The universal use of artificial intelligence in many aspects of human activity allows to shorten the time of activities performed from the design to the assumed objective of action. At the same time, the tasks performed are characterised by high precision and accuracy (Swaroop et al., 2023; Vinichenko et al., 2020). Systems supported by artificial intelligence are able to perform complex mathematical operations, thanks to which the results of calculations are efficient and free of errors (Gulwani, 2022; Wang and Zhao, 2022; Kasymova et al., 2023). The extensive development of deep neural networks followed the definition of the basic structure and learning algorithm of a specialised multilayer network, called U−Net (Ronneberger et al., 2015). Today, U−Net is the basic framework applied on a large scale in image processing (Benbahria et al., 2021; Lima et al., 2021; Reddy and Ghodke, 2022; Lee et al., 2023). In the monitoring of the natural environment, especially of air quality, the use of artificial intelligence is limited to the analysis of data obtained during chemical analyses and their forecasting (Ali et al., 2022; Neo et al., 2023; Soares et al., 2023). The presented paper presents an algorithm allowing to identify air pollution based on analysing the microphotos of the surface of a selected bioindicator – Pinus sylvestris L. needles, collected from locations with varying degrees of anthropopressure from the territory of Poland and Czech Republic. Pine needles, thanks to their diagnostic properties and wide geographical range, are commonly used in bioindication of the natural environment (Alaqouri et al., 2020; Chen et al., 2022; Maria et al., 2022). Analyses of the chemical composition and physicochemical properties are the subject of numerous papers in urban, industrial and natural zones (Holt et al., 2016; Kalugina et al., 2017; Polyakova et al., 2020; Jonczak et al., 2021; Zítková et al., 2021). In the activity carried out with the use of machine learning, an algorithm has been developed that is able to identify (distinguish) natural and artificial structures on the surface of needles, including; stomata responsible for gas exchange, mineral particles of natural and anthropogenic origin and ferruginous−silicate spherules.

Alaqouri, H., Genc, C.O., Aricak, B., Kuzmina, N., Menshikov, S., Cetin, M., 2020. The possibility of using scots pine (Pinus sylvestris L.) needles as biomonitor in the determination of heavy metal accumulation. Applied Ecology and Environmental Research, 18 (2): 3713-3727. DOI: https://doi.org/10.15666/aeer/1802_37133727.
Ali, A.N., Nassreddine, G., Younis, J., 2022. Air Quality prediction using Multinomial Logistic Regression. Journal of Computer Science and Technology Studies, 4 (2): 71-78. DOI: https://doi.org/10.32996/jcsts.2022.4.2.9.
Anderson, B.M., Wahid, K.A., Brock, K.K., 2021. Simple Python module for conversions between DICOM images and radiation therapy structures, masks, and prediction arrays. Practical Radiation Oncology, 11 (3): 226-229. DOI: https://doi.org/10.1016/j.prro.2021.02.003.
Benbahria, Z., Sebari, I·., Hajji, H., Smiej, M.F., 2021. Intelligent mapping of irrigated areas from Landsat 8 images using transfer learning. International Journal of Engineering and Geosciences, 6 (1): 40-50. DOI: https://doi.org/10.26833/ijeg.681312.
Chen, Y., Ning, Y., Bi, X., Liu, J., Yang, S., Liu, Z., Huang, W., 2022. Pine needles as urban atmospheric pollution indicators: Heavy metal concentrations and Pb isotopic source identification. Chemosphere, 296: 134043. DOI: https://doi.org/10.1016/j.chemosphere.2022.134043.
Fahmi, M.N., 2023. Implementasi mechine learning menggunakan Python Library: Scikit-Learn (supervised dan unsupervised learning). Sains Data Jurnal Studi Matematika Dan Teknologi, 1 (2): 87-96. DOI: https://doi.org/10.52620/sainsdata.v1i2.31.
Gulwani, S., 2022. AI-assisted programming: applications, user experiences, and neuro-symbolic techniques (keynote). Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering. DOI: https://doi.org/10.1145/3540250.3569444.
Holt, E., Kočan, A., Klánová, J., Assefa, A., Wiberg, K., 2016. Spatiotemporal patterns and potential sources of polychlorinated biphenyl (PCB) contamination in Scots pine (Pinus sylvestris) needles from Europe. Environmental Science and Pollution Research International, 23 (19): 19602-19612. DOI: https://doi.org/10.1007/s11356-016-7171-6.
Jonczak, J., Sut-Lohmann, M., Polláková, N., Parzych, A., Šimanský, V., Donovan, S., 2021. Bioaccumulation of potentially toxic elements by the needles of eleven pine species in low polluted area. Water, Air and Soil Pollution, 28: 232 . DOI: https://doi.org/10.1007/s11270-020-04959-3.
Kalugina, O.V., Mikhailova, T.A., Shergina, O.V., 2017. Pinus sylvestris as a bio-indicator of territory pollution from aluminum smelter emissions. Environmental Science and Pollution Research International, 24 (11): 10279-10291. DOI: https://doi.org/10.1007/s11356-017-8674-5.
Kasymova, T., Sydykova, M., Zhaparova, Z., 2023. The use of Artificial intelligence in mathematics: Scientific and social aspects. Bűlleten’ Nauki i Praktiki, 9 (6): 32-37. DOI: https://doi.org/10.33619/2414-2948/91/03.
Kejna, M., Sobota, I., Uscka-Kowalkowska, J., Wojtczak, H., 2021. Monitoring of small catchments in Poland under the Integrated Environmental Monitoring Programme: The functioning of the Struga Toruńska river agricultural catchment. In: M. Zeleňáková, K. Kubiak-Wójcicka, A.M. Negm, eds. Quality of water resources in Poland. Springer Water. Cham: Springer, pp. 347-372.
