Hostname: page-component-68c7f8b79f-8spss Total loading time: 0 Render date: 2025-12-19T10:06:16.166Z Has data issue: false hasContentIssue false
  • English
  • Français

Artificial intelligence-based classification of flower colour polymorphism for conservation and genetic resource management of Tecomella undulata (Sm) Seem

Published online by Cambridge University Press:  09 December 2025

Manish Mathur  and
Preet Mathur Open the ORCID record for Preet Mathur [Opens in a new window]
Manish Mathur
Affiliation:
ICAR - Central Arid Zone Research Institute, Jodhpur, RJ, India
Preet Mathur*
Affiliation:
Department of Computer Science, Thapar Institute of Engineering and Technology, Patiala, PB, India
*
Corresponding author: Preet Mathur; Email: preetm9535@gmail.com
Get access Rights & Permissions [Opens in a new window]

Abstract

Flower colour is a key trait shaping pollination, reproduction and plant–environment interactions. In arid ecosystems, it may also signal adaptations to heat and (Ultraviolet) UV stress. Tecomella undulata, a threatened keystone tree of the Indian Desert, exhibits striking flower colour polymorphism with yellow, orange and red morphs. This study tested whether artificial intelligence (AI) can reliably classify these morphs, thereby supporting conservation efforts. Field surveys were conducted across natural populations in the Thar Desert. An accessible no-code AI platform (Google Teachable Machine) was used for supervised classification of flower and tree images, with unsupervised clustering applied for validation. The AI classifier achieved high accuracy in distinguishing morphs at both flower and tree scales. Morphs showed consistent separation, with orange functioning as an intermediate form. Despite red morphs being more frequent, the presence of yellow and orange morphs contributes essential functional diversity important for pollinator interactions and reproductive resilience. This study demonstrates that no-code AI provides an effective, scalable approach to documenting intraspecific variation in threatened species. By enabling rapid and reliable identification of flower colour morphs, the approach offers practical applications for ex situ conservation, restoration and morph-aware biodiversity management in T. undulata and other arid-zone trees.

Keywords

digital phenotypingflower colour polymorphismmachine learning classificationplant genetic resourcesTecomella undulata

Information

Type
Research Article
Information
Plant Genetic Resources , First View , pp. 1 - 10
Copyright
© The Author(s), 2025. Published by Cambridge University Press on behalf of National Institute of Agricultural Botany.

