برآورد کربن آلی خاک با ترکیب تصاویر ماهوارهای لندست 8 و مادیس و مدلسازی به روش یادگیری ماشین
نوع مقاله : مقاله پژوهشی
نویسندگان
1
گروه خاکشناسی، واحد کرج، دانشگاه آزاد اسلامی، کرج، ایران
2
گروه خاکشناسی، واحد کرج، دانشگاه آزاد اسلامی،کرج، ایران
3
گروه سنجش از دور، دانشگاه تهران، تهران
10.22034/wmji.2024.2026606.1064
چکیده
هدف از این مطالعه، توسعه مدلهای یادگیری ماشین جهت برآورد کربن آلی خاک با استفاده از تصاویر لندست 8 و مادیس بهصورت جداگانه و همافزایی تصاویر فوق در خاکهای کشاورزی در منطقه مرکزی ایران میباشد. در این مطالعه، نمونههای خاک از 336 نقطه در خاکهای کشاورزی در دو کاربری زراعی و باغی استان البرز جمعآوری شدند و کربن آلی خاک به روش اکسیداسیون تر اندازهگیری شد. برای تحلیل کربن آلی خاک از دادههای سنجشازدور استفاده شد که از منابع مختلف مانند تصویر لندست 8 و سنجنده مادیس بهدستآمده بودند. در این مطالعه سه مدل یادگیری ماشینی شامل شبکههای عصبی مصنوعی (ANN)، رگرسیون بردار پشتیبان (SVR) و الگوریتم بیان ژن (GEP) استفاده شدند. این مدلها بهمنظور برآورد میزان کربن آلی خاک استفاده شدند. نتایج این پژوهش نشان داد که بهکارگیری مدل SVR در حالت استفاده همزمان از دادههای تصویر لندست 8 و سنجنده مادیس عملکرد بهتری (0/62 =R2، 0/63 =RMSE و 0/98 =R2/RMSE) نسبت به استفاده هر تصویر بهصورت جداگانه داشت؛ بنابراین، این پژوهش به این نتیجه رسید که استفاده همزمان (تحت عنوان همافزایی) دادههای سنجشازدور از منابع مختلف میتواند بهبود قابلتوجهی در دقت برآورد محتوای کربن آلی در خاکهای کشاورزی در منطقه مرکزی ایران ایجاد کند. استفاده از تکنیکهای فیوژن پیشرفته یا تکنیکهای یادگیری عمیق برای ترکیب ویژگیها در سطح بالاتر پیشنهاد میشود.
کلیدواژهها
عنوان مقاله English
Estimation of soil organic carbon using data synergy of Landsat 8 satellite imagery and MODIS sensor through machine learning models
نویسندگان English
Prinaz Abdoli
1
Ali Khanmirzaei
2
Saeid Hamzeh
3
Shekoofeh Rezaei
2
Somayeh Moghimi
2
1
Department of Soil Science, Karaj Branch, Islamic Azad University, Karaj, Iran
2
Department of Soil Science, Karaj Branch, Islamic Azad University, Karaj, Iran.
3
Remote Sensing Department, University of Tehran, Tehran, Iran.
چکیده English
The main objective of this study was to develop machine learning models for predicting soil organic carbon (SOC) content in agricultural soils enriched with calcium-rich materials in the central region of Iran. Soil samples were collected from 336 points in agricultural lands with two land uses, namely cropland and orchard, from Alborz Province. The soil organic carbon was measured using the Walkley-Black oxidation method. Remote sensing data, obtained from various sources such as Landsat 8 imagery and MODIS sensor, were utilized for soil organic carbon analysis. Three machine learning models, including Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Gene Expression Programming (GEP), were employed in this study to estimate the soil organic carbon content. The results of this research demonstrated positive outcomes, indicating that the simultaneous use of Landsat 8 imagery and MODIS sensor data through the SVR model yielded better performance (R2 = 0.62, RMSE = 0.63, R2/RMSE = 0.98) compared to the use of each image separately. Therefore, this study concluded that the simultaneous synergy of remote sensing data from different sources (referred to as data synergy) can significantly improve the accuracy of predicting soil organic carbon content in calcium-enriched agricultural soils in the central region of Iran. It is recommended to use advanced fusion techniques and deep learning methods for combining features at a higher level.
کلیدواژهها English
Environmental data
Modelling
and combination
Remote sensing
Vegetation indices
- Akbari, M., Goudarzi, I., Tahmoures, M., Elveny, M., and Bakhshayeshi, I. 2021. Predicting soil organic carbon by integrating Landsat 8 OLI, GIS and data mining techniques in semi-arid region. Earth Science Informatics. 14(4): 2113-2122 (In Persian).
- Chen, D., Chang, N., Xiao, J., Zhou, Q., and Wu, W. 2019. Mapping dynamics of soil organic matter in croplands with MODIS data and machine learning algorithms. Science of the Total Environment. 669: 844-855.
