Estimating chlorophyll content of Zizania latifolia with hyperspectral data and random forest

Year 2022, Volume: 7 Issue: 3, 221 - 228, 15.10.2022

Adenan Yandra Nofrizal Rei Sonobe Yamashita Hıroto Akio Morita Takashi Ikka

https://doi.org/10.26833/ijeg.953188

Cited By: 5

Abstract

The amount of chlorophyll in a plant useful to indicate its physiological activity and then changes in chlorophyll content have been used as a good indicator of disease as well as nutritional and environmental stresses on plants. Chlorophyll content estimation is one of the most applications of hyperspectral remote sensing data. The aim of this study is to evaluate dimensionality reduction for estimating chlorophyll contents from hyperspectral reflectance. Random Forest (RF) has been applied to assess biochemical properties such as chlorophyll content from remote sensing data; however, an approach integrating with dimensionality reduction techniques has not been fully evaluated. A total of 200 Zizania latifolia leaves with 5 treatments from Shizuoka University field were measured for reflectance and chlorophyll content. then, the regression models were generated based on RF with three dimensionality reduction methods including principal component analysis, kernel principal component analysis and independent component analysis. This research clarified that PCA is the best method for dimensionality reduction for estimating chlorophyll content in Zizania Latifolia with a RMSE value of 5.65 ± 0.58 μg cm-2.  

Keywords

Dimensionality reduction, Zizania latifolia, Hyperspectral, Machine learning

Thanks

We thank the members of the Laboratory of Plant Functional Physiology and the Laboratory of Macroecology, Shizuoka University, for their support during both fieldwork and laboratory analyses