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Albor, C, Ashman, TL, Stanley, AM, Martel, C and Arceo-Gomez, G (2022) Flower color and flowering phenology mediate plant–pollinator interaction assembly in a diverse co-flowering community. Functional Ecology 36(10), 2456–2468. https://doi.org/10.1111/1365-2435.14142CrossRefGoogle Scholar
Arshad, F, Waheed, M, Fatima, K, Jarim, N, Iqbal, M, Fatmia, K and Umbreen, S (2022) Predicting the suitable current and future potential distribution of the native endangered tree Tecomella undulata (Sm.) Seem. in Pakistan. Sustainability 14, 7215. https://doi.org/10.3390/su14127215CrossRefGoogle Scholar
Carne, M, Luccioni, A, Ou, A and Tao, C (2020) Teachable machine: Approachable web-based tool for exploring machine learning classification. In Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3334480.3382839CrossRefGoogle Scholar
Caruso, CM, Eisen, KE, Martin, RA and Sletvold, N (2010) A meta-analysis of the selection on floral traits in animal-pollinated plants. Evolution 64(2), 370–385. https://doi.org/10.1111/evo.13639Google Scholar
Chen, W (2024) Exploring the application of K-means machine learning algorithm in fruit classification. Transaction on Computer Science and Intelligent System Research 5. https://doi.org/10.62051/gr86br34Google Scholar
Chhajer, S, Jukanti, AK, Bhatt, RK and Kalia, RK (2018) Genetic diversity studies in endangered desert teak [Tecomella undulata (Sm.) Seem] using arbitrary (RAPD), semi-arbitrary (ISSR) and sequence based (nuclear rDNA) markers. Trees 32, 1083–1101. https://doi.org/10.1007/s00468-018-1697-9CrossRefGoogle Scholar
Coetzee, A, Seymour, CL and Spottiswoode, CN (2021) Facilitation and competition shape a geographical mosaic of flower color polymorphism. Functional Ecology. https://doi.org/10.1111/1365-2435.13851CrossRefGoogle Scholar
Dalal, V, Bhuker, A and Kathwal, R (2025) Seed quality response of rohida (Tecomella undulata) to storage conditions and packaging types. Seed Research 53(1), 65–75. https://doi.org/10.56093/sr.v53i1.11CrossRefGoogle Scholar
Daneva, V, Johar, V, Pathak, S, Rawat, V and Khan, S (2024) Studies on reproductive behaviour and phenology cycle of Tecomella undulata (Sm.) Seem. Plant Science Today 11(3), 152–158. https://doi.org/10.14719/pst.2513Google Scholar
Dave, PR, Pansiniya, VB, Patel, BP, Trivedi, BH and Patel, YB (2024) Comparative analysis of customized CNN and teachable machine in plant leaves images. ShodhKosh: Journal of Visual and Performance Arts 5(2). https://doi.org/10.29121/shodhkosh.v5.i2.2024.5192Google Scholar
Davies, KM (2009) Modifying anthocyanin production in flowers. Trends in Plant Science 14(2), 73–79. https://doi.org/10.1016/j.tplants.2008.11.005Google Scholar
Feldmann, MI, Hardigan, MA, Famula, RA, Lopez, CM, Tabb, A, Cole, GC and Knapp, SJ (2020) Multi-dimensional machine learning approaches for fruit shape phenotyping in strawberry. GigaScience 9(5). https://doi.org/10.1093/gigascience/giaa030CrossRefGoogle ScholarPubMed
Hasan, RI, Yusuf, SM and Alzubaidi, L (2020) Review of the state of the art of deep learning for plant diseases: A broad analysis and discussion. Plants 9(10), 1302. https://doi.org/10.3390/plants9101302CrossRefGoogle ScholarPubMed
Holton, TA and Cornish, EC (1995) Genetics and biochemistry of anthocyanin biosynthesis. The Plant Cell 7(7), 1071–1083. https://doi.org/10.2307/3870058CrossRefGoogle ScholarPubMed
Kasajima, I (2019) Measuring plant colors. Plant Biotechnology (Tokyo) 36(2), 63–75. https://doi.org/10.5511/plantbiotechnology.19.0322aCrossRefGoogle ScholarPubMed
Li, J, Li, Y, Qiao, J, Li, L, Wang, X, Yao, J and Liao, G (2024) Automatic counting of rapeseed inflorescences using deep learning method and UAV RGB imagery. Frontiers in Plant Science 14, 1101143. https://doi.org/10.3389/fpls.2023.1101143CrossRefGoogle Scholar
Malahina, EAU, Saitakela, M, Bulan, SJ, Lambelawa, MIJ and Belutowe, YS (2024) Teachable Machine: Optimization of herbal plant image classification based on epoch value, batch size and learning rate. Journal of Applied Data Sciences 5(2), 532–545. https://doi.org/10.47738/jads.v5i2.206Google Scholar
