Identification of representatives of the genus Pulsatilla (Ranunculaceae) and their hybrids using convolutional neural networks
UDC 582.675.1+57.087.1
Keywords:
convolutional neural networks, Google Teachable Machine, hybrid, machine learning, Personal Image Classifier, Pulsatilla multifida, Pulsatilla turczaninovii
Abstract
The presence of a limited number of reliable morphological features and a high level of interspecific hybridization in representatives of the genus Pulsatilla Mill. complicates their identification. In this study, the authors made a successful attempt to identify hybrids using various artificial intelligence tools. The initial data included 50 images of basal leaf blades for P. multifida, P. turczaninovii, and 8 for hybrid plants. An established computer vision approach to solving the classification problem using pre-trained convolutional neural networks was applied. First, classifiers based on the ResNet50 model were trained, the F1-score for which was 0.99. Then, it was shown that tools such as Google Teachable Machine (TM) and Personal Image Classifier (PIC) can be used for rapid prototyping of such solutions with virtually no knowledge of artificial intelligence technologies and programming skills. All test samples of P. turczaninovii and P. multifida were classified correctly.
Downloads
Download data is not yet available.
References
Aichele D., Schwegler H.-W. 1957. Die taxonomie der Gattung Pulsatilla. Feddes Repert. 60: 1–230.
Baltacıoğlu C. 2024. Prediction of apple drying level by machine learning and electronic nose. Acta Alimentaria 53(4): 659–672.
Chen J., Yang W., Tan G., Tian C., Wang H., Zhou J., Liao H. 2022. Prediction of the taxonomical classification of the Ranunculaceae family using a machine learning method. New J. Chem. 46(11): 5150–5161.
Cheng L., Zhang M., Zhang P., Song Z., Ma Z., Qu H. 2008. Silver complexation and tandem mass spectrometry for differentiation of triterpenoid saponins from the roots of Pulsatilla chinensis (Bunge) Regel. Rapid Commun. Mass Spectrom 22: 3783–3790. https://doi.org/10.1002/rcm.3801
Choudhary M., Sentil S., Jones J. B., Paret M. L. 2023. Non-coding deep learning models for tomato biotic and abiotic stress classification using microscopic images. Front. Plant Sci. 14: 1–13.
Fedasyuk D., Marusenkova T., Hura Y. 2023. Architecture of mobile application for real-time calculation of fruit and vegetable mass-to-volume ratio. In: 18th International Conference on Computer Science and Information Technologies (CSIT) (Lviv, October 19–21, 2023). Lviv: IEEE. Pp. 1–4.
Forchhammer S., Abu-Ghazaleh A., Metzler G., Garbe C., Eigentler T. 2022. Development of an image analysis-based prognosis score using google’s teachable machine in Melanoma. Cancers 14(9): 2243.
Google Teachable Machine [2025]. URL: https://teachablemachine.withgoogle.com/train/image (Accessed 28 February 2025).
Grey-Wilson C. 2014. Pasque-Flowers. The genus Pulsatilla. Norfolk: “Barnwell Print”. 216 pp.
Hassan S. M., Maji A. K., Jasiński M., Leonowicz Z., Jasińska E. 2021. Identification of plant-leaf diseases using CNN and transfer-learning approach. Electronics 10(12): 1388.
He K., Zhang X., Ren S., Sun J. 2015. Deep residual learning for image recognition. Tech. report.: 770–778. https://doi.org/10.48550/arXiv.1512.03385
Ibrahim N. M., Gabr D. G. I., Rahman A. U., Dash S., Nayyar A. 2022. A deep learning approach to intelligent fruit identification and family classification. Multimed. Tool. Appl. 81(19): 27783–27798.
ImageNet [2025]. Stanford Vision Lab, Stanford University, Princeton University. URL: https://www.image-net.org/ (Accessed 20 June 2025).
Kim S., Seo M., Laptev I., Cho M., Kwak S. 2019. Deep metric learning beyond binary supervision. In: Conference on Computer Vision and Pattern Recognition (Long Beach, June 15–20, 2019). Long Beach: IEEE. Pp. 2283–2292.
Koklu M., Unlersen M. F., Ozkan I. A., Aslan M. F., Sabanci K. 2022. A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement. 188: 110425.
