Inteligentny system identyfikacji zanieczyszczenia powietrza = Intelligent air pollution identification system

Szwed, Mirosław

doi:0033-2143 (print)

Download

Title: Inteligentny system identyfikacji zanieczyszczenia powietrza = Intelligent air pollution identification system

Abstract:

The aim of the work is to develop an air pollution identification system using neural networks. The use of artificial intelligence (AI), which uses the analysis of surface images of selected air pollution indicators to build a machine learning algorithm, has enabled the development of a cheap and effective method for identifying hazardous substances. Scanning electron microscopy photos of two-year-old needles of Scots pine Pinus sylvestris L. from representative research catchments of the national network of Integrated Environmental Monitoring were used to build the model. Scanning electron microscopy photos were processed in a graphics program so that the particles classified based on size, shape and chemical composition had the same attribute. The layers made were an element necessary to develop a machine learning algorithm identifying pollutants divided into previously defined categories. The use of neural networks to build a self-learning algorithm allowed us to optimize the analysis of deposited contaminants imaged on the surface of pine needles. The developed system for identifying natural and anthropogenic particles in the form of categorized layers provides high level of prediction efficiency. Thanks to the use of multiple convolutional layers, the neural network captured the most important features from the image during training and then used them to predict segmentation masks of interesting objects. Based on the association of input pixels and the features extracted from them and the pixels of the real segmentation mask, algorithm adjusted its parameters to later recreate masks for completely new input data. The network response was at the level of 80%, which is the optimal result of the developed system.
;

References:

