Estimation model of potassium content in cotton leaves based on hyperspectral information of multi-leaf position

doi:10.1016/j.jia.2024.03.012

Journal of Integrative Agriculture

2025, Vol. 24

Issue (11): 4225-4241 DOI: 10.1016/j.jia.2024.03.012

Crop Science

Advanced Online Publication | Current Issue | Archive | Adv Search

Estimation model of potassium content in cotton leaves based on hyperspectral information of multi-leaf position

Qiushuang Yao*, Huihan Wang*, Ze Zhang^#, Shizhe Qin, Lulu Ma, Xiangyu Chen, Hongyu Wang, Lu Wang, Xin Lü^#

Key Laboratory of Oasis Eco-Agriculture, College of Agriculture, Shihezi University, Shihezi 832000, China

Highlights
● Vertical distribution characteristics of leaf potassium content (LKC, %) of cotton have been clarified.
● Considering the instability and limited applicability of the single-leaf position and layered-leaf position models in estimating nutrient content, this paper has developed a LKC multi-leaf position estimation model.
● Based on the selected advantageous monitoring leaf position, the hyperspectral remote sensing technology can accurately estimate the LKC of cotton during its critical growth stages.

Abstract
References

Download: PDF in ScienceDirect
Export: BibTeX | EndNote (RIS)

摘要

钾（K）作为一种流动性强的营养元素，可以通过再分配不断调整棉花叶间与叶内对K需求的适应策略，间接导致了不同叶位叶片钾含量（LKC, %）的丰缺变化。然而，受光照和叶龄的相互作用，不同叶位叶片对这种变化的敏感程度并不相同，也包括对光谱的反射和吸收。如何选择最佳监测叶位是利用光谱遥感技术快速准确评估棉花LKC的一个重要因素。因此，本研究基于棉花自上而下叶位LKC的垂直分布特征，提出一种多叶位综合估算模型，实现准确估算棉花LKC的同时优化监测叶位的选择策略。连续2年（2020-2021年），我们采集了棉花蕾期、花期和铃期自上而下全部叶位主茎叶片（Li, i=1, 2, 3,...n）的高光谱成像数据。研究不同叶位LKC的垂直分布特征，敏感性差异以及与光谱之间的相关关系，确定最佳监测优势叶位范围；利用偏最小二乘（PLSR）、随机森林回归（RFR）、支持向量机回归（SVR）以及熵权法（EWM）分别建立了单叶位和多叶位LKC估算模型。结果表明，棉花LKC呈垂直异质性分布，LKC自上而下呈先增加后缓慢减少的趋势，平均LKC在开花期达到最大值。上部叶位叶片对K的敏感性更强，与光谱的相关性更好。三个生育时期选择的监测优势叶位范围分别为L1-L5, L1-L4以及L1-L2。基于监测优势叶位，三个生育期估算LKC的最佳单叶位模型分别为PLSR-CARS-L4, PLSR-RF-L1及SVR-RF-L2，R2val分别为0.786, 0.58及0.768，RMSEval分别为0.168, 0.197及0.191；利用EWM构建多叶位置LKC估计模型，R2val分别为0.887, 0.728和0.703；RMSEval分别为0.134, 0.172和0.209。相比之下，新开发的多叶位综合估算模型取得较好结果，在精度较高的基础上提高了模型的稳定性，尤其是在蕾期和花期。这些结果对棉花LKC光谱模型的研究及选择适合的田间监测叶位具有重要意义。

