Advancing Hyperspectral Imaging Techniques for Root Systems: a New Pipeline for Macro- and Microscale Image Acquisition and Classification

Overview

Journal Plant Methods

Publisher Biomed Central

Specialty Biology

Date 2024 Nov 11

PMID 39529150

Authors

Corine Faehn

Grzegorz Konert

Markku Keinanen

Katja Karppinen

Kirsten Krause

Affiliations

Soon will be listed here.

Abstract

Background: Understanding the environmental impacts on root growth and root health is essential for effective agricultural and environmental management. Hyperspectral imaging (HSI) technology provides a non-destructive method for detailed analysis and monitoring of plant tissues and organ development, but unfortunately examples for its application to root systems and the root-soil interface are very scarce. There is also a notable lack of standardized guidelines for image acquisition and data analysis pipelines.

Methods: This study investigated HSI techniques for analyzing rhizobox-grown root systems across various imaging configurations, from the macro- to micro-scale, using the imec VNIR SNAPSCAN camera. Focusing on three graminoid species with different root architectures allowed us to evaluate the influence of key image acquisition parameters and data processing techniques on the differentiation of root, soil, and root-soil interface/rhizosheath spectral signatures. We compared two image classification methods, Spectral Angle Mapper (SAM) and K-Means clustering, and two machine learning approaches, Random Forest (RF) and Support Vector Machine (SVM), to assess their efficiency in automating root system image classification.

Results: Our study demonstrated that training a RF model using SAM classifications, coupled with wavelength reduction using the second derivative spectra with Savitzky-Golay (SG) smoothing, provided reliable classification between root, soil, and the root-soil interface, achieving 88-91% accuracy across all configurations and scales. Although the root-soil interface was not clearly resolved, it helped to improve the distinction between root and soil classes. This approach effectively highlighted spectral differences resulting from the different configurations, image acquisition settings, and among the three species. Utilizing this classification method can facilitate the monitoring of root biomass and future work investigating root adaptations to harsh environmental conditions.

Conclusions: Our study addressed the key challenges in HSI acquisition and data processing for root system analysis and lays the groundwork for further exploration of VNIR HSI application across various scales of root system studies. This work provides a full data analysis pipeline that can be utilized as an online Python-based tool for the semi-automated analysis of root-soil HSI data.

References

Chandregowda M, Tjoelker M, Pendall E, Zhang H, Churchill A, Power S . Belowground carbon allocation, root trait plasticity, and productivity during drought and warming in a pasture grass. J Exp Bot. 2023; 74(6):2127-2145. PMC: 10084810. DOI: 10.1093/jxb/erad021. View

Grosskinsky D, Svensgaard J, Christensen S, Roitsch T . Plant phenomics and the need for physiological phenotyping across scales to narrow the genotype-to-phenotype knowledge gap. J Exp Bot. 2015; 66(18):5429-40. DOI: 10.1093/jxb/erv345. View

Gould B, McCouch S, Geber M . De Novo Transcriptome Assembly and Identification of Gene Candidates for Rapid Evolution of Soil Al Tolerance in Anthoxanthum odoratum at the Long-Term Park Grass Experiment. PLoS One. 2015; 10(7):e0124424. PMC: 4493143. DOI: 10.1371/journal.pone.0124424. View

Nagel K, Putz A, Gilmer F, Heinz K, Fischbach A, Pfeifer J . GROWSCREEN-Rhizo is a novel phenotyping robot enabling simultaneous measurements of root and shoot growth for plants grown in soil-filled rhizotrons. Funct Plant Biol. 2020; 39(11):891-904. DOI: 10.1071/FP12023. View

Manley M . Near-infrared spectroscopy and hyperspectral imaging: non-destructive analysis of biological materials. Chem Soc Rev. 2014; 43(24):8200-14. DOI: 10.1039/c4cs00062e. View

Chen W, Tape K, Euskirchen E, Liang S, Matos A, Greenberg J . Impacts of Arctic Shrubs on Root Traits and Belowground Nutrient Cycles Across a Northern Alaskan Climate Gradient. Front Plant Sci. 2020; 11:588098. PMC: 7758488. DOI: 10.3389/fpls.2020.588098. View

