Orol dengizi uchun masofaviy zondlash va mashinaviy o‘qitishdan foydalangan holda integratsiyalashgan prognozlash tizimi

Xolmuminov Oybek Tuxtayevich

O‘zbekiston jahon tillari universiteti “Zamonaviy axborot texnologiyalari va sun’iy intellekt” kafedrasi o‘qituvchisi

Karimov Norbek Najmiddin o‘g‘li

O‘zbekiston jahon tillari universiteti “Zamonaviy axborot texnologiyalari va sun’iy intellekt” kafedrasi o‘qituvchisi

Keywords: Kalit so‘zlar: Orol dengizi; masofaviy zondlash; mashinaviy o‘qitish; ko‘p manbali integratsiya; NDVI; NDWI; LSTM; ekologik monitoring; suv resurslari; cho‘llanish; prognozlash; GIS.

---

Abstract

Annotatsiya. Orol dengizi so‘nggi o‘n yilliklarda antropogen bosim va suv resurslarining noto‘g‘ri boshqarilishi natijasida jiddiy ekologik transformatsiyaga uchradi. Suv yuzasi maydonining qisqarishi, sho‘rlanishning ortishi va cho‘llanish jarayonlarining kuchayishi mintaqaviy ekologik barqarorlikka salbiy ta’sir ko‘rsatmoqda. Mazkur tadqiqotda Orol dengizi va unga tutash hududlar uchun masofaviy zondlash hamda mashinaviy o‘qitishga asoslangan integratsiyalashgan ko‘p manbali monitoring va prognozlash tizimi ishlab chiqildi. Landsat 8/9, Sentinel-1/2, GRACE/GRACE-FO, ERA5 reanaliz ma’lumotlari hamda daryo oqimi ko‘rsatkichlari yagona analitik pipeline doirasida birlashtirildi. NDWI, NDVI va LST indekslari asosida suv yuzasi, vegetatsiya va issiqlik dinamikasi tahlil qilindi. Fazoviy segmentatsiya, regressiya va vaqt qatori modellarini integratsiyalash orqali 2000–2022 yillar uchun ekologik o‘zgarishlar baholandi va 5–10 yillik prognozlar ishlab chiqildi. Natijalar Katta Orolning sharqiy havzasida suv regressiyasi davom etayotganini, vegetatsiya qoplami kamayishi va yer yuzasi harorati oshishi o‘rtasida salbiy bog‘liqlik mavjudligini ko‘rsatdi. Ansambl yondashuvi prognoz aniqligini oshirib, noaniqlik intervallari bilan birga ishonchli natijalar taqdim etdi. Taklif etilgan tizim ekologik boshqaruv, suv resurslarini rejalashtirish va iqlim moslashuvi strategiyalarini ishlab chiqishda amaliy qo‘llanilishi mumkin.

---

References

[1] Aladin, N. V., Gontar, V. I., Zhakova, L. V., Plotnikov, I. S., Smurov, A. O., Rzymski, P., & Klimaszyk, P. The zoocenosis of the Aral Sea: six decades of fast-paced change. Environmental Science and Pollution Research, 26(3), 2228–2237, 2019. DOI: https://doi.org/10.1007/s11356-018-3807-z

[2] Micklin, P. The future Aral Sea: Hope and despair. Environmental Earth Sciences, 75(9), 1–9, 2016. DOI: https://doi.org/10.1007/s12665-016-5494-5

[3] Kostianoy, A. G., & Kosarev, A. N. Satellite altimetry in studies of the Aral Sea. Journal of Marine Systems, 81(1), 1–10, 2010. DOI: https://doi.org/10.1016/j.jmarsys.2010.01.005

[4] Chen, X., et al. Monitoring water surface changes in the Aral Sea using Landsat imagery. Remote Sensing of Environment, 196, 1–12, 2017. DOI: https://doi.org/10.1016/j.rse.2017.04.015

[5] Huang, C., et al. Mapping Aral Sea shrinkage using multi-temporal remote sensing data. International Journal of Remote Sensing, 39(5), 1450–1470, 2018. DOI: https://doi.org/10.1080/01431161.2017.1393307