- Gomes, L. C., Faria, R. M., de Souza, E., Veloso, G. V., Schaefer, C. E. G., and Fernandes Filho, E. I. 2019. Modelling and mapping soil organic carbon stocks in Brazil. Geoderma. 340: 337-350.
- Gray, J., Karunaratne, S., Bishop, T., Wilson, B., and Veeragathipillai, M. 2019. Driving factors of soil organic carbon fractions over New South Wales, Australia. Geoderma. 353: 213-226.
- Liao, C., Wang, J., Dong, T., Shang, J., Liu, J., and Song, Y. 2019. Using spatio-temporal fusion of Landsat-8 and MODIS data to derive phenology, biomass and yield estimates for corn and soybean. Science of the total environment. 650: 1707-1721.
- Li, W., Fang, H., Qin, G., Tan, X., Huang, Z., Zeng, F., Du, H. and Li, S. 2020. Concentration estimation of dissolved oxygen in Pearl River Basin using input variable selection and machine learning techniques. Science of the Total Environment. 731: 139099.
- Li, Y., Shi, Q., He, L., Cai, R., Meng, L., Li, J., and Plaza, A. 2022. Fusing Sentinel-2 and Landsat-8 surface reflectance data via pixel-wise local normalization. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 15: 7359-7374.
- Mahmoudabadi, A., Karimi. A. R., Haqnia. G. and Sepehr. A. 2017. Performance evaluation of multivariate regression, artificial neural network and Biangen programming in estimating some soil properties. Journal of water and soil protection research. 24 (2): 23-44 (In Persian).
- Mirchooli, F., Kiani-Harchegani, M., Darvishan, A. K., Falahatkar, S., and Sadeghi, S. H. 2020. Spatial distribution dependency of soil organic carbon content to important environmental variables. Ecological Indicators. 116: 106473.
- Mirzaee, S., Ghorbani-Dashtaki, S., Mohammadi, J., Asadi, H., and Asadzadeh, F. 2016. Spatial variability of soil organic matter using remote sensing data. Catena. 145: 118-127.
- Minasny, B., Setiawan, B. I., Arif, C., Saptomo, S. K., and Chadirin, Y. 2016. Digital mapping for cost-effective and accurate prediction of the depth and carbon stocks in Indonesian peatlands. Geoderma. 272: 20-31.
- Nawar, S., and Mouazen, A. M. 2019. On-line vis-NIR spectroscopy prediction of soil organic carbon using machine learning. Soil and Tillage Research. 190: 120-127.
- Nelson, D. W., and Sommers, L. E. 1983. Total carbon, organic carbon, and organic matter. Methods of soil analysis: Part 2 chemical and microbiological properties. 9: 539-579.
- Paustian, K., Larson, E., Kent, J., Marx, E., and Swan, A. 2019. Soil C sequestration as a biological negative emission strategy. Frontiers in Climate. 1: 482133.
- Peng, J., Biswas, A., Jiang, Q., Zhao, R., Hu, J., Hu, B., and Shi, Z. 2019. Estimating soil salinity from remote sensing and terrain data in southern Xinjiang Province, China. Geoderma. 337: 1309-1319.
- Seifi, M., Ahmadi, A., Neyshabouri, M. R., Taghizadeh-Mehrjardi, R., and Bahrami, H. A. 2020. Remote and Vis-NIR spectra sensing potential for soil salinization estimation in the eastern coast of Urmia hyper saline lake, Iran. Remote Sensing Applications: Society and Environment. 20: 100398.
- Soussana, J. F., Loiseau, P., Vuichard, N., Ceschia, E., Balesdent, J., Chevallier, T., and Arrouays, D. 2004. Carbon cycling and sequestration opportunities in temperate grasslands. Soil use and management. 20(2): 219-230.
- Wang, B., Gray, J.M., Waters, C.M., Anwar, M.R., Orgill, S.E., Cowie, A.L., Feng, P. and Li Liu, D. 2022. Modelling and mapping soil organic carbon stocks under future climate change in south-eastern Australia. Geoderma. 405: 115442.
- Wenzel, W. W., Duboc, O., Golestanifard, A., Holzinger, C., Mayr, K., Reiter, J., and Schiefer, A. 2022. Soil and land use factors control organic carbon status and accumulation in agricultural soils of Lower Austria. Geoderma. 409: 115595.
- Zepp, S., Heiden, U., Bachmann, M., Wiesmeier, M., Steininger, M., and Van Wesemael, B. 2021. Estimation of soil organic carbon contents in croplands of Bavaria from SCMaP soil reflectance composites. Remote Sensing. 13(16): 3141.
- Zhang, M., Zhang, M., Yang, H., Jin, Y., Zhang, X., and Liu, H. 2021. Mapping regional soil organic matter based on sentinel-2a and modis imagery using machine learning algorithms and google earth engine. Remote Sensing. 13(15): 2934.
