Keywords:
- soil organic carbon (SOC)
- spectroscopy
- near-infrared (NIR)
- mid-infrared (MIR)
- remote sensing
- artificial intelligence (AI/ML)
- GIS
- carbon sequestration
Abstract
This article theoretically substantiates the advantages of an innovative integrated method aimed at fundamentally increasing the accuracy, efficiency, and speed of determining soil organic carbon (SOC). The approach combines direct laboratory measurements, soil spectroscopy (NIR/MIR), remote sensing (Sentinel, Landsat), and Artificial Intelligence (AI/ML) models.
References
Bobomurodov Sh., Baxodirov Z., Yuldashov M., Tursunov Sh. “Anʼanaviy va zamonaviy usullarni o‘zaro integratsiyalash orqali tuproqdagi organik uglerodni baholash hususida”. O‘zbekiston agrar fani xabarnomasi. Ilmiy-amaliy jurnal. № 6/1 (24) 2025 yil. 154-159.
Qo‘ziyev R.Q., Abduraxmonov N.Yu. va boshqalar. Davlat yer kadastrini yuritish uchun tuproq tadqiqotlarini bajarish va tuproq kartalarini tuzish bo‘yicha yo‘riqnoma. / – Toshkent, 2013 y. – B. -52.
“Paxta maydonlarida tuproqlarning agrofizikaviy, agrokimyoviy va mikrobiologik xossalarini o‘rganish uslublari”. / O‘zPITI. – Toshkent, 1993 y. – B. -37
Аринушкина. Е.В. “Руководство по химическому анализу почв”. – М.: 1970 г. – С. -485.
Агрохимические, агрофизические и микробилогические исследования почв и растений” // ЎзПИТИ. – Ташкент, 1963. – С. –50-60.
Lal, R. (2004). Soil carbon sequestration impacts on global climate change and food security. Science, 304(5677), 1623–1627.
Janik, L. J., Skjemstad, J. O., & Shepherd, K. D. (2007). The prediction of soil carbon by visible and near infrared diffuse reflectance spectroscopy. Soil Research, 45(2), –73–81.
Vagen, T. G., Shepherd, K. D., & Walsh, M. G. (2010). Sensing soil organic carbon on a regional scale using satellite imagery. Remote Sensing of Environment, 114(8), 1629–1637.
Hengl, T., Heuvelink, G. B. M., & Rossiter, D. G. (2007). About default settings in geostatistical soil mapping. Geoderma, 140 (4), –412–427.
Padarian, J., Minasny, B., & McBratney, A.B. (2019). Using deep learning to predict soil properties from visible near-infrared spectra. Geoderma, – 353, –168–176.