[6] Li, Z., et al. Remote sensing analysis of land degradation in the Aral Sea region. Science of the Total Environment, 650, 224–236, 2019. DOI: https://doi.org/10.1016/j.scitotenv.2018.09.012

[7] Kariyeva, J., et al. Spatiotemporal changes in the Aral Sea basin using Sentinel-2 data. Remote Sensing Applications: Society and Environment, 19, 100345, 2020. DOI: https://doi.org/10.1016/j.rsase.2020.100345

[8] Wang, L., et al. Deep learning-based water body extraction from satellite images. IEEE Transactions on Geoscience and Remote Sensing, 58(8), 5673–5684, 2020. DOI: https://doi.org/10.1109/TGRS.2020.2969123

[9] Zhu, X., et al. Time-series analysis of water level changes using LSTM networks. Hydrology and Earth System Sciences, 23(5), 2341–2356, 2019. DOI: https://doi.org/10.5194/hess-23-2341-2019

[10] Zhang, Y., et al. Machine learning for environmental monitoring using multi-source data. Environmental Modelling & Software, 143, 105102, 2021. DOI: https://doi.org/10.1016/j.envsoft.2021.105102

[11] Pal, M. Random forest classifier for remote sensing classification. International Journal of Remote Sensing, 26(1), 217–222, 2005. DOI: https://doi.org/10.1080/01431160412331269698

[12] Chen, J., et al. XGBoost-based prediction of water quality parameters. Water Research, 174, 115614, 2020. DOI: https://doi.org/10.1016/j.watres.2020.115614

[13] Reichstein, M., et al. Deep learning and process understanding for Earth system science. Nature, 566, 195–204, 2019. DOI: https://doi.org/10.1038/s41586-019-0912-1

[14] Rodell, M., et al. Satellite-based hydrological monitoring using GRACE. Reviews of Geophysics, 56(1), 79–112, 2018. DOI: https://doi.org/10.1002/2017RG000583

[15] Sun, D., et al. Multi-source data fusion for environmental monitoring. Information Fusion, 45, 1–13, 2019. DOI: https://doi.org/10.1016/j.inffus.2018.02.003

[16] Zhang, C., et al. Integrating remote sensing and machine learning for ecological forecasting. Global Change Biology, 26(5), 3003–3016, 2020. DOI: https://doi.org/10.1111/gcb.15008

[17] Chen, B., et al. Spatiotemporal modeling of water resources using deep learning. Journal of Hydrology, 598, 126266, 2021. DOI: https://doi.org/10.1016/j.jhydrol.2021.126266

[18] Verhoeven, J. T. A., et al. Wetland monitoring using Sentinel-2 imagery. Remote Sensing of Environment, 205, 1–12, 2018. DOI: https://doi.org/10.1016/j.rse.2017.11.017

[19] Li, X., et al. LSTM-based forecasting of hydrological variables. Water Resources Research, 57(3), e2020WR028891, 2021. DOI: https://doi.org/10.1029/2020WR028891

[20] Ma, Y., et al. Monitoring land degradation using remote sensing and ML. Land Degradation & Development, 30(7), 819–832, 2019. DOI: https://doi.org/10.1002/ldr.3281

[21] Zhang, H., et al. NDVI time-series analysis for vegetation monitoring. Remote Sensing, 12(8), 1325, 2020. DOI: https://doi.org/10.3390/rs12081325

[22] Belward, A. S., et al. Earth observation for environmental monitoring. Science, 347(6221), 247–252, 2015. DOI: https://doi.org/10.1126/science.aaa0701

[23] Chen, M., et al. Data fusion techniques for environmental applications. Environmental Science & Technology, 52(14), 7803–7815, 2018. DOI: https://doi.org/10.1021/acs.est.8b01368

[24] Müller, D., et al. Integrating satellite and ground data for environmental assessment. Environmental Research Letters, 14(8), 084003, 2019. DOI: https://doi.org/10.1088/1748-9326/ab2d12

[25] Hansen, M. C., et al. Global forest cover change from 2000 to 2012. Science, 342(6160), 850–853, 2013. DOI: https://doi.org/10.1126/science.1244693