Ailon, N., Chazelle, B., Clarkson, K.L., Liu, D., Mulzer, W., & Seshadhri, C. (2011). Self‑Improving Algorithms. SIAM Journal on Computing, 40(2), 350‑375. https://doi.org/10.1137/090766437
Akimoto, H. (2003). Global air quality and pollution. Science, 302(5651), 1716‑1719. https://doi.org/10.1126/science.1092666
Alaimo, M.G., Dongarra, G., Melati, M.R., Monna, F., & Varrica, D. (2000). Recognition of environmental trace metal contamination using pine needles as bioindicators. The urban area of Palermo (Italy). Environmental Geology, 39(8), 914‑924. https://doi.org/10.1007/s002549900071
Allegrini, I., & Pirrone, N. (2007). 19 Global scale atmospheric pollution: a regional problem. W: R. Baudo, G. Tartari, & E. Vuillermoz (red.), Developments in earth surface processes, 10 (s. 145‑146). https://doi.org/10.1016/s0928‑2025(06)10019‑x
Arroyo, P., Gómez‑Suárez, J., Suárez, J.I., & Lozano, J. (2021). Low‑Cost Air Quality Measurement System Based on Electrochemical and PM Sensors with Cloud Connection. Sensors, 21(18), 6228.https://doi.org/10.3390/s21186228
Ayaz, M., Tasdemirci, E., Yuksel, H., & Aygul, V. (2018). Comprehensive study on automation of toxic gas measurement. Arabian Journal of Geosciences, 11(22). https://doi.org/10.1007/s12517‑018‑4066‑5
Benbahria, Z., Sebari, İ., 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. https://doi.org/10.26833/ijeg.681312
Bousiotis, D., Singh, A., Haugen, M., Beddows, D.C.S., Diez, S., Murphy, K.L., Edwards, P.M., Boies, A., Harrison, R.M., & Pope, F.D. (2021). Assessing the sources of particles at an urban background site using both regulatory instruments and low‑cost sensors - a comparative study. Atmospheric Measurement Techniques, 14(6), 4139‑4155. https://doi.org/10.5194/amt‑14‑4139‑2021
Cetina, K., Buenaposada, J.M., & Baumela, L. (2018). Multi‑class segmentation of neuronal structures in electron microscopy images. BMC Bioinformatics, 19(1). https://doi.org/10.1186/s12859‑018‑2305‑0
Chklovskii, D.B., Vitaladevuni, S., & Scheffer, L.K. (2010). Semi‑automated reconstruction of neural circuits using electron microscopy. Current Opinion in Neurobiology, 20(5), 667‑675. https://doi.org/10.1016/j.conb.2010.08.002
Chollet, F. (2021). Deep Learning with Python, Second Edition. Simon and Schuster.
Cindrić, I.J., Zeiner, M., Starčević, A., & Stingeder, G. (2018). Metals in pine needles: characterisation of bio‑indicators depending on species. International Journal of Environmental Science and Technology, 16(8), 4339‑4346. https://doi.org/10.1007/s13762‑018‑2096‑x
Eriksson, G., Jensen, S., Kylin, H., & Strachan, W. (1989). The pine needle as a monitor of atmospheric pollution. Nature, 341(6237), 42‑44. https://doi.org/10.1038/341042a0
Fan, A.M. (2014). Biomarkers in toxicology, risk assessment, and environmental chemical regulations. W: R.C. Gupta (red.), Elsevier eBooks (s. 1057‑1080). https://doi.org/10.1016/b978‑0‑12‑404630‑6.00064‑6
Fowler, D., Brimblecombe, P., Burrows, J., Heal, M.R., Grennfelt, P., Stevenson, D.S., Jowett, A., Nemitz, E., Coyle, M., Liu, X., Chang, Y., Fuller, G.W., Sutton, M.A., Klimont, Z., Unsworth, M.H., & Vieno, M. (2020). A chronology of global air quality. Philosophical Transactions - Royal Society. Mathematical, Physical and Engineering Sciences/Philosophical Transactions - Royal Society. Mathematical, Physical and Engineering Sciences, 378(2183), 20190314. https://doi.org/10.1098/rsta.2019.0314
Hagan, D.H., & Kroll, J.H. (2020). Assessing the accuracy of low‑cost optical particle sensors using a physics‑based approach. Atmospheric Measurement Techniques, 13, 6343‑6355. https://doi.org/10.5194/amt‑13‑6343‑2020
Hartmann, J., West, A.J., Renforth, P., Köhler, P., De La Rocha, C.L., Wolf‑Gladrow, D.A., Dürr, H.H., & Scheffran, J. (2013). Enhanced chemical weathering as a geoengineering strategy to reduce atmospheric carbon dioxide, supply nutrients, and mitigate ocean acidification. Reviews of Geophysics, 51(2), 113‑149. https://doi.org/10.1002/rog.20004
Huszar, P., Karlický, J., Marková, J., Nováková, T., Liaskoni, M., & Bartík, L. (2021). The regional impact of urban emissions on air quality in Europe: the role of the urban canopy effects. Atmospheric Chemistry and Physics, 21(18), 14309‑14332. https://doi.org/10.5194/acp‑21‑14309‑2021
Ikeno, H., Kumaraswamy, A., Kai, K., Wachtler, T., & Ai, H. (2018). A segmentation scheme for complex neuronal arbors and application to vibration sensitive neurons in the honeybee brain. Frontiers in Neuroinformatics, 12. https://doi.org/10.3389/fninf.2018.00061
Jiménez, E., Tapiador, F.J., & Sáez‑Martínez, F.J. (2014). Atmospheric pollutants in a changing environment: key issues in reactivity and monitoring, global warming, and health. Environmental Science and Pollution Research International, 22(7), 4789‑4792. https://doi.org/10.1007/s11356‑014‑3850‑3
Jones, C., Sayedhosseini, M., Ellisman, M., & Tasdizen, T. (2013). Neuron Segmentation in Electron Microscopy Images Using Partial Differential Equations. 2013 IEEE 10th International Symposium on Biomedical Imaging, San Francisco, CA, USA, 2013, 1457‑1460. https://doi.org/10.1109/ISBI.2013.6556809
Jones, C., Sayedhosseini, M., Ellisman, M., & Tasdizen, T. (2013). Neuron Segmentation in Electron Microscopy Images Using Partial Differential Equations. 2013 IEEE 10th International Symposium on Biomedical Imaging, San Francisco, CA, USA, 2013, 1457‑1460.https://doi.org/10.1109/ISBI.2013.6556809
