KOSMIK TASVIRLAR ASOSIDA PAXTA VA G'ALLA EKINLARINI MASHINALI O'RGANISH ALGORITMLARI YORDAMIDA MONITORING QILISH
Keywords:
giperspektral masofaviy zondlash; EnMAP; ekin tasniflash; mashinali oʼrganish; Random Forest; SVM; spektral kutubxona; OʻzbekistonAbstract
Ushbu maqolada Toshkent viloyati sugʼoriladigan qishloq xoʼlaligi hududlarida EnMAP giperspektral sunʼi (224 spektral kanal, 400–2500 nm, 30 m fazoviy aniqlik) maʼlumotlari asosida paxta va gʼalla ekinlarini mashinali oʼrganish algoritmlari yordamida tasniflash natijalari bayon etiladi. Tasvirlarni qayta ishlash jarayonida radiometrik va atmosferik korreksiya, Minimal Shovqin Fraktsiyasi (MNF) hamda Asosiy Komponentlar Tahlili (PCA) transformatsiyalari qoʼllandi. Dala kuzatuv maʼlumotlari asosida ekin turlarining spektral kutubxonasi tuzildi. Olti xil algoritm — Random Forest (RF), Qoʼllab-quvvatlash Vektor Mashina (SVM), Gradient Boosting (GB), Qaror Daraxti (DT), k-eng yaqin qoʼshni (kNN) va Naiv Bayes (NB) — 10-qatlamli kross-validatsiya asosida baholandi. Eng yuqori natija Random Forest algoritmida qayd etildi: umumiy aniqlik (OA) 95,2% va Kappa koeffitsienti 0,91 ga teng. Tadqiqot natijalari giperspektral maʼlumotlarning anʼanaviy koʼp spektral sensorglariga nisbatan ekin turlarini ajratishda sezilarli ustunligini tasdiqlaydi.
References
1.Djumaboev K., Hamidov A., Anarbekov O., Gafurov Z., Tussupova K. Impact of institutional change on irrigation management: a case study from southern Uzbekistan // Water. — 2017. — Vol. 9, № 6. — P. 419.
2.Aslanov I., Teshaev N., Khayitov K., Uzbekhon M., Khaitbaeva J., Murodova D. Analysis of desertification trends in Central Asia based on MODIS data using Google Earth Engine // E3S Web of Conferences. — 2023. — Vol. 443. — P. 06015.
3.Erdanaev E., Kappas M., Wyss D. Irrigated crop types mapping in Tashkent Province of Uzbekistan with remote sensing-based classification methods // Sensors. — 2022. — Vol. 22, № 15. — P. 5683.
4.Teshaev N., Inamov A., Juraev K. Assessment of forest fires in Zaamin National Park using remote sensing: comparative analysis of NBR and NDVI // AIP Conference Proceedings. — 2025. — Vol. 3256, № 1. — P. 040042.
5.Ghamisi P., Yokoya N., Li J., Liao W., Liu S., Plaza J., Rasti B., Plaza A. Advances in hyperspectral image and signal processing: a comprehensive overview of the state of the art // IEEE Geoscience and Remote Sensing Magazine. — 2017. — Vol. 5, № 4. — P. 37–78.
6.Guanter L., Kaufmann H., Segl K., Foerster S., Rogass C., Chabrillat S. [va b.q.]. The EnMAP spaceborne imaging spectroscopy mission for Earth observation // Remote Sensing. — 2015. — Vol. 7, № 7. — P. 8830–8857.
7.Segl K., Guanter L., Rogass C., Kuester T., Roessner S., Kaufmann H. [va b.q.]. EeteS — the EnMAP end-to-end simulation tool // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. — 2012. — Vol. 5, № 2. — P. 522–530.
8.Chang C. I. Hyperspectral Data Processing: Algorithm Design and Analysis. — Hoboken: Wiley, 2013. — 1164 b.
9.Hughes G. On the mean accuracy of statistical pattern recognizers // IEEE Transactions on Information Theory. — 1968. — Vol. 14, № 1. — P. 55–63.
10.Pal M. Random forest classifier for remote sensing classification // International Journal of Remote Sensing. — 2005. — Vol. 26, № 1. — P. 217–222.
11.Melgani F., Bruzzone L. Classification of hyperspectral remote sensing images with support vector machines // IEEE Transactions on Geoscience and Remote Sensing. — 2004. — Vol. 42, № 8. — P. 1778–1790.
12.Zagajewski B., Kycko M., Twardowski-Iglewska A., Koppik M., Jarocinska J. Comparison of support vector machines and random forests for mapping of heterogeneous land cover using multitemporal Sentinel-2 and EnMAP imagery // Remote Sensing of Environment. — 2023. — Vol. 299. — P. 113867.
13.Chemura A., Mutanga O., Dube T. Separability of coffee leaf rust infection levels with machine learning methods at Sentinel-2 MSI spectral resolutions // Precision Agriculture. — 2017. — Vol. 18, № 5. — P. 859–881.
14.Ham J., Chen Y., Crawford M. M., Ghosh J. Investigation of the random forest framework for classification of hyperspectral data // IEEE Transactions on Geoscience and Remote Sensing. — 2005. — Vol. 43, № 3. — P. 492–501.
15.Green R. O., Eastwood M. L., Sarture C. M., Chrien T. G., Aronsson M., Chippendale B. J. [va b.q.]. Imaging spectroscopy and the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) // Remote Sensing of Environment. — 1998. — Vol. 65, № 3. — P. 227–248.