IMPROVEMENT OF REMOTE SENSING METHODS OF THE SPREAD OF INVASIVE PLANT SPECIES IN THE CONTEXT OF ASSESSING POTENTIAL DAMAGE TO THE ENVIRONMENT AND AGRICULTURE
Abstract
Faifura V.V., Spivak I.Ya., Faifura V.V. IMPROVEMENT OF REMOTE SENSING METHODS OF THE SPREAD OF INVASIVE PLANT SPECIES IN THE CONTEXT OF ASSESSING POTENTIAL DAMAGE TO THE ENVIRONMENT AND AGRICULTURE
Purpose. The aim of the article is to increase the efficiency of methods of spread of invasive plant species remote sensing to assess potential economic damage to the environment and agriculture through the use of intelligent surveillance systems.
Methodology of research. The following methods were used in the study: monographic – for studying literature sources; machine learning method – for model training; three-way data split method for assessing model accuracy and statistical analysis for comparing recognition results; basic (traditional) methods for image enhancement; gradient image processing (Poisson mixing) – for image fusion.
Findings. A model for improving the efficiency of methods for remote recognition of the spread of invasive plant species was developed and proposed. The performance of the proposed model was compared with the model based on traditional image augmentation methods. It was found that the CAIPIS method, which is the basis of the model, achieves significantly higher results in detecting invasive plant species, especially when the data set is limited. In addition, the method helps to increase the reliability and generalization of deep-learning models for detecting the spread of invasive plant species. The CAIPIS method provides means to create more diverse and realistic training samples, which helps to improve the generalization ability of the deep learning model in detecting invasive plants in aerial imagery of agricultural fields and ecosystems obtained using unmanned aerial vehicles.
Originality. A new method for enhancing (augmenting) aerial images of crop fields is presented, which aims to improve the performance of invasive plant detection models by creating diverse and realistic training samples and increasing the variability of the training dataset to improve the performance of such models.
Practical value. The application of the aerial images enhancement (augmentation) method will increase the effectiveness of controlling the spread of invasive pests in ecosystems.
Key words: invasive species, phytoinvasion, augmentation, recognition, remote sensing.Keywords
Full Text:
References
Abduloieva, O.S. and Karpenko, N.I. (2012), “Justification of criteria for the invasive potential of alien plant species in Ukraine”, Chornomorskyi botanichnyi zhurnal, Vol. 8, no. 3, pp. 252-256.
Abduloieva, O., Karpenko, N. and Senchylo, O. (2008), “Justification of the “black list” of invasive plant species of Ukraine threatening biodiversity”, Visnyk Kyivskoho natsionalnoho universytetu imeni Tarasa Shevchenka. Seriia: Biolohiia, no. 52-53, pp. 108-110.
Adamiv, S.S. (2021), “Adventitious plant species in Ternopil region”, Almanakh nauky, no. 2(47), pp. 52-55.
Burda, R.I. (2006), “Phytoinvasions in agroecosystems. Synanthropization of vegetation cover of Ukraine”, Synantropizatsiia roslynnoho pokryvu Ukrainy, pp. 34-37.
Burda, R.I., Pashkevych, N.A., Boiko, H.V. and Fitsailo, T.V. (2015), Chuzhoridni vydy okhoronnykh flor Lisostepu Ukrainy [Alien species of protective flora of the Forest Steppe of Ukraine], Naukova dumka, Kyiv, Ukraine, 116 p.
Zavialova, L.V. (2017), “Types of invasive plants dangerous for the natural phytodiversity of the objects of the nature reserve fund of Ukraine”, Biolohichni systemy, Vol. 9, Iss. 1, pp. 87-107.
Zavialova, L. (2019), “Review of adventitious plant research methods”, GEO&BIO, Vol. 18, pp. 64-76.
