Abstract
Soil organic carbon (SOC) stands out as a crucial indicator for assessing soil properties due to its direct impact on soil productivity. To delve into this, we collected 350 soil samples from depths ranging from 0 to 30 cm in the northwest region of Iran, measuring SOC levels. Concurrently, we obtained vegetation indices from Landsat 8 and Sentinel-2 satellite images. Subsequently, we employed machine learning techniques, specifically artificial neural network (ANN) and random forest (RF) models, to estimate the spatial distribution of SOC. In the subsequent phase, we classified the land units of the region based on physiography, vegetation, erosion, flooding, soil type, and depth for a more accurate comparison of estimation models. We then compared the average values of measured and predicted SOC within these land units. The evaluation of ANN and RF models, utilizing vegetation indices from Landsat 8 and Sentinel-2 satellites, revealed that the RF method, particularly when using vegetation indices from the Sentinel-2 satellite, exhibited superior accuracy in predicting SOC (R2 = 0.8, RMSE = 0.19, and ρc = 0.81). Moreover, when comparing the estimated and predicted average values of SOC in different land units, we observed no significant difference between the measured and predicted averages using the RF method. This underscores the robustness of the RF model in accurately predicting SOC by leveraging vegetation indices extracted from Sentinel-2 satellite data. Consequently, the RF model emerges as a reliable tool for SOC evaluation, offering precise forecasts and contributing to cost and time savings by minimizing the need for extensive soil sampling and laboratory analysis.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request. The data of digital elevation model are available in the earth explorer website (https://earth.explorer.usgs.gov/).
References
Akbari M, Goudarzi I, Tahmoures M, Elveny M, Bakhshayeshi I (2021) Predicting soil organic carbon by integrating Landsat 8 OLI, GIS and data mining techniques in semi-arid region. Earth Sci Inf 14(4):2113–2122. https://doi.org/10.1007/s12145-021-00673-8
Ayoubi S, Karchegani PM, Mosaddeghi MR, Honarjoo N (2012) Soil aggregation and organic carbon as affected by topography and land use change in western Iran. Soil and Tillage Research 121:18–26. https://doi.org/10.1016/j.still.2012.01.011
Bhunia GS, Shit PK, Maiti R (2016) Spatial variability of soil organic carbon under different land use using radial basis function (RBF). Model Earth Syst Environ 2:1–8. https://doi.org/10.1007/s40808-015-0070-x
Bouyoucos GJ (1962) Hydrometer method improved for making particle size analyses of soils 1. Agron J 54(5):464–465. https://doi.org/10.2134/agronj1962.00021962005400050028x
Brest CL, Goward SN (1987) Deriving surface albedo measurements from narrow band satellite data. Int J Remote Sens 8(3):351–367. https://doi.org/10.1080/01431168708948646
Chen Q, Miao F, Wang H, Xu ZX, Tang Z, Yang L, Qi S (2020) Downscaling of satellite remote sensing soil moisture products over the Tibetan Plateau based on the random forest algorithm: Preliminary results. Earth Space Sci 7(6): e2020EA001265. https://doi.org/10.1029/2020EA001265
Clay J (2013) World agriculture and the environment: a commodity-by-commodity guide to impacts and practices. Island Press
Dalal R, Chan K (2001) Soil organic matter in rainfed cropping systems of the Australian cereal belt. Soil Research 39(3):435–464. https://doi.org/10.1071/SR99042
De Anta RC, Luís E, Febrero-Bande M, Galiñanes J, Macías F, Ortíz R, Casás F (2020) Soil organic carbon in peninsular Spain: Influence of environmental factors and spatial distribution. Geoderma 370:114365. https://doi.org/10.1016/j.geoderma.2020.114365
De la Casa A, Ovando G, Bressanini L, Martínez J, Díaz G, Miranda C (2018) Soybean crop coverage estimation from NDVI images with different spatial resolution to evaluate yield variability in a plot. ISPRS J Photogramm Remote Sens 146:531–547. https://doi.org/10.1016/j.isprsjprs.2018.10.018