Abstract

Potassium (K) is a highly mobile nutrient element that continuously adjusts its demand strategy among and within cotton leaves through redistribution, indirectly leading to variations in the leaf potassium content (LKC, %) at different leaf positions. However, due to the interaction between light and leaf age, leaf sensitivity to this change varies at different positions, including the reflection and absorption of the spectrum. Selecting the optimal leaf position for monitoring is a crucial factor in the rapid and accurate evaluation of cotton LKC using spectral remote sensing technology. Therefore, this study proposes a comprehensive multi-leaf position estimation model based on the vertical distribution characteristics of LKC from top to bottom, aiming to achieve an accurate estimation of cotton LKC and optimize the strategy for selecting the monitored leaf position. Between 2020 and 2021, we collected hyperspectral imaging data of the main stem leaves at different positions from top to bottom (Li, i=1, 2, 3, ..., n) during the cotton budding, flowering, and boll-setting stages. Vertical distribution characteristics, sensitivity differences, and spectral correlations of LKC at different leaf positions were investigated. Additionally, the optimal range of the dominant leaf position for monitoring was determined. Partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), and the entropy weight method (EWM) were employed to develop LKC estimation models for single- and multi-leaf positions. The results showed a vertical heterogeneous distribution of cotton LKC, with LKC initially increasing and then gradually decreasing from top to bottom; the average LKC of cotton reached its maximum value at the flowering stage. The upper leaf position demonstrated greater sensitivity to K and exhibited a stronger correlation with the spectrum. The selected dominant leaf positions for the three growth stages were L1–L5, L1–L4, and L1–L2, respectively. Based on the dominant leaf position monitoring range, the optimal single leaf position models for estimating LKC during the three growth stages were PLSR-L4, PLSR-L1, and SVR-L2, with the coefficient of determination of the validation set (R²val) being 0.786, 0.580, and 0.768, and the root-mean-square error of the validation set (RMSEval) being 0.168, 0.197, and 0.191, respectively. The multi-leaf position LKC estimation model was constructed by EWM with R²val being 0.887, 0.728, and 0.703, and RMSEval being 0.134, 0.172, and 0.209, respectively. In contrast, the newly developed multi-leaf position comprehensive estimation model yielded superior results, improving the model’s stability based on high accuracy, especially during the budding and flowering stages. These findings hold significant importance for investigating cotton LKC spectral models and selecting suitable leaf positions for field monitoring.

Keywords: hyperspectral vertical heterogeneity leaf position cotton LKC

Received: 01 November 2023 Accepted: 01 January 2024 Online: 02 March 2024

Fund: This study was supported by the Corps Leading Talents Program, China (2023YZ01), the Tianshan Talent Training Program, China (2023TS05), and the Crop Smart Production Innovation Team, China (2023TD01).

About author: Qiushuang Yao, E-mail: 20182012108@stu.shzu.edu.cn; Huihan Wang, E-mail: 20192012028@stu.shzu.edu.cn; #Correspondence Ze Zhang, E-mail: zhangze1227@shzu.edu.cn; Xin Lü, E-mail: luxin@shzu.edu.cn * These authors contributed equally to this study.

	Service
	E-mail this article
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors

Cite this article:

Qiushuang Yao, Huihan Wang, Ze Zhang, Shizhe Qin, Lulu Ma, Xiangyu Chen, Hongyu Wang, Lu Wang, Xin Lü. 2025. Estimation model of potassium content in cotton leaves based on hyperspectral information of multi-leaf position. Journal of Integrative Agriculture, 24(11): 4225-4241.

Bao S D. 2000. Soil and Agricultural Chemistry Analysis. 3rd ed. China Agriculture Press, Beijing. (in Chinese)

Battie-Laclau P, Laclau J P, Beri C, Mietton L, Muniz M R A, Arenque B C, Piccolo M D C, De Cassia Piccolo M, Jordan-Meille L, Bouillet J P, Nouvellon Y. 2013. Photosynthetic and anatomical responses of Eucalyptus grandis leaves to potassium and sodium supply in a field experiment. Plant Cell & Environment, 37, 70–81.

Cassman K G, Kerby T A, Robert B A, Bryant D C, Broude S M. 1989. Differential response of two cotton cultivars to fertilizer and soil potassium. Agronomy Journal, 81, 870–876.