Mariushkina, V.Ya., Hrytsenko V.V. and Didyk, N.P. (2006), “Comparative adaptive strategy of invasive and indigenous species”, Ukrainskyi fitotsenolohichnyi zbirnyk, Ser. S, Iss. 24, pp. 103-109.
Pokozii, Y.T. (Ed.), Pysarenko, V.M., Dovhan, S.V. et al. (2010), Monitorynh shkidnykiv silskohospodarskykh kultur [Monitoring of pests of agricultural crops], textbook, Ahrarna osvita, Kyiv, Ukraine, 223 p.
Mosiakin, A.S. (2012), “Modern methods of biological control (biological regulation) of the activity of invasive plants: examples and prospects of application”, Naukovi osnovy zberezhennia biotychnoi riznomanitnosti, Vol. 3(10), no. 1, pp. 93-109.
“National report on the state of the natural environment in Ukraine in 2021”, available at: https://mepr.gov.ua/wp-content/uploads/2023/01/Natsdopovid-2021-n.pdf (access date January 30, 2023).
Protopopova, V. and Shevera, M. (2012), “Phytoinvasions. II. Analysis of the main classifications, schemes and models”, Promyshlennaia botanika, Iss. 12, pp. 88-95.
Chorna, H.A. “Reproductive biology of invasive species of higher aquatic flora”, available at: https://dspace.udpu.edu.ua/bitstream/6789/3012/1/chorna_%D0%A5%D0%B0%D1%80%D0%BA%D1%96%D0%B2.pdf (access date January 30, 2023).
Shuvar, I.A. (Ed.), Hudz, V.P. and Shuvar, A.I. (2013), Osoblyvo nebezpechni roslyny Ukrainy [Especially dangerous plants of Ukraine], tutorial, “Tsentr uchbovoi literatury”, Kyiv, Ukraine, 192 p.
Hamida, Ben A., Benoit, A. and Lambert, P. (2018), “3-D Deep Learning Approach for Remote Sensing Image Classification”. IEEE Transactions on Geoscience and Remote Sensing, no.56(8), pp. 4420-4434.
Buslaev, A., Parinov, A. and Khvedchenya, E. (2018), “Albumentations: Fast and flexible image augmentations”, Information, no.11(2), pp. 125.
Cao, C., Zhou, F. and Dai, Y. (2022), “A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability”, ArXiv.
Dwibedi, D., Misra, I. and Hebert, M. (2017), “Cut, Paste and Learn: Surprisingly Easy Synthesis for Instance Detection”, ArXiv.
Hao, X., Liu, L. and Yang, R. (2023), “A Review of Data Augmentation Methods of Remote Sensing Image Target Recognition”, Remote Sensing, no.15(3), pp.827.
Lameski, P., Zdravevski, E. and Trajkovik, V. (2017), “Weed Detection Dataset with RGB Images Taken Under Variable Light Conditions”, In Smart Innovations in Communication and Computational Sciences, no. 9, pp. 112-119.
Sankaran, S., Khot, L. and Espinoza, C. (2015), “Low-altitude, high-resolution aerial imaging systems for row and field crop phenotyping: A review”, European Journal of Agronomy, no. 70, pp. 112-123.
Shorten, C. and Khoshgoftaar, T. (2019), “A survey on Image Data Augmentation for Deep Learning”, Journal of Big Data, no. 6(1), pp. 1-48.
Yang, Z., Fan, Z. and Niu, C. (2023), “Development of Invasive Plant Recognition System Based on Deep Learning”, Journal of Advances in Mathematics and Computer Science, no. 38(6), pp. 39–53.
Zhu, X., Tuia, D. and Mou, L. (2017), “Deep learning in remote sensing: A review”, IEEE Geoscience and Remote Sensing Magazine, no. 5(4), pp. 8-36.
DOI: https://doi.org/10.37332/2309-1533.2023.1.16
Refbacks
- There are currently no refbacks.
INNOVATIVE ECONOMY 2006 - 2024