Fekadu G, Adgo E, Meshesha DT, Tsunekawa A, Haregeweyn N, Peng F, Mulualem T, Tsubo M, Tassew A, Masunaga T (2023) Spatiotemporal variations of soil respiration under different land uses and their control in Northwestern Ethiopia. Model Earth Syst Environ, 1–13. https://doi.org/10.1007/s40808-023-01842-y
Gholami V, Booij M, Tehrani EN, Hadian M (2018) Spatial soil erosion estimation using an artificial neural network (ANN) and field plot data. CATENA 163:210–218. https://doi.org/10.1016/j.catena.2017.12.027
Gitelson A (1996) Use of a green channel in remote sensing of global vegetation from EOSMODIS. Remote Sens Environ 58:289–298. https://doi.org/10.1016/S0034-4257(96)00072-7
Gomes LC, Faria RM, de Souza E, Veloso GV, Schaefer CEG, Fernandes Filho EI (2019) Modelling and mapping soil organic carbon stocks in Brazil. Geoderma 340:337–350. https://doi.org/10.1016/j.geoderma.2019.01.007
Guignard MS, Leitch AR, Acquisti C, Eizaguirre C, Elser JJ, Hessen DO, Jeyasingh PD, Neiman M, Richardson AE, Soltis PS (2017) Impacts of nitrogen and phosphorus: from genomes to natural ecosystems and agriculture. Front Ecol Evol 5:70. https://doi.org/10.3389/fevo.2017.00070
Guo L, Fu P, Shi T, Chen Y, Zeng C, Zhang H, Wang S (2021) Exploring influence factors in mapping soil organic carbon on low-relief agricultural lands using time series of remote sensing data. Soil Tillage Res 210:104982. https://doi.org/10.1016/j.still.2021.104982
Haji K, Khaledi Darvishan A, Mostafazadeh R (2023) Soil erosion and sediment sourcing in the Hyrcanian forests, Northern Iran: an integration approach of the G2loss model and sediment fingerprinting technique. Model Earth Syst Environ 1–18. https://doi.org/10.1007/s40808-023-01879-z
Huete A, Didan K, Miura T, Rodriguez EP, Gao X, Ferreira LG (2002) Overview of the radiometric and biophysical performance of the MODIS vegetation indices. Remote Sens Environ 83(1–2):195–213. https://doi.org/10.1016/S0034-4257(02)00096-2
Kumar S, Lal R, Liu D (2012) A geographically weighted regression kriging approach for mapping soil organic carbon stock. Geoderma 189:627–634. https://doi.org/10.1016/j.geoderma.2012.05.022
Luo C, Zhang X, Wang Y, Men Z, Liu H (2022) Regional soil organic matter mapping models based on the optimal time window, feature selection algorithm and Google Earth Engine. Soil Tillage Res 219:105325. https://doi.org/10.1016/j.still.2022.105325
Malone BP, Minasny B, McBratney AB (2017) Using R for digital soil mapping (Vol. 35). Springer. https://doi.org/10.1007/978-3-319-44327-0
Mason A, Salomon M, Lowe A, Cavagnaro T (2023) Microbial solutions to soil carbon sequestration. J Clean Prod 137993. https://doi.org/10.1016/j.jclepro.2023.137993
Mirbakhsh M, Zahed Z, Mashayekhi S, Jafari M (2023) Investigation of in vitro apocarotenoid expression in perianth of saffron (Crocus sativus L.) under different soil EC. arXiv preprint arXiv:2304.01049. https://doi.org/10.25047/agriprima.v7i1.508
Mirbakhsh M (2022) Effect of short and long period of salinity stress on physiological responses and biochemical markers of Aloe vera L. Ilmu Pertanian (Agricultural Science), 7(3): 178–187. https://doi.org/10.22146/ipas.78646
Mirzaee S, Mirzakhani Nafchi A (2023) Monitoring spatiotemporal vegetation response to drought using remote sensing data. Sensors 23(4):2134. https://doi.org/10.3390/s23042134
Muhetaer N, Nurmemet I, Abulaiti A, Xiao S, Zhao J (2022) A quantifying approach to soil salinity based on a radar feature space model using alos palsar-2 data. Remote Sensing 14(2):363. https://doi.org/10.3390/rs14020363
Nelson Da, Sommers LE (1983) Total carbon, organic carbon, and organic matter. Methods of soil analysis: Part 2 chemical and microbiological properties, 9: 539–579. https://doi.org/10.2134/agronmonogr9.2.2ed.c29
Nelson R (1982) Carbonate and gypsum. p 181–197.