Chen Q, Tian X L, Wei Y, Wang N. 2015. Spatiotemporal pattern of potassium deficiency symptoms and K+ concentration in cotton leaf. Acta Agronomica Sinica, 41, 1888–1898. (in Chinese)

Clement-Bailey J, Gwathmey C O. 2007. Potassium effects on partitioning, yield, and earliness of contrasting cotton cultivars. Agronomy Journal, 99, 1130–1136.

Coble A P, VanderWall B, Mau A, Cavaleri M A. 2016. How vertical patterns in leaf traits shift seasonally and the implications for modeling canopy photosynthesis in a temperate deciduous forest. Tree Physiology, 36, 1077–1091.

Cope J T. 1981. Effects on 50 years of fertilization with phosphorus and potassium on soil test levels and yields at six locations. Soil Science Society of America Journal, 45, 342–347.

Dong R, Miao Y X, Wang X B, Chen Z C, Yuan F, Zhang W N, Li H. 2020. Estimating plant nitrogen concentration of maize using a leaf fluorescence sensor across growth stages. Remote Sensing, 12, 1139.

Duan D D, Zhao C J, Li Z H, Yang G J, Yang W D. 2019. Estimating total leaf nitrogen concentration in winter wheat by canopy hyperspectral data and nitrogen vertical distribution. Journal of Integrative Agriculture, 18, 1562.

El-Hendawy S, Al-Suhaibani N, Hassan W, Tahir M, Schmidhalter U, Aroca R. 2017. Hyperspectral reflectance sensing to assess the growth and photosynthetic properties of wheat cultivars exposed to different irrigation rates in an irrigated arid region. PLoS ONE, 12, e0183262.

El-Hendawy S E, Al-Suhaibani N A, Hassan W M, Dewir Y H, Elsayed S, Al-Ashkar I, Abdella K A, Schmidhalter U. 2019. Evaluation of wavelengths and spectral reflectance indices for high-throughput assessment of growth, water relations and ion contents of wheat irrigated with saline water. Agricultural Water Management, 212, 358–377.

Fridgen J L, Varco J J. 2004. Dependency of cotton leaf nitrogen, chlorophyll, and reflectance on nitrogen and potassium availability. Agronomy Journal, 96, 63–69.

Gara T W, Darvishzadeh R, Skidmore A K. 2018. Impact of vertical canopy position on leaf spectral properties and traits across multiple species. Remote Sensing, 10, 346.

Halevy J. 1976. Growth and nutrient uptake of two cotton cultivars grown under irrigation. Agronomy Journal, 68, 701–705.

He J Y, Zhang X B, Guo W T, Pan Y Y, Yao X, Cheng T, Zhu Y, Cao W X, Tian Y C. 2020. Estimation of vertical leaf nitrogen distribution within a rice canopy based on hyperspectral data. Frontiers in Plant Science, 10, 1802.

Hirose T, Werger M J A. 1987. Maximizing daily canopy photosynthesis with respect to the leaf nitrogen allocation pattern in the canopy. Oecologia, 72, 520–526.

Huang W J, Wang Z J, Huang L S, David W, Lamb, Ma Z H, Zhang J C, Wang J H, Zhao C J. 2011. Estimation of vertical distribution of chlorophyll concentration by bi-directional canopy reflectance spectra in winter wheat. Precision Agriculture, 12, 165–178.

Hui F, Xie Z W, Li H g, Guo Y, Li B G, Liu Y L, Ma Y T. 2022. Image-based root phenotyping for field-grown crops: An example under maize/soybean intercropping. Journal of Integrative Agriculture, 21, 1606–1619.

Jordan-Meille L, Pellerin S. 2004. Leaf area establishment of a maize (Zea mays L.) field crop under potassium deficiency. Plant & Soil, 265, 75–92.

Leigh R A, Jones R G W. 2010. A hypothesis relating critical potassium concentrations for growth to the distribution and functions of this ion in the plant cell. New Phytologist, 97, 1–13.