Song Y, Sapes G, Chang S, Chowdhry R, Mejia T, Hampton A . Hyperspectral signals in the soil: Plant-soil hydraulic connection and disequilibrium as mechanisms of drought tolerance and rapid recovery. Plant Cell Environ. 2024; 47(11):4171-4187. DOI: 10.1111/pce.15011. View

Feeney D, Crawford J, Daniell T, Hallett P, Nunan N, Ritz K . Three-dimensional microorganization of the soil-root-microbe system. Microb Ecol. 2006; 52(1):151-8. DOI: 10.1007/s00248-006-9062-8. View

Petropoulos G, Vadrevu K, Xanthopoulos G, Karantounias G, Scholze M . A comparison of Spectral Angle Mapper and Artificial Neural Network classifiers combined with Landsat TM imagery analysis for obtaining burnt area mapping. Sensors (Basel). 2012; 10(3):1967-85. PMC: 3264462. DOI: 10.3390/s100301967. View

10.

Kruger M, Zemanek T, Wuttke D, Dinkel M, Serfling A, Bockmann E . Hyperspectral imaging for pest symptom detection in bell pepper. Plant Methods. 2024; 20(1):156. PMC: 11447932. DOI: 10.1186/s13007-024-01273-5. View

11.

Galloway A, Knox P, Krause K . Sticky mucilages and exudates of plants: putative microenvironmental design elements with biotechnological value. New Phytol. 2019; 225(4):1461-1469. DOI: 10.1111/nph.16144. View

12.

Smith A, Petersen J, Selvan R, Rasmussen C . Segmentation of roots in soil with U-Net. Plant Methods. 2020; 16:13. PMC: 7007677. DOI: 10.1186/s13007-020-0563-0. View

13.

Liu K, Yang M, Huang S, Lin C . Plant Species Classification Based on Hyperspectral Imaging a Lightweight Convolutional Neural Network Model. Front Plant Sci. 2022; 13:855660. PMC: 9044035. DOI: 10.3389/fpls.2022.855660. View

14.

Bodner G, Nakhforoosh A, Arnold T, Leitner D . Hyperspectral imaging: a novel approach for plant root phenotyping. Plant Methods. 2018; 14:84. PMC: 6169016. DOI: 10.1186/s13007-018-0352-1. View

15.

Goossens T, Geelen B, Pichette J, Lambrechts A, Van Hoof C . Finite aperture correction for spectral cameras with integrated thin-film Fabry-Perot filters. Appl Opt. 2018; 57(26):7539-7549. DOI: 10.1364/AO.57.007539. View

16.

Liu T, Zhao Y, Wang H, Wu W, Yang T, Zhang W . Harnessing UAVs and deep learning for accurate grass weed detection in wheat fields: a study on biomass and yield implications. Plant Methods. 2024; 20(1):144. PMC: 11412042. DOI: 10.1186/s13007-024-01272-6. View

17.

Fan X, Liu C, Liu S, Xie Y, Zheng L, Wang T . The Instrument Design of Lightweight and Large Field of View High-Resolution Hyperspectral Camera. Sensors (Basel). 2021; 21(7). PMC: 8037560. DOI: 10.3390/s21072276. View

18.

Jammer A, Akhtar S, Buchvaldt Amby D, Pandey C, Mekureyaw M, Bak F . Enzyme activity profiling for physiological phenotyping within functional phenomics: plant growth and stress responses. J Exp Bot. 2022; 73(15):5170-5198. DOI: 10.1093/jxb/erac215. View

19.

Schmidt J, Lowry C, Gaudin A . An Optimized Rhizobox Protocol to Visualize Root Growth and Responsiveness to Localized Nutrients. J Vis Exp. 2018; (140). PMC: 6235577. DOI: 10.3791/58674. View

20.

Amziane A, Losson O, Mathon B, Dumenil A, Macaire L . Reflectance Estimation from Multispectral Linescan Acquisitions under Varying Illumination-Application to Outdoor Weed Identification. Sensors (Basel). 2021; 21(11). PMC: 8196826. DOI: 10.3390/s21113601. View