Kabata‑Pendias, A., & Pendias, H. (1999). Biogeochemia pierwiastków śladowych. Warszawa: Wydawnictwo PWN.
Keywood, M., Paton‑Walsh, C., Lawrence, M., George, C., Formenti, P., Schofield, R., Cleugh, H., Borgford‑Parnell, N., & Capon, A. (2023). Atmospheric goals for sustainable development. Science, 379(6629), 246‑247. https://doi.org/10.1126/science.adg2495
Kingma, D.P., & Ba, J.L. (2014). Adam: A method for stochastic optimization. arXiv (Cornell University). https://doi.org/10.48550/arxiv.1412.6980
Konwencja LRTAP. 1979. Konwencja w sprawie transgranicznego zanieczyszczania powietrza na dalekie odległości, sporządzona w Genewie dnia 13 listopada 1979 r. (Dz.U. z 1985 r. Nr 60, poz. 311)
Kostrzewski, A., & Majewski, M. (2021). Zintegrowany monitoring środowiska przyrodniczego: organizacja, system pomiarowy, metody badań, wytyczne do realizacji. Warszawa: Biblioteka Monitoringu Środowiska.
Kostrzewski, A., Majewski, M., & Szpikowski, J. (2022). Współczesne przemiany naturalne i antropogeniczne środowiska przyrodniczego zlewni rzecznych i jeziornych. Storkowo: Biblioteka Monitoringu Środowiska.
Kozáková, J., Pokorná, P., Vodička, P., Ondráčková, L., Ondráček, J., Křůmal, K., Mikuška, P., Hovorka, J., Moravec, P., & Schwarz, J. (2018). The influence of local emissions and regional air pollution transport on a European air pollution hot spot. Environmental Science and Pollution Research International, 26(2), 1675‑692. https://doi.org/10.1007/s11356‑018‑3670‑y
Kozłowski, R., Szwed, M., Kozłowska, A., Przybylska, J., & Mach, T. (2024). Quality Management System in Air Quality Measurements for Sustainable Development. Sustainability, 16(17), 7537. https://doi.org/10.3390/su16177537
Kurenkov, A. (2020). A Brief History of Neural Nets and Deep Learning. Skynet Today. https://skynettoday.com/overviews/neural‑net‑history
Magiera, T., Gołuchowska, B., Jabłońska, M. (2013). Technogenic magnetic particles in alkaline dusts from power and cement plants. Water Air & Soil Pollution, 224 (1389), 1‑17. https://doi.org/10.1007/s11270‑012‑1389‑9.
Maňkovská, B., Godzik, B., Badea, O., Shparyk, Y., & Moravčík, P. (2004). Chemical and morphological characteristics of key tree species of the Carpathian Mountains. Environmental Pollution, 130(1), 41‑54. https://doi.org/10.1016/j.envpol.2003.10.020
Мелехин, В.Б. (1984). Self‑learning algorithm for an integrated robot with active and passive behavioral logic. Cybernetics, 20(4), 600‑606. https://doi.org/10.1007/bf01068936
Romanič, S., & Krauthacker, B. (2007). Are pine needles bioindicators of air pollution? Comparison of organochlorine compound levels in pine needles and ambient air. Arhiv Za Higijenu Rada I Toksikologiju, 58(2), 195‑199. https://doi.org/10.2478/v10004‑007‑0012‑8
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., & Fei‑Fei, L. (2015). ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision, 115(3), 211‑252. https://doi.org/10.1007/s11263‑015‑0816‑y
Samet, J.M., & Chung, Y.S. (2017). Air Quality, Atmosphere & Health: the 10‑year anniversary. Air Quality, Atmosphere & Health, 11(1), 1‑2. https://doi.org/10.1007/s11869‑017‑0541‑5
Shaddick, G., Salter, J.M., Peuch, V., Ruggeri, G., Thomas, M.L., Mudu, P., Tarasova, O., Baklanov, A., & Gumy, S. (2020). Global Air Quality: An Inter‑Disciplinary Approach to exposure assessment for burden of disease analyses. Atmosphere, 12(1), 48. https://doi.org/10.3390/atmos12010048
Susanto, A.D. (2020). Air pollution and human health. Medical Journal of Indonesia, 29(1), 8‑10. https://doi.org/10.13181/mji.com.204572
Szwed, M., Kozłowski, R., Żukowski, W. (2020). Assessment of Air Quality in the South‑Western Part of the Świętokrzyskie Mountains Based on Selected Indicators. Forests, 11, 499. https://doi.org/10.3390/f11050499.
Szwed, M., Żukowski, W., & Kozłowski, R. (2021). The Presence of Selected Elements in the Microscopic Image of Pine Needles as an Effect of Cement and Lime Pressure within the Region of Białe Zagłębie (Central Europe). Toxics, 9(1), 15. https://doi.org/10.3390/toxics9010015
Świercz, A., Szwed, M., Bąk, Ł. (2024). Environmental consequences of a galvanising plant fire. Journal of Water and Land Development, 62(7‑9), 1‑9. https://doi.org/10.24425/jwld.2024.151552
Tadeusiewicz, R. (1993). Sieci neuronowe. Warszawa: Akademicka Oficyna Wydawnicza
Tadeusiewicz, R. (2015). Neural networks as a tool for modeling of biological systems. Bio-Algorithms & Med-Systems (Online)/Bio-Algorithms and Med-Systems, 11(3), 135‑144. https://doi.org/10.1515/bams‑2015‑0021
Takano, A.P.C., Rybak, J., Veras, M.M. (2024). Bioindicators and Human Biomarkers as Alternative Approaches for Cost‑Effective Assessment of Air Pollution Exposure. Frontiers in Environmental Engineering, 3. https://doi.org/10.3389/fenve.2024.1346863.
Thacore, S. (1998). An evolutionary self‑learning methodology: Some preliminary results from a case study. In Lecture notes in computer science (pp. 387‑396). https://doi.org/10.1007/bfb0040791
WHO. 2021. WHO global air quality guidelines: particulate matter (PM2.5 and PM10), ozone, nitrogen dioxide, sulfur dioxide and carbon monoxide. Geneva: World Health Organization. Pobrane z: https: //www.who.int/publications/i/item/9789240034228 (19.05.2024).