Li L T, Geng S N, Lin D, Su G L, Zhang Y J, Chang L Y, Ji Y R, Wang Y L, Wang L. 2022. Accurate modeling of vertical leaf nitrogen distribution in summer maize using in situ leaf spectroscopy via CWT and PLS-based approaches. European Journal of Agronomy, 140, 126607.

Li L T, Jakli B, Lu P P, Ren T, Ming J, Liu S S, Wang S Q, Lu J W. 2018. Assessing leaf nitrogen concentration of winter oilseed rape with canopy hyperspectral technique considering a non-uniform vertical nitrogen distribution. Industrial Crops and Products, 116, 1–14.

Lin D, Li G Z, Zhu Y D, Liu H T, Li L T, Fashad S, Zhang X Y, Wei C, Jiao Q J. 2021. Predicting copper content in chicory leaves using hyperspectral data with continuous wavelet transforms and partial least squares. Computers and Electronics in Agriculture, 187, 106293.

Liu S S, Peng Y, Du W, Le Y, Li L. 2015. Remote estimation of leaf and canopy water content in winter wheat with different vertical distribution of water-related properties. Remote Sensing, 7, 4626–4650.

Liu X J, Zhang, K, Zhang Z Y, Cao Q, Lv Z F, Yuan Z F, Tian Y C, Cao W X, Zhu Y. 2017. Canopy chlorophyll density based index for estimating nitrogen status and predicting grain yield in rice. Frontiers in Plant Science, 8, 1829.

López M, El-Dahan M A A, Leidi E O. 2008. Genotypic variation in potassium uptake in dryland cotton. Journal of Plant Nutrition, 31, 1947–1962.

Ma C Y, Zhai L T, Li C C, Wang Y L. 2022. Hyperspectral estimation of nitrogen content in different leaf positions of wheat using machine learning models. Applied Sciences Basel, 12, 7427.

Oos terhuis D M, Bednarz C W. 1997. Phy siological changes during the development of potassium deficiency in cotton. In: Plant Nutrition for Sustainable Food Production and Environment: Proceedings of the XIII International Plant Nutrition Colloquium. Tokyo, Japan. pp. 347–351.

Osaki M. 1995. Ontogenetic changes of N, P, K, Ca, and Mg contents in individual leaves and tubers of potato plants. Soil Science and Plant Nutrition, 41, 417–428.

Peng S, Garcia F V, Laza R C. 1996. Increased N-use efficiency using a chlorophyll meter on high-yielding irrigated rice. Field Crops Research, 47, 243–252.

Pettigrew W T. 2008. Potassium influences on yield and quality production for maize, wheat, soybean and cotton. Physiologia Plantarum, 133, 670–681.

Qin S Z, Ding Y R, Zhou Z X, Zhou M, Wang H Y, Xu F, Yao Q S, Lv X, Zhang Z, Zhang L F. 2023. Study on the nitrogen content estimation model of cotton leaves based on “image–spectrum–fluorescence” data fusion. Frontiers in Plant Science, 14, 1117277.

Reddy K R, Zhao D L. 2005. Interactive effects of elevated CO2 and potassium deficiency on photosynthesis, growth, and biomass partitioning of cotton. Field Crops Research, 94, 201–213.

Oosterhuis D M, Loka D A, Raper T B. 2013. Potassium and stress alleviation: physiological functions and management of cotton. Journal of Plant Nutrition & Soil Science, 176, 331–343.

Romero I, Garcia-Escudero E, Martin I. 2010. Effects of leaf position on blade and petiole mineral nutrient concentration of tempranillo grapevine (Vitis vinifera L.). American Journal of Enology & Viticulture, 61, 544–550.

Shahzad A N, Rizwan M, Asghar M G, Qureshi M K, Bukhari S A H, Kiran A, Wakeel A. 2019. Early maturing Bt cotton requires more potassium fertilizer under water deficiency to augment seed-cotton yield but not lint quality. Scientific Reports, 9, 7378.