Kozan H. İ., Akyürek H. A. 2025. Efficient and rapid classification of various maize seeds using transfer learning and advanced AI techniques. ASEAN J. Sci. Tech. Report. Online 28(1): e255200. https://doi.org/10.55164/ajstr.v28i1.255200
Li Q.-J., Wang X., Wang J.-R., Su N., Zhang L., Ma Y.-P., Chang Z.-Y.., Zhao L., Potter D. 2019. Efficient identification of Pulsatilla (Ranunculaceae) using DNA barcodes and micro-morphological characters. Front. Plant Sci. 10: 1196. https://doi.org/10.3389/fpls.2019.01196
Ling Y., Lin Z., Zha W., Lian T., You S. 2016. Rapid detection and characterisation of triterpene saponins from the root of Pulsatilla chinensis (Bunge) Regel by HPLC-ESIQTOF-MS/MS. Phytochem. 27: 174–183. https://doi.org/10.1002/pca.2613
Malahina E. A. U., Saitakela M., Bulan S. J., Lamabelawa M. I. J., Belutowe Y. S. 2024. Teachable machine: optimization of herbal plant image classification based on epoch value, batch size and learning rate. J. Appl. Data Sci. 5(2): 532–545.
Odabas M. S., Şenyer N., Saka S. O. 2024. Classification of apple diseases and pests using the Google.com Powered Teachable Machine. JAFAG 41(2): 66–71.
Pang B., Nijkamp E., Wu Y. N. 2020. Deep learning with tensorflow: A review. J. Educ. Behav. Stat. 45(2): 227–248.
Personal Image Classifier [2025]. URL: https://classifier.appinventor.mit.edu/oldpic/ (Accessed 28 February 2025).
Пунина Е. О., Михайлова Ю. В., Шнеер В. С., Крапивская Е. Е., Мачс Э. М., Родионов А. В. Внутригеномный полиморфизм внутренних транскрибируемых спейсеров 35S рДНК (ITS) у трёх видов и трёх межвидовых гибридов Pulsatilla (Ranunculaceae) // Turczaninowia, 2024. Т. 27, № 4. С. 67–85. https://doi.org/10.14258/turczaninowia.27.4.8
Rahman N. A. A., Rahman R. M. P., Abd R. F., Hasan Z., Izaham R. M. A. R. 2022. Scan de microbes using MIT app inventor. Hum. En. Tech. 1(2): 56–63.
ResNet50 [2025]. In: PyTorch Foundation – Linux Foundation. URL: https://pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html) (Accessed 20 June 2025).
Rezaei D., Mohseni F. 2024. MIT App Inventor: A tool for enhancing technological pedagogical content knowledge. IJVLMS 15(1): 107–115.
Selvaraju R. R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. 2020. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128: 336–359. https://doi.org/10.1007/s11263-019-01228-7
Shorten C., Khoshgoftaar T. M. 2019. A survey on image data augmentation for deep learning. J. Big Data 6(1): 1–48. https://doi.org/10.1186/s40537-019-0197-0
Sramko G., Laczkó L., Volkova P. A., Bateman R. M., Mlinarec J. 2019. Evolutionary history of the Pasque-flowers (Pulsatilla, Ranunculaceae): Molecular phylogenetics, systematics and rDNA evolution. Mol. Phylogenet. Evol. 135: 45–61. https://doi.org/10.1016/j.ympev.2019.02.015
Степанов Н. В. Заметки о некоторых видах Pulsatilla L. (Ranunculaceae) из приенисейских Саян // Сист. зам. Герб. Томск. ун-та, 2014. Т. 109. С. 6–19.
Suh S. Y., An W. G. 2017. Systems pharmacological approach of Pulsatilla radix on treating сrohn's disease. Evid. Based Complement. Alternat. Med. 2017: 1–21. https://doi.org/10.1155/2017/4198035
Tamura M. A. 1991. New classification of the family Ranunculaceae 2. Acta Phytotax. Geobot. 42(2): 177−187.
Valuyskikh O. E., Teteryuk L. V., Pylina Y. I., Sushentsov O. E., Martynenko N. A., Shadrin D. M. 2020. Phylogenetic relationships and status of taxa of Pulsatilla uralensis and P. patens s. str. (Ranunculaceae) in north-eastern European Russia. PhytoKeys 162: 113–130. https://doi.org/10.3897/phytokeys.162.53361
Wang X., Fan F., Cao Q. 2016. Modified Pulsatilla decoction attenuates oxazolone-induced colitis in mice through suppression of inflammation and epithelial barrier disruption. Mol. Med. Rep. 14: 1173–1179. https://doi.org/10.3892/mmr.2016.5358
Wei T. J., Chang S. W., Abdul-Kareem S., Yap H. J., Yong K. T. 2018. Deep learning for plant species classification using leaf vein morphometric. IEEE/ACM T Comput. BI 17(1): 82–90.