Korkmaz, F., 2023. U-Net##: A powerful novel architecture for medical image segmentation. In: R. Su, Y. Zhang, H. Liu, A. Frangi, eds. Medical imaging and computer-aided diagnosis. MICAD 2022. Lecture Notes in Electrical Engineering. Singapore: Springer, pp. 231-241.
Kostrzewski, A., Majewski, M., eds. 2021. Zintegrowany monitoring środowiska przyrodniczego: organizacja, system pomiarowy, metody badań, wytyczne do realizacji. Biblioteka Monitoringu Środowiska. Warszawa: Główny Inspektorat Ochrony Środowiska, 377 pp.
Lee, M., Wang, S., Pan, C., Chien, M., Li, W., Xu, J., Luo, C., Shiue, Y., 2023. Development of deep learning with RDA U-Net network for bladder cancer segmentation. Cancers, 15 (4): 1343. DOI: https://doi.org/10.3390/cancers15041343.
Lima, R., Pozo, A., Mendiburu, A., Santana, R., 2021. Automatic design of deep neural networks applied to image segmentation problems. In: T. Hu, N. Lourenço, E. Medvet, eds. Genetic Programming. EuroGP 2021. Lecture Notes in Computer Science, 12691. Cham: Springer, pp. 98-113.
Mahalaxmi, G., Donald, A.D., Srinivas, T.A.S., 2023. A short review of Python libraries and data science tools. South Asian Research Journal of Engineering and Technology, 5 (1): 1-5. DOI: https://doi.org/10.36346/sarjet.2023.v05i01.001.
Maria, G.M., Banciu, C., Vladimirescu, M., Paica, I.C., Manole, A., 2022. Structural modifications in black pine needles as potential biomarkers of environmental pollution. Carpathian Journal of Earth and Environmental Sciences, 17 (1): 111-118. DOI: https://doi.org/10.26471/cjees/2022/017/205.
Neo, E.X., Hasikin, K., Lai, K.W., Mokhtar, M.I., Azizan, M.M., Hizaddin, H.F., Razak, S.A., Yanto, N., 2023. Artificial intelligence-assisted air quality monitoring for smart city management. PeerJ. Computer Science, 9: e1306. DOI: https://doi.org/https://doi.org/10.7717/peerj-cs.1306.
Polyakova, G., Pashenova, N., Senashova, V., Podolyak, N., Kudryasheva, N., 2020. Pine stands as bioindicators of soil contamination with heavy metals. Environmental Science and Pollution Research, 27 (7): 7174-7186. DOI: https://doi.org/10.1007/s11356-019-07236-9.
Reddy, P.S., Ghodke, P.K., 2022. Image analysis using artificial intelligence in chemical engineering processes. In: S. Prateek, V. Abhishek, K.S. Prabhat, R. Virender, K. Ram, eds. Image processing and intelligent computing systems. Boca Raton: CRC Press eBooks, pp. 79-100. DOI: https://doi.org/10.1201/9781003267782-6.
Ronneberger, O., Fischer, P., Brox, T., 2015. U-NET: Convolutional networks for biomedical image segmentation. arXiv: 1505.04597. DOI: https://doi.org/10.48550/arxiv.1505.04597.
Soares, P.H., Monteiro, J.P., Gaioto, F.J., Ogiboski, L., Andrade, C.M.G., 2023. Use of association algorithms in air quality monitoring. Atmosphere, 14 (4): 648. DOI: https://doi.org/10.3390/atmos14040648.
Swaroop, S., Buçinca, Z., Doshi-Velez, F., 2023. Adaptive interventions for both accuracy and time in AI-assisted human decision making. arXiv: 2306.07458. DOI: https://doi.org/10.48550/arxiv.2306.07458.
Szwed, M., Kozłowski, R., 2022. Snow cover as an indicator of dust pollution in the area of exploitation of rock materials in the Świętokrzyskie Mountains. Atmosphere, 13 (3): 409. DOI: https://doi.org/10.3390/atmos13030409.
Szwed, M., Żukowski, W., Misztal, K., Kozłowski, R., 2023. High-energy transformations of fossil fuels in the cement industry. Energies, 16 (9): 3634. DOI: https://doi.org/10.3390/en16093634.
TIBCO Software Inc., 2017. Statistica (data analysis software system), version 13. Available from: http://statistica.io.
Vinichenko, M.V., Narrainen, G.S., Melnichuk, A.V., Chalid, P., 2020. The influence of artificial intelligence on human activities. In: A.V. Bogoviz, A.E. Suglobov, A.N. Maloletko, O.V. Kaurova, S.V. Lobova, eds. Frontier information technology and systems research in cooperative economics. Studies in systems, decision and control, vol 316. Cham: Springer, pp. 561-570. DOI: https://doi.org/10.1007/978-3-030-57831-2_60.
Wang, L., Zhao, L., 2022. Digital economy meets artificial intelligence: Forecasting economic conditions based on big data analytics. Journal of Mobile Information Systems: 7014874. DOI: https://doi.org/10.1155/2022/7014874.
Węgiel, A., Bielini, E., Polowy, K., 2018. Heavy metals accumulation in scots pine stands of different densities growing on not contaminated forest area (north-western Poland). Austrian Journal of Forest Science, 135 (3): 259-281.
Zítková, J., Hegrová, J., Keken, Z., Ličbinský, R., 2021. Impact of road salting on Scots pine (Pinus sylvestris) and Norway spruce (Picea abies). Ecological Engineering, 159: 106129. DOI: https://doi.org/10.1016/j.ecoleng.2020.106129.