeding 9 billion people[J]. Science, 2010, 327(5967): 812-818.
2	Liu B, Asseng S, Müller C, et al. Similar estimates of temperature impacts on global wheat yield by three independent methods[J]. Nature Climate Change, 2016, 6(12): 1130-1136.
3	Araus J L, Cairns J E. Field high-throughput phenotyping: the new crop breeding frontier[J]. Trends in Plant Science, 2014, 19(1): 52-61.
4	Furbank R T, Tester M. Phenomics-technologies to relieve the phenotyping bottleneck[J]. Trends in Plant Science, 2011, 16(12): 635-644.
5	Chapman S C, Zheng B, Potgieter A, et al. Visible, infrarednear, and thermal spectral radiance on-board UAVs for high-throughput phenotyping of plant breeding trials[M]. Thenkabail P S, Lyon J G, Huete A. Biophysical and biochemical characterization and plant species studies. CRC Press, 2018: 275-298.
6	Martre P, Quilot-Turion B, Luquet B, et al. Model-assisted phenotyping and ideotype design[M]. Victor O S, Calderini D F. Crop Physiology. Academic Press, 2015: 349-373.
7	Tardieu F, Cabrera-Bosquet L, Pridmore T, et al. Plant phenomics, from sensors to knowledge[J]. Current Biology, 2017, 27(15): 770-783.
8	Monteith J L. Climate and the efficiency of crop production in Britain[J]. Philosophical Transactions of the Royal Society of London Series B： Biological Sciences, 1977, 281(980): 277-294.
9	Monteith J L. Validity of the correlation between intercepted radiation and biomass[J]. Agricultural and Forest Meteorology, 1994, 68(3-4): 213-220.
10	Parry M A, Reynolds M, Salvucci M E, et al. Raising yield potential of wheat II. increasing photosynthetic capacity and efficiency[J]. Journal of Experimental Botany, 2010, 62(2): 453-467.
11	Furbank R T, Jimenez-Berni J A, George-Jaeggli B, et al. Field crop phenomics: Enabling breeding for radiation use efficiency and biomass in cereal crops[J]. New Phytologist, 2019, 223(4): 1714-1727.
12	Su Y, Wu F, Zurui A, et al. Evaluating maize phenotype dynamics under drought stress using terrestrial lidar[J]. Plant Methods, 2019, 15(1): 11-26.
13	Cabrera-Bosquet L, Fournier C, Brichet N, et al. High throughput estimation of incident light, light interception and radiation use efficiency of thousands of plants in a phenotyping platform[J]. New Phytologist, 2016, 212(1): 269-281.
14	Weiss M, Baret F. fAPAR (fraction of Absorbed Photosynthetically Active Radiation) estimates at various scale[C]// 34th International Symposium on Remote Sensing of Environment, 2011.
15	Baret F, Madec S, Irfan K, et al. Leaf-rolling in maize crops: From leaf scoring to canopy-level measurements for phenotyping[J]. Journal of Experimental Botany, 2018, 69(10): 2705-2716.
16	Liu S, Baret F, Abichou M, et al. Estimating wheat green area index from ground-based LiDAR measurement using a 3D canopy structure model[J]. Agricultural and Forest Meteorology, 2017, 247: 12-20.
17	Jimenez-Berni J A, Deery D M, PabloRozas-Larraondo, et al. High throughput determination of plant height, ground cover, and above-ground biomass in wheat with LiDAR[J]. Frontiers in Plant Science, 2018, 9: no. 237.
18	Jin S, Su Y, Gao S， et al. Deep learning: Individual maize segmentation from terrestrial lidar data using faster R-CNN and regional growth algorithms[J]. Frontiers in Plant Science, 2018, 9: no. 866.
19	Jin S, Su Y, Wu F, et al. Stem-leaf segmentation and phenotypic trait extraction of individual maize using terrestrial LiDAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(3): 1336-1346.
20	Lin Y. LiDAR: An important tool for next-generation phenotyping technology of high potential for plant phenomics?[J]. Computers and Electronics in Agriculture, 2015, 119: 61-73.
21	Campbell G S, Norman J M. An Introduction to Environmental Biophysics[M]. New York: Springer, 1998.
22	Zhao K, García M, Liu S, et al. Terrestrial lidar remote sensing of forests: Maximum likelihood estimates of canopy profile, leaf area index, and leaf angle distribution[J]. Agricultural and Forest Meteorology, 2015, 209-210: 100-113.
23	Liu S, Martre P, Buis S, et al. Estimation of plant and canopy architectural traits using the D3P Digital Plant Phenotyping Platform[J]. Plant Physiology, 2019, 181(3): 881-890.
24	Godin C, Sinoquet H. Functional-structural plant modelling[J]. New phytologist, 2005, 166(3): 705-708.
25	Vos J, Evers B, Buck-Sorlin H, et al. Functional-structural plant modelling: A new versatile tool in crop science[J]. Journal of Experimental Botany, 2010, 61(8): 2101-2115.
26	Pradal C, Dufour-Kowalski S, Boudon F, et al. OpenAlea: A visual programming and component-based software platform for plant modelling[J]. Functional Plant Biology, 2008, 35(10): 751-760.
27	Fournier C, Andrieu B, Ljutovac S, et al. ADEL-Wheat: A 3D architectural model of wheat development[C]// International Symposium on Plant Growth Modeling, Simulation, Visualization and their Applications (PMA03). 2003: 54-63.