Shu M Y, Zhu J Y, Yang X H, Gu X H, Li B G, Ma Y T. 2023. A spectral decomposition method for estimating the leaf nitrogen status of maize by UAV-based hyperspectral imaging. Computers and Electronics in Agriculture, 212, 180100.

Song C Y, Zhang F, Li J S, Xie J Y, Yang C, Zhou H, Zhang J X. 2023. Detection of maize tassels for UAV remote sensing image with an improved YOLOX model. Journal of Integrative Agriculture, 22, 1671–1683.

Sun J J, Yang W D, Zhang M J, Feng M C, Xiao L J, Ding G W. 2021. Estimation of water content in corn leaves using hyperspectral data based on fractional order savitzky–golay derivation coupled with wavelength selection. Computers and Electronics in Agriculture, 182, 105989.

Vreugdenhil D. 1985. Source-to-sink gradient of potassium in the phloem. Planta, 163, 238–240.

Wan L, Cen H Y, Zhu J P, Zhang J F, Zhu Y M, Sun D W, Du X Y, Zhai L, Weng H Y, Li Y J, Li X R, Bao Y D, Shou J Y, He Y. 2020. Grain yield prediction of rice using multitemporal UAV-based RGB and multispectral images and model transfer - A case study of small farmlands in the South of China. Agriculture and Forest Meteorology, 291, 108096.

Wang J Y, Gu C C, Liu K C. 2022. Anomaly electricity detection method based on entropy weight method and isolated forest algorithm. Frontiers in Energy Research, 10, 984473.

Wang N, Hua H B, Eneji A E, Li Z H, Duan L S, Tian X L. 2012. Genotypic variations in photosynthetic and physiological adjustment to potassium deficiency in cotton (Gossypium hirsutum). Journal of Photochemistry and Photobiology (B: Biology), 110, 1–8.

Wang Q, Li P H. 2013. Canopy vertical heterogeneity plays a critical role in reflectance simulation. Agricultural and Forest Meteorology, 169, 111–121.

Wang S H, Zhu Y, Jiang H D, Cao W X. 2006. Positional differences in nitrogen and sugar concentrations of upper leaves relate to plant N status in rice under different N rates. Field Crops Ressearch, 96, 224–234.

Wijewardane N K, Zhang H C, Yang J L, Schnable J C, Schachtman D P, Ge Y F. 2023. A leaf-level spectral library to support high-throughput plant phenotyping: Predictive accuracy and model transfer. Journal of Experimental Botany, 74, 4050–4062.

Wolpert J A, Anderson M M. 2007. Rootstock influence on grapevine nutrition: Minimizing nutrient losses to the environment. In: Conference Proceedings of the 2007 California Plant and Soil Conference: Opportunities for California Agriculture. California, America.

Wu X, Qian C, Mao Z. 2007. Study on the hyperspectral characteristics of cotton. Agriculture & Hydrology Applications of Remote Sensing. International Society for Optics and Engineering, 6411, doi: 10.1117/12.693313.

Yang F Q,Wang G W, Zhang Z Y, Eneji A E, Duan L S, Li Z H, Tian X L. 2011. Genotypic variations in potassium uptake and utilization in cotton. Journal of Plant Nutrition, 34, 83–97.

Ye H C, Huang W J, Huang S Y, Wu B, Dong Y Y, Cui B. 2018. Remote estimation of nitrogen vertical distribution by consideration of maize geometry characteristics. Remote Sensing, 10, 1995.

Yu F H, Bai J C, Jin Z Y, Guo Z H, Yang J X, Chen C l. 2023. Combining the critical nitrogen concentration and machine learning algorithms to estimate nitrogen deficiency in rice from UAV hyperspectral data. Journal of Integrative Agriculture, 22, 1216–1229.