Xenakis A., Papastergiou G., Gerogiannis V. C., Stamoulis G. 2020. Applying a convolutional neural network in an IoT robotic system for plant disease diagnosis. In: 11th International Conference on Information, Intelligence, Systems and Applications. Los Alamitos, IISA. Pp. 1–8.
Xu Q.-M., Shu Z., He W.-J., Chen L.-Y., Yang S.-L., Yang G., Liu Y.-L., Li X.-R. 2012. Antitumor activity of Pulsatilla chinensis (Bunge) Regel saponins in human liver tumor 7402 cells in vitro and in vivo. Phytomedicine 19: 293–300. https://doi.org/10.1016/j.phymed.2011.08.066
Зайков В. Ф., Кечайкин А. А., Куцев М. Г., Дорофеев В. И., Синицына Т. А., Каракулов А. В., Анисимов А. В., Баткин А. А., Панкратов С. Ю., Чупина И. С., Шестаков И. А., Колтунова А. М., Ахметов А. Е., Шмаков А. И. Pulsatilla chemalensis (Ranunculaceae) – новый для науки нотовид с Алтая // Turczaninowia, 2025. Т. 28, № 2. С. 127–138. https://doi.org/10.14258/turczaninowia.28.2.13
Зайков В. Ф., Кечайкин А. А., Скапцов М. В., Смирнов С. В., Дорофеев В. И., Анисимов А. В., Баткин А. А., Панкратов С. Ю., Шмаков А. И. Ревизия серии Bungeanae рода Pulsatilla (Ranunculaceae) на основе морфологических и молекулярно-генетических данных // Turczaninowia, 2024. Т. 27, № 2. С. 71–85. https://doi.org/10.14258/turczaninowia.27.2.9
Zamels A., Paegle B. 1927. Untersuchungen uber den anatomischen bau der blattstiele in der Gattung Pulsatilla Tourn. Acta Horti Bot. Univ. Latv. 2: 133–164.
Baltacıoğlu C. 2024. Prediction of apple drying level by machine learning and electronic nose. Acta Alimentaria 53(4): 659–672.
Chen J., Yang W., Tan G., Tian C., Wang H., Zhou J., Liao H. 2022. Prediction of the taxonomical classification of the Ranunculaceae family using a machine learning method. New J. Chem. 46(11): 5150–5161.
Cheng L., Zhang M., Zhang P., Song Z., Ma Z., Qu H. 2008. Silver complexation and tandem mass spectrometry for differentiation of triterpenoid saponins from the roots of Pulsatilla chinensis (Bunge) Regel. Rapid Commun. Mass Spectrom 22: 3783–3790. https://doi.org/10.1002/rcm.3801
Choudhary M., Sentil S., Jones J. B., Paret M. L. 2023. Non-coding deep learning models for tomato biotic and abiotic stress classification using microscopic images. Front. Plant Sci. 14: 1–13.
Fedasyuk D., Marusenkova T., Hura Y. 2023. Architecture of mobile application for real-time calculation of fruit and vegetable mass-to-volume ratio. In: 18th International Conference on Computer Science and Information Technologies (CSIT) (Lviv, October 19–21, 2023). Lviv: IEEE. Pp. 1–4.
Forchhammer S., Abu-Ghazaleh A., Metzler G., Garbe C., Eigentler T. 2022. Development of an image analysis-based prognosis score using google’s teachable machine in Melanoma. Cancers 14(9): 2243.
Google Teachable Machine [2025]. URL: https://teachablemachine.withgoogle.com/train/image (Accessed 28 February 2025).
Grey-Wilson C. 2014. Pasque-Flowers. The genus Pulsatilla. Norfolk: “Barnwell Print”. 216 pp.
Hassan S. M., Maji A. K., Jasiński M., Leonowicz Z., Jasińska E. 2021. Identification of plant-leaf diseases using CNN and transfer-learning approach. Electronics 10(12): 1388.