Mathur, M and Mathur, P (2024) Ecological niche modelling of Tecomella undulata (Sm.) Seem: An endangered (A2a) tree species from arid and semi-arid environment imparts multiple ecosystem services. Tropical Ecology 65(2), 59–80. https://doi.org/10.1007/s42965-023-00311-yCrossRefGoogle Scholar
Negi, RS, Sharma, MK, Sharma, KC, Kshetrapal, S, Kothari, SL and Trivedi, PC (2011) Genetic diversity and variations in the endangered tree (Tecomella undulata) in Rajasthan. Indian Journal of Fundamental and Applied Life Science 1(1), 50–58. https://www.cibtech.org/J-LIFE-SCIENCES/PUBLICATIONS/2011/Vol%201%20No%201/9%20Negi%20et%20al.pdfGoogle Scholar
OriginLab Corporation (2022) Origin Pro Version 2022. Northampton, MA, USA: OriginLab Corporation itself.Google Scholar
Perez-Udell, RA, Udell, AT and Chang, SM (2023) An automated pipeline for supervised classification of petal color from citizen science photographs. Applications in Plant Sciences 11(1), e11505. https://doi.org/10.1002/aps3.11505CrossRefGoogle ScholarPubMed
Post, PC and Schlautman, MA (2020) Measuring Camellia petal color using a portable color sensor. Horticulturae 6(3), 53. https://doi.org/10.3390/horticulturae6030053CrossRefGoogle Scholar
Rausher, MD (2008) Evolutionary transitions in floral color. International Journal of Plant Sciences 169(1), 7–21. https://doi.org/10.1086/523358CrossRefGoogle Scholar
Saleem, MH, Potgieter, J and Arif, KM (2019) Plant disease detection and classification by deep learning. Plants 8(11), 468. https://doi.org/10.3390/plants8110468CrossRefGoogle ScholarPubMed
Salman, INA, Dener, E, Tzin, V and Seifan, M (2025) Plant fitness is shaped by cascading effects of aridity and drought on floral traits and pollination services. Agriculture Ecosystems and Environment 393, 109855. https://doi.org/10.1016/j.agee.2025.109855CrossRefGoogle Scholar
Singh, G, Bala, N, Mutha, S, Rathod, TR and Limba, NK (2012) Biomass production of Tecomella undulata agroforestry system in arid India. Biological Agriculture and Horticulture. https://doi.org/10.1080/01448765.2004.9755286Google Scholar
Singh, S, Dhyani, D, Yadav, AK and Rajkumar, S (2011) Flower color variations in gerbera (Gerbera jamesonii) population using image analysis. Indian Journal of Agricultural Sciences 81(12), 1130–1136.Google Scholar
Singh, VK, Barman, C and Tandon, R (2014) Nectar robbing positively influences the reproductive success of Tecomella undulata (Bignoniaceae). PLoS ONE 9(7), e102607. https://doi.org/10.1371/journal.pone.0102607CrossRefGoogle ScholarPubMed
Thampan, J, Srivastava, J, Saraf, PN and Samal, P (2025) Habitat distribution modelling to identify areas of high conservation value under climate change for an endangered arid land tree Tecomella undulata. Journal of Arid Environments 227, 105317. https://doi.org/10.1016/j.jaridenv.2025.105317CrossRefGoogle Scholar
Vaidya, P, McDurmon, A, Mattoon, E, Keefe, M, Carley, L, Lee, CR, Bingham, R and Anderson, JT (2018) Ecological causes and consequences of flower color polymorphism in a self-pollinating plant (Boechera stricta). New Phytologist 218(1), 380–392. https://doi.org/10.1111/nph.14998CrossRefGoogle Scholar
van der Kooi, CJ, Dyer, AG, Kevan, PG and Lunau, K (2019) Functional significance of the optical properties of flowers for visual signalling. Annals of Botany 123(2), 263–276. https://doi.org/10.1093/aob/mcy119CrossRefGoogle ScholarPubMed
Wehrens, R, Afonso, M, Fonteijn, H, Paula, J, Polder, G, Rijsbergen, M, van Hameren, G, Haegens, R, van den Helder, M and Zwinkels, H (2024) Determining flower colors from images using artificial intelligence. Euphytica. https://doi.org/10.1007/s10681-023-03258-2CrossRefGoogle Scholar
Zhao, P and Shin, BC (2023) Counting of flowers based on K-means clustering and watershed segmentation. Journal of the Korean Society for Industrial and Applied Mathematics 27(2), 146–159. https://doi.org/10.12941/jksiam.2023.27.146Google Scholar
Supplementary material: File

Mathur and Mathur supplementary material

Mathur and Mathur supplementary material
Download Mathur and Mathur supplementary material(File)
File 489 KB