Nguyen TT, Pham TD, Nguyen CT, Delfos J, Archibald R, Dang KB, Hoang NB, Guo W, Ngo HH (2022) A novel intelligence approach based active and ensemble learning for agricultural soil organic carbon prediction using multispectral and SAR data fusion. Sci Total Environ 804:150187. https://doi.org/10.1016/j.scitotenv.2021.150187
Padarian J, Stockmann U, Minasny B, McBratney A (2022) Monitoring changes in global soil organic carbon stocks from space. Remote Sens Environ 281:113260. https://doi.org/10.1016/j.rse.2022.113260
Padró J-C, Pons X, Aragonés D, Díaz-Delgado R, García D, Bustamante J, Pesquer L, Domingo-Marimon C, González-Guerrero Ò, Cristóbal J (2017) Radiometric correction of simultaneously acquired Landsat-7/Landsat-8 and Sentinel-2A imagery using pseudoinvariant areas (PIA): contributing to the Landsat time series legacy. Remote Sensing 9(12):1319. https://doi.org/10.3390/rs9121319
Pearson RL, Miller LD (1972) Remote mapping of standing crop biomass for estimation of the productivity of the shortgrass prairie. Remote Sens Environ, VIII, 1355.
Qin C-Z, Zhu A-X, Pei T, Li B-L, Scholten T, Behrens T, Zhou C-H (2011) An approach to computing topographic wetness index based on maximum downslope gradient. Precision Agric 12:32–43. https://doi.org/10.1007/s11119-009-9152-y
Rasmussen C, Southard RJ, Horwath WR (2006) Mineral control of organic carbon mineralization in a range of temperate conifer forest soils. Glob Change Biol 12(5):834–847. https://doi.org/10.1111/j.1365-2486.2006.01132.x
Richardson AJ, Everitt JH (1992) Using spectral vegetation indices to estimate rangeland productivity. Geocarto Int 7(1):63–69. https://doi.org/10.1080/10106049209354353
Rondeaux G, Steven M, Baret F (1996) Optimization of soil-adjusted vegetation indices. Remote Sens Environ 55(2):95–107. https://doi.org/10.1016/0034-4257(95)00186-7
Rossiter D, Hengl T (2001) Creating geometrically-correct photo-interpretations, photomosaics, and base maps for a project GIS. International Institute for Geoinformation Science and Earth Observation (ITC), PO Box, 6, 7500.
Sadeghi M, Babaeian E, Tuller M, Jones SB (2017) The optical trapezoid model: a novel approach to remote sensing of soil moisture applied to Sentinel-2 and Landsat-8 observations. Remote Sens Environ 198:52–68. https://doi.org/10.1016/j.rse.2017.05.041
Shafizadeh-Moghadam H, Minaei F, Talebi-khiyavi H, Xu T, Homaee M (2022) Synergetic use of multi-temporal Sentinel-1, Sentinel-2, NDVI, and topographic factors for estimating soil organic carbon. CATENA 212:106077. https://doi.org/10.1016/j.catena.2022.106077
Somaratne S, Seneviratne G, Coomaraswamy U (2005) Prediction of soil organic carbon across different land-use patterns: a neural network approach. Soil Sci Soc Am J 69(5):1580–1589. https://doi.org/10.2136/sssaj2003.0293
Song X-D, Brus DJ, Liu F, Li D-C, Zhao Y-G, Yang J-L, Zhang G-L (2016) Mapping soil organic carbon content by geographically weighted regression: a case study in the Heihe River Basin, China. Geoderma 261:11–22. https://doi.org/10.1016/j.geoderma.2015.06.024
Suleymanov A, Tuktarova I, Belan L, Suleymanov R, Gabbasova I, Araslanova L (2023) Spatial prediction of soil properties using random forest, k-nearest neighbors and cubist approaches in the foothills of the Ural Mountains, Russia. Model Earth Syst Environ 1–11. https://doi.org/10.1007/s40808-023-01723-4
Theobald DM, Harrison-Atlas D, Monahan WB, Albano CM (2015) Ecologically-relevant maps of landforms and physiographic diversity for climate adaptation planning. PLoS ONE 10(12):e0143619. https://doi.org/10.1371/journal.pone.0143619
USDA-NRCS. (1996). Survey laboratory methods manual. Soil Survey Investigations Report.