He K., Zhang X., Ren S., Sun J. 2015. Deep residual learning for image recognition. Tech. report.: 770–778. https://doi.org/10.48550/arXiv.1512.03385
Ibrahim N. M., Gabr D. G. I., Rahman A. U., Dash S., Nayyar A. 2022. A deep learning approach to intelligent fruit identification and family classification. Multimed. Tool. Appl. 81(19): 27783–27798.
ImageNet [2025]. Stanford Vision Lab, Stanford University, Princeton University. URL: https://www.image-net.org/ (Accessed 20 June 2025).
Kim S., Seo M., Laptev I., Cho M., Kwak S. 2019. Deep metric learning beyond binary supervision. In: Conference on Computer Vision and Pattern Recognition (Long Beach, June 15–20, 2019). Long Beach: IEEE. Pp. 2283–2292.
Koklu M., Unlersen M. F., Ozkan I. A., Aslan M. F., Sabanci K. 2022. A CNN-SVM study based on selected deep features for grapevine leaves classification. Measurement. 188: 110425.
Kozan H. İ., Akyürek H. A. 2025. Efficient and rapid classification of various maize seeds using transfer learning and advanced AI techniques. ASEAN J. Sci. Tech. Report. Online 28(1): e255200. https://doi.org/10.55164/ajstr.v28i1.255200
Li Q.-J., Wang X., Wang J.-R., Su N., Zhang L., Ma Y.-P., Chang Z.-Y.., Zhao L., Potter D. 2019. Efficient identification of Pulsatilla (Ranunculaceae) using DNA barcodes and micro-morphological characters. Front. Plant Sci. 10: 1196. https://doi.org/10.3389/fpls.2019.01196
Ling Y., Lin Z., Zha W., Lian T., You S. 2016. Rapid detection and characterisation of triterpene saponins from the root of Pulsatilla chinensis (Bunge) Regel by HPLC-ESIQTOF-MS/MS. Phytochem. 27: 174–183. https://doi.org/10.1002/pca.2613
Malahina E. A. U., Saitakela M., Bulan S. J., Lamabelawa M. I. J., Belutowe Y. S. 2024. Teachable machine: optimization of herbal plant image classification based on epoch value, batch size and learning rate. J. Appl. Data Sci. 5(2): 532–545.
Odabas M. S., Şenyer N., Saka S. O. 2024. Classification of apple diseases and pests using the Google.com Powered Teachable Machine. JAFAG 41(2): 66–71.
Pang B., Nijkamp E., Wu Y. N. 2020. Deep learning with tensorflow: A review. J. Educ. Behav. Stat. 45(2): 227–248.
Personal Image Classifier [2025]. URL: https://classifier.appinventor.mit.edu/oldpic/ (Accessed 28 February 2025).
Пунина Е. О., Михайлова Ю. В., Шнеер В. С., Крапивская Е. Е., Мачс Э. М., Родионов А. В. Внутригеномный полиморфизм внутренних транскрибируемых спейсеров 35S рДНК (ITS) у трёх видов и трёх межвидовых гибридов Pulsatilla (Ranunculaceae) // Turczaninowia, 2024. Т. 27, № 4. С. 67–85. https://doi.org/10.14258/turczaninowia.27.4.8
Rahman N. A. A., Rahman R. M. P., Abd R. F., Hasan Z., Izaham R. M. A. R. 2022. Scan de microbes using MIT app inventor. Hum. En. Tech. 1(2): 56–63.
ResNet50 [2025]. In: PyTorch Foundation – Linux Foundation. URL: https://pytorch.org/vision/main/models/generated/torchvision.models.resnet50.html) (Accessed 20 June 2025).
Rezaei D., Mohseni F. 2024. MIT App Inventor: A tool for enhancing technological pedagogical content knowledge. IJVLMS 15(1): 107–115.
Selvaraju R. R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. 2020. Grad-CAM: Visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128: 336–359. https://doi.org/10.1007/s11263-019-01228-7
Shorten C., Khoshgoftaar T. M. 2019. A survey on image data augmentation for deep learning. J. Big Data 6(1): 1–48. https://doi.org/10.1186/s40537-019-0197-0
Sramko G., Laczkó L., Volkova P. A., Bateman R. M., Mlinarec J. 2019. Evolutionary history of the Pasque-flowers (Pulsatilla, Ranunculaceae): Molecular phylogenetics, systematics and rDNA evolution. Mol. Phylogenet. Evol. 135: 45–61. https://doi.org/10.1016/j.ympev.2019.02.015
Степанов Н. В. Заметки о некоторых видах Pulsatilla L. (Ranunculaceae) из приенисейских Саян // Сист. зам. Герб. Томск. ун-та, 2014. Т. 109. С. 6–19.