References

• Ahmad F A, Khan I U, Islam M, Uzair & Ullah H (2017). EIllumination normalization using independent component analysis and filtering. Imaging Science Journal, 65, 308-313.
• Bell A J & Sejnowski T J (1997). The ''independent components'' of natural scenes are edge filters. Vision Research, 37, 3327-3338.
• Benhart S (1997). Kernel principal component analysis. In Artificial Neural Networks-ICAN’97, 583-588.
• Bergstra J & Bengio Y (2012). Random Search for Hyper-Parameter Optimization. Journal of Machine Learning Research, 13, 281-305.
• Biau G & Scornet E (2016). A random forest guided tour. Test, 25, 197-227.
• Bioucas-Dias J M, Plaza A, Camps-Valls G, Scheunders P, Nasrabadi N M & Chanussot J (2013) Hyperspectral Remote Sensing Data Analysis and Future Challenges. Ieee Geoscience and Remote Sensing Magazine, 1, 6-36.
• Blackburn G A & Steele C M (1999). Towards the remote sensing of matorral vegetation physiology: Relationships between spectral reflectance, pigment, and biophysical characteristics of semiarid bushland canopies. Remote Sensing of Environment, 70, 278-292.
• Breiman L (2001). Random forests. Machine Learning, 45, 5-32.
• Breunig F M, Galvao L S, Dalagnol R, Dauve C E, Parraga A, Santi A L, Della Flora D P & Chen S S (2020). Delineation of management zones in agricultural fields using cover crop biomass estimates from PlanetScope data. International Journal of Applied Earth Observation and Geoinformation, 85.
• Chen D, Meng Z W & Chen Y P (2019). Toxicity assessment of molybdenum slag as a mineral fertilizer: A case study with pakchoi (Brassica chinensis L.). Chemosphere, 217, 816-824.
• Cui L, Jiao Z T, Dong Y D, Sun M, Zhang X N, Yin S Y, Ding A X, Chang Y X, Guo J & Xie R (2019). Estimating Forest Canopy Height Using MODIS BRDF Data Emphasizing Typical-Angle Reflectances. Remote Sensing, 11, 21.
• Duda R, Hart O P E & Stork D G. (2001). Pattern Classification. Wiley-Interscience.
• Fan S X, Zhang B H, Li J B, Huang W Q & Wang C P (2016). Effect of spectrum measurement position variation on the robustness of NIR spectroscopy models for soluble solids content of apple. Biosystems Engineering, 143, 9-19.
• Fernandez-Delgado M, Sirsat M S, Cernadas E, Alawadi S, Barro S & Febrero-Bande M (2019). An extensive experimental survey of regression methods. Neural Networks, 111, 11-34.
• Féret J-B, Francois C, Asner G P, Gitelson A A, Martin R E, Bidel L P R, Ustin S L, G. le Maire & Jacquemoud S (2008). PROSPECT-4 and 5: Advances in the leaf optical properties model separating photosynthetic pigments. Remote Sensing of Environment, 112, 3030-3043.
• Gonzales C G & Woods R E (2008). Digital image processing: third edition. Pearson Prentice Hall.
• Gu C Y, Du H Q, Mao F J, Han N, Zhou G M, Xu X J, Sun S B & Gao G L (2016). Global sensitivity analysis of PROSAIL model parameters when simulating Moso bamboo forest canopy reflectance. International Journal of Remote Sensing, 37, 5270-5286.
• Hernandez-Clemente R, Navarro-Cerrillo R M & Zarco-Tejada P J (2014). Deriving Predictive Relationships of Carotenoid Content at the Canopy Level in a Conifer Forest Using Hyperspectral Imagery and Model Simulation. IEEE Transactions on Geoscience and Remote Sensing, 52, 5206-5217.
• Hobley E, Steffens M, Bauke S L & Kogel-Knabner I (2018). Hotspots of soil organic carbon storage revealed by laboratory hyperspectral imaging. Scientific Reports, 8.
• Hotelling H (1933). Analysis of a complex of statistical variables into principal components. Journal of Education Psychology, 24, 417-441.
• Huang J, Sun Y H, Wang M Y, Zhang D D, Sada R & Li M C (2017). Juvenile tree classification based on hyperspectral image acquired from an unmanned aerial vehicle. International Journal of Remote Sensing, 38, 2273-2295.
• Huang Y B, Lee M A, Thomson S J & Reddy K N (2016). Ground-based hyperspectral remote sensing for weed management in crop production. International Journal of Agricultural and Biological Engineering, 9, 98-109.
• Hunt E R, Daughtry C S T & Li L (2016). Feasibility of estimating leaf water content using spectral indices from WorldView-3 ' s near-infrared and shortwave infrared bands. International Journal of Remote Sensing, 37, 388-402.
• Hyvrinen A & Oja E (2000). Independent component analysis: algorithms and applications. Neural nertworks, 13, 411-430.
• Jacquemoud S & Baret F (1990). PROSPECT: A Model of leaf optical properties spectra. Remote Sensing of Environment, 34, 75-91.
• Johansson U, Bostrom H, Lofstrom T & Linusson H (2014). Regression conformal prediction with random forests. Machine Learning, 97, 155-176.
• Kalaji H M, Dabrowski P, Cetner M D, Samborska I A, Lukasik I, Brestic M, Zivcak M, Tomasz H, Mojski J, Kociel H & Panchal B M (2017). A comparison between different chlorophyll content meters under nutrient deficiency conditions. Journal of Plant Nutrition, 40, 1024-1034.
• Kindomihou V, Sinsin B & Meerts P (2006). Effect of defoliation on silica accumulation in five tropical fodder grass species in Benin. Belgian Journal of Botany, 139, 87-102.
• Krawiec G, Czaplicka M & Czernecki J (2017). Physicochemical properties of slags produced at various amounts of iron addition in lead smelting. Journal of Material Cycles and Waste Management, 19, 959-967.
• Lausch A, Pause M, Schmidt A, Salbach C, Gwillym-Margianto S & Merbach I (2013). Temporal hyperspectral monitoring of chlorophyll, LAI, and water content of barley during a growing season. Canadian Journal of Remote Sensing, 39, 191-207.
• Li L M, Zhao J, Wang C R & Yan C J (2020). Comprehensive evaluation of robotic global performance based on modified principal component analysis. International Journal of Advanced Robotic Systems, 17, 11.
• Liaw A & Wiener M (2002). Classification and Regression by random forest. R news, 2, 18-22.
• Lin N, Liu H Q, Yang J J & Liu H L (2020). Hyperspectral estimation of soil composition contents based on kernel principal component analysis and machine learning model. Journal of Applied Remote Sensing, 14.