van der Westhuizen S, Heuvelink GB, Hofmeyr DP (2023) Multivariate random forest for digital soil mapping. Geoderma 431:116365
Wei Z, Meng Y, Zhang W, Peng J, Meng L (2019) Downscaling SMAP soil moisture estimation with gradient boosting decision tree regression over the Tibetan Plateau. Remote Sens Environ 225:30–44. https://doi.org/10.1016/j.rse.2019.02.022
Xie B, Ding J, Ge X, Li X, Han L, Wang Z (2022) Estimation of soil organic carbon content in the Ebinur Lake wetland, Xinjiang, China, based on multisource remote sensing data and ensemble learning algorithms. Sensors 22(7):2685. https://doi.org/10.3390/s22072685
Yoo K, Amundson R, Heimsath AM, Dietrich WE (2006) Spatial patterns of soil organic carbon on hillslopes: Integrating geomorphic processes and the biological C cycle. Geoderma 130(1–2):47–65. https://doi.org/10.1016/j.geoderma.2005.01.008
Zeraatpisheh M, Ayoubi S, Jafari A, Tajik S, Finke P (2019) Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran. Geoderma 338:445–452. https://doi.org/10.1016/j.geoderma.2018.09.006
Zhang N, Hong Y, Qin Q, Liu L (2013) VSDI: a visible and shortwave infrared drought index for monitoring soil and vegetation moisture based on optical remote sensing. Int J Remote Sens 34(13):4585–4609. https://doi.org/10.1080/01431161.2013.779046
Zhang Y, Xu X, Li Z, Yi R, Xu C, Luo W (2022) Modelling soil thickness using environmental attributes in karst watersheds. CATENA 212:106053. https://doi.org/10.1016/j.catena.2022.106053
Zhe, D., Xiaoqin, W., & Qunyong, W. (2018). Effects of different spatial resolution of remote sensing images on estimation accuracy of urban building height. Remote Sens Technol Appl, 33(3): 418–427. https://doi.org/10.11873/j.issn.1004-0323.2018.3.0418
Acknowledgements
This study was supported by the Urmia University, Agricultural Jihad Organization of West Azarbaijan province, and the soil laboratory of AZAR KHAK. The authors of this article would like to thank from them for accepting all expenses of this study.
Author information
Authors and Affiliations
Contributions
PA: conceptualization, formal analysis, investigation, methodology, writing—original draft. FA: conceptualization, formal analysis, investigation, methodology, software, writing—review & editing, supervision. SR: conceptualization, formal analysis, investigation, writing—review & editing, supervision. KKA: conceptualization, formal analysis, investigation, software, writing—review & editing, supervision. FS: conceptualization, validation, formal analysis, investigation, methodology, writing—review & editing, supervision.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethics approval
All authors have read, understood, and have complied as applicable with the statement on "Ethical responsibilities of Authors" as found in the Instructions for Authors and are aware that with minor exceptions, no changes can be made to authorship once the paper is submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Abbaszad, P., Asadzadeh, F., Rezapour, S. et al. Evaluation of Landsat 8 and Sentinel-2 vegetation indices to predict soil organic carbon using machine learning models. Model. Earth Syst. Environ. 10, 2581–2592 (2024). https://doi.org/10.1007/s40808-023-01916-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40808-023-01916-x