Suh S. Y., An W. G. 2017. Systems pharmacological approach of Pulsatilla radix on treating сrohn's disease. Evid. Based Complement. Alternat. Med. 2017: 1–21. https://doi.org/10.1155/2017/4198035
Tamura M. A. 1991. New classification of the family Ranunculaceae 2. Acta Phytotax. Geobot. 42(2): 177−187.
Valuyskikh O. E., Teteryuk L. V., Pylina Y. I., Sushentsov O. E., Martynenko N. A., Shadrin D. M. 2020. Phylogenetic relationships and status of taxa of Pulsatilla uralensis and P. patens s. str. (Ranunculaceae) in north-eastern European Russia. PhytoKeys 162: 113–130. https://doi.org/10.3897/phytokeys.162.53361
Wang X., Fan F., Cao Q. 2016. Modified Pulsatilla decoction attenuates oxazolone-induced colitis in mice through suppression of inflammation and epithelial barrier disruption. Mol. Med. Rep. 14: 1173–1179. https://doi.org/10.3892/mmr.2016.5358
Wei T. J., Chang S. W., Abdul-Kareem S., Yap H. J., Yong K. T. 2018. Deep learning for plant species classification using leaf vein morphometric. IEEE/ACM T Comput. BI 17(1): 82–90.
Xenakis A., Papastergiou G., Gerogiannis V. C., Stamoulis G. 2020. Applying a convolutional neural network in an IoT robotic system for plant disease diagnosis. In: 11th International Conference on Information, Intelligence, Systems and Applications. Los Alamitos, IISA. Pp. 1–8.
Xu Q.-M., Shu Z., He W.-J., Chen L.-Y., Yang S.-L., Yang G., Liu Y.-L., Li X.-R. 2012. Antitumor activity of Pulsatilla chinensis (Bunge) Regel saponins in human liver tumor 7402 cells in vitro and in vivo. Phytomedicine 19: 293–300. https://doi.org/10.1016/j.phymed.2011.08.066
Зайков В. Ф., Кечайкин А. А., Куцев М. Г., Дорофеев В. И., Синицына Т. А., Каракулов А. В., Анисимов А. В., Баткин А. А., Панкратов С. Ю., Чупина И. С., Шестаков И. А., Колтунова А. М., Ахметов А. Е., Шмаков А. И. Pulsatilla chemalensis (Ranunculaceae) – новый для науки нотовид с Алтая // Turczaninowia, 2025. Т. 28, № 2. С. 127–138. https://doi.org/10.14258/turczaninowia.28.2.13
Зайков В. Ф., Кечайкин А. А., Скапцов М. В., Смирнов С. В., Дорофеев В. И., Анисимов А. В., Баткин А. А., Панкратов С. Ю., Шмаков А. И. Ревизия серии Bungeanae рода Pulsatilla (Ranunculaceae) на основе морфологических и молекулярно-генетических данных // Turczaninowia, 2024. Т. 27, № 2. С. 71–85. https://doi.org/10.14258/turczaninowia.27.2.9
Zamels A., Paegle B. 1927. Untersuchungen uber den anatomischen bau der blattstiele in der Gattung Pulsatilla Tourn. Acta Horti Bot. Univ. Latv. 2: 133–164.
Published
2025-10-11
How to Cite
Zaikov V. F., Kutsev M. G., Tikhomirova Z. V., Kozlov D. Y. Identification of representatives of the genus Pulsatilla (Ranunculaceae) and their hybrids using convolutional neural networks // Turczaninowia, 2025. Vol. 28, № 3. P. 96–105 DOI: 10.14258/turczaninowia.28.3.10. URL: https://turczaninowia.asu.ru/article/view/18004.
Section
Science articles
Turczaninowia is a golden publisher, as we allow self-archiving, but most importantly we are fully transparent about your rights.
Authors may present and discuss their findings ahead of publication: at biological or scientific conferences, on preprint servers, in public databases, and in blogs, wikis, tweets, and other informal communication channels.
Turczaninowia allows authors to deposit manuscripts (currently under review or those for intended submission to Turczaninowia) in non-commercial, pre-print servers such as ArXiv.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