• Liu H J, Li M Z, Zhang J Y, Sun H, Long Y W, Wu L & Zhang Q (2018). PCA based model on chlorophyll content diagnosis of winter wheat. Ifac Papersonline, 51, 643-647.
• Mallapragada S, Wong M & Hung C C (2018). Dimensionality reduction of Hyperspectral Images for Classification. In Ninth International Conference on Information, 1-7. Tokyo, Japan.
• Mishra S P, Sarkar U, Taraphder S, Datta S, Swain D P, Saikhom R, Panda S & Laishram M (2017). Multivariate statistical data analysis-principal component analysis (PCA). International Journal of Livestock Research, 7, 60-78.
• Mutanga O & Skidmore A K (2004). Narrow band vegetation indices overcome the saturation problem in biomass estimation. International Journal of Remote Sensing, 25, 3999-4014.
• Naik N R & Dinesh K K (2011). An Overview of Independent Component Analysis and Its Applications. Informatica, 53, 63-81.
• Neil S P & Hashemi M R (2018). Fundamentals of Ocean Renewable Energy; Generating electricity from the sea. Elsevier.
• Ormeci C, Sertel E & Sarikaya O (2009). Determination of chlorophyll-a amount in Golden Horn, Istanbul, Turkey using IKONOS and in situ data. Environmental Monitoring and Assessment, 155, 83-90.
• Pearson K (1901) On lines and planes of closet fit to system of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journals of Science, 2, 559-572.
• Porra R J, Thompson W A & Kriedemann P E (1989). Determination of accurate extinction coefficients and simultaneous equations for assaying chlorophylls a and b extracted with four different solvents: verification of the concentration of chlorophyll standards by atomic absorption spectroscopy. Biochimica et Biophysica Acta (BBA) - Bioenergetics, 975, 384-394.
• Prado-Cabrero A, Beatty S, Howard A, Stack J, Bettin P & Nolan J M (2016). Assessment of lutein, zeaxanthin and meso-zeaxanthin concentrations in dietary supplements by chiral high-performance liquid chromatography. European Food Research and Technology, 242, 599-608.
• Richards J A (2013). Remote Sensing Digital Image Analysis fitfh edition. Springer.
• Rodarmel C & Shan J (2002). Principal component analysis for hyperspectral image classification. Surveying and Land Information Science, 62, 115-122.
• Romero A, Aguado I & Yebra M (2012). Estimation of dry matter content in leaves using normalized indexes and PROSPECT model inversion. International Journal of Remote Sensing, 33, 396-414.
• Rutledge D N (2018). Comparison of Principal Components Analysis, Independent Components Analysis and Common Components Analysis. Journal of Analysis and Testing, 2, 235-248.
• Saputro A H, Juansyah S D, Handayani W & Ieee (2018). Banana (Musa sp.) Maturity Prediction System based on Chlorophyll Content using Visible-NIR Imaging. In International Conference on Signals and Systems (ICSigSys), 64-68. Bali, INDONESIA: Ieee.
• Shlens J (2014). A tutorial on principal component analysis. arXiv, arXiv:1404.1100.
• Sims D A & Gamon J A (2002). Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages. Remote Sensing of Environment, 81, 337-354.
• Sonobe R, Hirono Y & Oi A (2020). Non-Destructive Detection of Tea Leaf Chlorophyll Content Using Hyperspectral Reflectance and Machine Learning Algorithms. Plants, 9.
• Sonobe R, Miura Y, Sano T & Horie H (2018). Monitoring Photosynthetic Pigments of Shade-Grown Tea from Hyperspectral Reflectance. Canadian Journal of Remote Sensing, 44, 104-112.
• Sonobe R & Wang Q (2017a). Hyperspectral indices for quantifying leaf chlorophyll concentrations performed differently with different leaf types in deciduous forests. Ecological Informatics, 37, 1-9.
• Sonobe R & Wang Q (2017b). Towards a universal hyperspectral index to assess chlorophyll content in deciduous forests. Remote Sensing, 9, 191.
• Sonobe R, Yamashit H, Nofrizal A Y, Seki H, Morita A & Takashi I (2021). Use of spectral reflectance from a compact spectrometer to assess chlorophyll content in Zizania latifolia. Geocarto International, 1914747.
• Swiniarski R W & Skowron A (2004). Independent component analysis, principal component analysis and rough sets in face recognition. In Transactions on Rough Sets I, eds. J. F. Peters, A. Skowron, J. W. GrzymalaBusse, B. Kostek, R. W. Swiniarski & M. S. Szczuka, 392-404.
• Varshney P K & Arora M K (2004). Advanced image processing techniques for remotely sensed hyperspectral data. Springer.
• Wang H L, Zhang X K, Jin B S, Wang M D, Chen W X & Liu D (2020). WATER LEVEL FLUCTUATIONS DETERMINE THE SPATIAL AND TEMPORAL DISTRIBUTION OF MANCHURIAN WILD RICE (ZIZANIA LATIFOLIA) IN SIX YANGTZE RIVER FLOODPLAIN LAKES, CHINA. Applied Ecology and Environmental Research, 18, 5491-5503.
• Yan N, Du Y M, Liu X M, Chu C, Shi J, Zhang H B, Liu Y H & Zhang Z F (2018). Morphological Characteristics, Nutrients, and Bioactive Compounds of Zizania latifolia, and Health Benefits of Its Seeds. Molecules, 23.
• Zhang H, Duan Z, Li Y Y, Zhao G Y, Zhu S M, Fu W, Peng T, Zhao Q Z, Svanberg S & Hu J D (2019). Vis/NIR reflectance spectroscopy for hybrid rice variety identification and chlorophyll content evaluation for different nitrogen fertilizer levels. Royal Society Open Science, 6.
• Zhang K W, Hu B X, Wang J G, Pattey E & Smith A M (2011). Improving the retrieval of the biophysical parameters of vegetation canopies using the contribution index. Canadian Journal of Remote Sensing, 37, 643-652.
• Zolotova E S, Ivanova N S, Ryabinin V F, Ayan S & Kotelnikova A L (2017). Kotelnikova Element mobility from the copper smelting slag recycling waste into forest soils of the taiga in Middle Urals. Environmental Science and Pollution Research.
• Zou X C, Hernandez-Clemente R, Tammeorg P, Torres C L, Stoddard F L, Makela P, Pellikka P & Mottus M (2015). Retrieval of leaf chlorophyll content in field crops using narrow-band indices: effects of leaf area index and leaf mean tilt angle. International Journal of Remote Sensing, 36, 6031-6055.