Yuan Z F, Cao Q, Zhang K, Ata-Ul-Karim S T, Tian Y C, Zhu Y, Cao W X, Liu X J. 2016. Optimal leaf positions for SPAD meter measurement in rice. Frontiers in Plant Science, 7, 719.

Zhang K, Liu X J, Ata-Ul-Karim S T, Lu J S, Krienke B, Li S Y, Cao Q, Zhu Y, Cao W X, Tian Y C. 2019. Development of chlorophyll-meter-index-based dynamic models for evaluation of high-yield japonica rice production in Yangtze river reaches. Agronomy-Basel, 9, 106.

Zhao C J, Li H L, Li P H, Yang G J, Gu X H, Lan Y B. 2017. Effect of vertical distribution of crop structure and biochemical parameters of winter wheat on canopy reflectance characteristics and spectral indices. IEEE Transactions on Geoscience and Remote Sensing, 5, 236–247.

Zhao D L, Oosterhuis D M, Bednarz C W. 2001. Influence of potassium deficiency on photosynthesis, chlorophyll content, and chloroplast ultrastructure of cotton plants. Photosynthetica, 39, 103–109.

Zörb C, Senbayram M, Peiter E. 2014. Potassium in agriculture-status and perspectives. Journal of Plant Physiology, 171, 656–669.

[1]	Weiguang Yang, Bin Zhang, Weicheng Xu, Shiyuan Liu, Yubin Lan, Lei Zhang. Impact of hyperspectral reconstruction techniques on the quantitative inversion of rice physiological parameters: A case study using the MST++ model[J]. >Journal of Integrative Agriculture, 2025, 24(7): 2540-2557.
[2]	Phiraiwan Jermwongruttanachai, Siwalak Pathaveerat, Sirinad Noypitak. Quantification of the adulteration concentration of palm kernel oil in virgin coconut oil using near-infrared hyperspectral imaging [J]. >Journal of Integrative Agriculture, 2024, 23(1): 298-309.
[3]	YU Feng-hua, BAI Ju-chi, JIN Zhong-yu, GUO Zhong-hui, YANG Jia-xin, CHEN Chun-ling. Combining the critical nitrogen concentration and machine learning algorithms to estimate nitrogen deficiency in rice from UAV hyperspectral data[J]. >Journal of Integrative Agriculture, 2023, 22(4): 1216-1229.
[4]	YANG Fei-fei, LIU Tao, WANG Qi-yuan, DU Ming-zhu, YANG Tian-le, LIU Da-zhong, LI Shi-juan, LIU Sheng-ping. Rapid determination of leaf water content for monitoring waterlogging in winter wheat based on hyperspectral parameters[J]. >Journal of Integrative Agriculture, 2021, 20(10): 2613-2626.
[5]	DUAN Dan-dan, ZHAO Chun-jiang, LI Zhen-hai, YANG Gui-jun, ZHAO Yu, QIAO Xiao-jun, ZHANG Yun-he, ZHANG Lai-xi, YANG Wu-de. Estimating total leaf nitrogen concentration in winter wheat by canopy hyperspectral data and nitrogen vertical distribution[J]. >Journal of Integrative Agriculture, 2019, 18(7): 1562-1570.
[6]	LIU Ke, ZHOU Qing-bo, WU Wen-bin, XIA Tian, TANG Hua-jun. Estimating the crop leaf area index using hyperspectral remote sensing[J]. >Journal of Integrative Agriculture, 2016, 15(2): 475-491.
[7]	DONG Chun-wang, YE Yang, ZHANG Jian-qiang, ZHU Hong-kai , LIU Fei. Detection of Thrips Defect on Green-Peel Citrus Using Hyperspectral Imaging Technology Combining PCA and B-Spline Lighting Correction Method[J]. >Journal of Integrative Agriculture, 2014, 13(10): 2229-2235.

No Suggested Reading articles found!

Viewed

Full text

Abstract

Cited

Shared

Discussed

Cite this article:

About JIA

Editorial board

For authors