28	Chelle M, Andrieu B. The nested radiosity model for the distribution of light within plant canopies[J]. Ecological Modelling, 1998, 111(1): 75-91.
29	Andrieu B, Baret F. Indirect methods of estimating crop structure from optical measurements, crop structure and light microclimate[M]. Crop Structure and Light Microclimate: Characterization and Application. Paris: INRA, 1993: 285-322.
30	Chen J M, Black T Defining leaf area index for non-flat leaves[J]. Plant, Cell & Environment, 1992, 15(4): 421-429.
31	Lang A R G. Application of some of Cauchy's theorems to estimation of surface areas of leaves, needles and branches of plants, and light transmittance[J]. Agricultural and Forest Meteorology, 1991, 55(3): 191-212.
32	Baret F, Buis S. Estimating canopy characteristics from remote sensing observations: Review of methods and associated problems[M]. Liang S. Advances in Land Remote Sensing. Dordrecht: Springer, 2008: 173-201.
33	Zhao K, Popescu S, Meng X, et al. Characterizing forest canopy structure with lidar composite metrics and machine learning[J]. Remote Sensing of Environment, 2011, 115(8): 1978-1996.
34	Abichou M, de Solan B, Andrieu B. Architectural Response of wheat cultivars to row spacing reveals altered perception of plant density[J]. Frontiers in Plant Science, 2019, 10: 999.
35	Baret F, Hagolle O, Geiger B, et al. LAI, fAPAR and fCover CYCLOPES global products derived from VEGETATION: Part 1: Principles of the algorithm[J]. Remote Sensing of Environment, 2007, 110(3): 275-286.
36	Bacour C, Baret F, Béal D, et al. Neural network estimation of LAI, fAPAR, fCover and LAI×Cab, from top of canopy MERIS reflectance data: Principles and validation[J]. Remote Sensing of Environment, 2006, 105(4): 313-325.
37	Martre P, Dambreville A. A model of leaf coordination to scale-up leaf expansion from the organ to the canopy[J]. Plant Physiology, 2018, 176(1): 704-716.
38	Liu S, Baret F, Andrieu B, et al. Modeling the spatial distribution of plants on the row for wheat crops: Consequences on the green fraction at the canopy level[J]. Computers and Electronics in Agriculture, 2017, 136: 147-156.
39	Sinclair R, Hone T. Leaf nitrogen, photosynthesis, and crop radiation use efficiency: A review[J]. Crop Science, 1989, 29: 90-98.
40	Baret F, de Solan B, Lopez-Lozano R, et al. GAI estimates of row crops from downward looking digital photos taken perpendicular to rows at 57.5° zenith angle: Theoretical considerations based on 3D architecture models and application to wheat crops[J]. Agricultural and Forest Meteorology, 2010, 150(11): 1393-1401.
41	Hartmann A, Czauderna T, Hoffmann R, et al. HTPheno: An image analysis pipeline for high-throughput plant phenotyping[J]. BMC bioinformatics, 2011, 12(1): 148.
42	Donald C M. The breeding of crop ideotypes[J]. Euphytica, 1967, 17(3): 385-403.
43	Jin X, Madec S, Dutartre D, et al. High-throughput measurements of stem characteristics to estimate ear density and above-ground biomass[J]. Plant Phenomics, 2019： no. 4820305.
44	Madec S, Jin X, Lu H, et al. Ear density estimation from high resolution RGB imagery using deep learning technique[J]. Agricultural and Forest Meteorology, 2019， 264: 225-234.
45	Pound M P, Atkinson J A, Townsend A J, et al. Deep machine learning provides state-of-the-art performance in image-based plant phenotyping[J]. Gigascience, 2017, 6(10): 1-10.
46	Taghavi Namin S, Esmaeilzadeh M, Najafi M, et al. Deep phenotyping: Deep learning for temporal phenotype/genotype classification[J]. Plant Methods, 2018, 14(1): no. 66.
47	Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets[C]// International Conference on Neural Information Processing Systems, 2014: 2672-2680.
48	Qi C, Yi L, Su H, et al. PointNet++: Deep hierarchical feature learning on point sets in a metric space[M]. Bach F R, Jordan M. Advances in neural information processing systems, 2017: 5099-5108.
49	Jin S, Su Y, Gao S, et al. Separating the structural components of maize for field phenotyping using terrestrial lidar data and deep convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020, 58(4): 2644-2658.
50	Han J, Jentzen A, Weinan E. Solving high-dimensional partial differential equations using deep learning[J]. Proceedings of the National Academy of Sciences, 2018, 115(34): 8505-8510.

[1]	胡松涛, 翟瑞芳, 王应华, 刘志, 朱剑忠, 任荷, 杨万能, 宋鹏. 基于多源数据的马铃薯植株表型参数提取[J]. 智慧农业(中英文), 2023, 5(1): 132-145.
[2]	刘理民, 何雄奎, 刘伟洪, 刘紫嫣, 韩虎, 李扬帆. 果园自主导航兼自动对靶喷雾机器人[J]. 智慧农业(中英文), 2022, 4(3): 63-74.
[3]	范道全, 张美娜, 潘健, 吕晓兰. 基于靶标叶面积密度参数的变量喷雾控制系统开发与性能试验[J]. 智慧农业(中英文), 2021, 3(3): 60-69.
[4]	阳旭, 胡松涛, 王应华, 杨万能, 翟瑞芳. 利用多时序激光点云数据提取棉花表型参数方法[J]. 智慧农业(中英文), 2021, 3(1): 51-62.

基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发

An algorithm for estimating field wheat canopy light interception based on Digital Plant Phenotyping Platform

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价