نقشه برداری زمانی مکانی کربن آلی خاک با استفاده از رویکرد مدلسازی معکوس : مطالعه موردی حوضه آبخیز زاینده‌رود استان اصفهان

نوع مقاله : مقالات پژوهشی

نویسندگان

• شیما معصومی ¹
• حمیدرضا متین فر ¹
• سید روح اله موسوی ²

¹ گروه علوم و مهندسی خاک، دانشگده کشاورزی، دانشگاه لرستان، ایران

² گروه علوم و مهندسی خاک، دانشکده کشاورزی، دانشگاه تهران، کرج، ایران

10.22067/jsw.2025.94129.1488

چکیده

تغییرات زمانی و مکانی کربن آلی خاک تحت تأثیر عوامل متعددی از جمله کاربری اراضی، شرایط اقلیمی، توپوگرافی و فعالیت‌های انسانی قرار دارد. با توجه به جایگاه کربن آلی در بهبود کیفیت خاک، پژوهش حاضر با هدف بررسی تغییرات زمانی و مکانی کربن آلی خاک (SOC) با استفاده از رویکرد مدلسازی معکوس بر مبنای مدل مکانی تهیه شده در سال 2024 و تعمیم آن به سال‌های ماقبل 2015، 2010 و 2000 با استفاده از متغیرهای محیطی در حوضه آبخیز زاینده رود انجام گردید. همچنین سه مدل یادگیری ماشین جنگل تصادفی (RF)، رگرسیون بردار پشتیبان (SVR) و درخت تقویت شده با گرادیان افراطی (XGBoost) برای بررسی ارتباط بین فاکتورهای محیطی و SOC به همراه دو رویکرد کمی سازی عدم قطعیت پیش‌بینی شامل بوتسراپت و k-فولد استفاده گردید. نتایج اعتبارسنجی کارایی مدل‌های یادگیری ماشین حاکی از دقت بالاتر مدل RF نسبت به دو مدل دیگر بود. اگرچه بطور مشابه در هر سه مدل روند دقت پیش‌بینی SOC از سال 2024 به 2000 کاهش یافت. همچنین رویکرد عدم قطعیت بوتسراپت بر اساس آماره‌های انحراف معیار و میانگین عدم قطعیت از اطمینان بالاتری در پیش‌بینی SOC برخوردار بود. اهمیت نسبی متغیرهای محیطی نیز نشان دهنده فاکتورهای اقلیمی و توپوگرافی از درجه اهمیت بالاتری در پیش‌بینی SOC بودند. همچنین، تغییرات مکانی SOC با روند الگوی پراکنش متغیرهای اقلیمی و توپوگرافی همخوانی داشت، به طوری که مناطق با بارش و ارتفاع بیشتر به‌همراه دمای پایین‌تر، محتوای SOC بیشتری را نشان دادند. نقشه‌های پیش-بینی مکانی و زمانی نیز بیانگر افزایش سطح اراضی با محتوای SOC بسیار پایین (کمتر از 5/0 درصد) در طی دوره زمانی بلند مورد بررسی از 2000 تا 2024 بود. بطورکلی رویکرد مورد استفاده در این پژوهش می‌تواند به‌عنوان یک چارچوب مناسب برای دست‌یابی به روند تغییرات ویژگی‌های خاک در مناطقی باشد، که بطور عمده فاقد پایگاه داده‌های اطلاعات مکانی خاک در گذشته می‌باشند.

کلیدواژه‌ها

• نقشه‌برداری رقومی متغیرهای محیطی
• الگوریتم‌های یادگیری ماشین
• تغییرپذیری زمانی و مکانی

موضوعات

• علوم خاک

عنوان مقاله [English]

Spatiotemporal Mapping of Soil Organic Carbon Using an Inverse Modeling Approach: A Case Study of the Zayandeh Rud Watershed in Isfahan Province

نویسندگان [English]

• S. Masoumi ¹
• H.R. Matinfar ¹
• S.R. Mousavi ²

¹ Department of Soil Science, Faculty of Agriculture, Lorestan University, Iran

² Department of Soil Science, Faculty of Agriculture, University of Tehran, Karaj, Iran

چکیده [English]

Introduction

Soil organic carbon (SOC), as one of the most important components of the global carbon cycle, plays a vital role in maintaining soil quality, enhancing fertility, and moderating climate change. The spatio-temporal variations of SOC are influenced by various factors, including land use, climatic conditions, topography, and human activities. Additionally, SOC contributes to diverse functions in natural and agricultural ecosystems, such as increasing soil fertility, controlling erosion, enhancing water permeability in soil, and reducing the effects of greenhouse gases.

Materials and Methods

Given the critical role of SOC in enhancing soil quality, this study aims to investigate the spatio-temporal variability of SOC using a reverse modeling approach based on a spatial model developed in 2024. The model is extended to analyze data from the years prior to 2015, 2010, and 2000, incorporating environmental variables derived from remote sensing (RS), topographic attributes, climatic data, land use, and geological information within the Zayandeh Rud watershed. For the environmental covariates, RS data, land use, and climatic information were obtained from Google Earth Engine's open-source spatial database for the relevant years from 2000 to 2024. In total, 76 auxiliary variables were prepared, including vegetation indices derived from band ratios of RS data, as well as the digital elevation model (DEM), geology, land use, and climatic factors, which were used as representatives of soil-forming factors. A relative importance feature selection method was employed to finalize the dataset of environmental covariates. Furthermore, three machine learning models—Random Forest (RF), Support Vector Regression (SVR), and Extreme Gradient Boosting (XGBoost) tree—were utilized to explore the relationships between environmental factors and SOC. Four common statistical indices, including the coefficient of determination (R²), concordance correlation coefficient (CCC), root mean square error (RMSE), and percentage of normalized root mean square error (nRMSE), were used to evaluate the performance of the machine learning models Two uncertainty quantification approaches for prediction, namely bootstrap and k-fold cross-validation, were also applied.

Results and Discussion

The evaluation of machine learning models for predicting SOC revealed a notable decline in the performance of all models from the year 2024 back to 2000, as indicated by the R² statistic. Among the models assessed, the RF model exhibited superior performance, achieving the highest R² values for the years 2024 and 2015, thereby indicating its effectiveness in capturing the complexities of SOC dynamics. The SVR model demonstrated intermediate performance, while the XGBoost model showed relatively weaker results compared to the other two model. Despite these variances in performance, all three machine learning models effectively established a robust connection between SOC and the predictive environmental variables, affirming their suitability for this analysis. Furthermore, the uncertainty quantification of SOC predictions highlighted that the bootstrap method outperformed the k-fold method, yielding lower values for both standard deviation (SD) and mean uncertainty, which suggests that the bootstrap approach provides a more reliable prediction of SOC variability. In terms of the relative importance of environmental variables in predicting SOC, the analysis across all time periods indicated that climatic factors played the most significant role, closely followed by topographical attributes. Other environmental variables, including land use, geology, and RS data, had a lesser impact on explaining spatial variations in SOC. The spatial analysis indicated alarming increases in areas with very low SOC content, suggesting soil degradation risks. Furthermore, higher rainfall and lower temperatures were associated with highest SOC levels, emphasizing the need for effective soil management strategies.

Conclusion

This study emphasizes the necessity of ongoing monitoring and management of Soil Organic Carbon (SOC) to combat soil degradation and promote sustainable agriculture. The findings also provide a framework for creating soil property maps in data-scarce regions, enhancing decision-making for effective soil management strategies.

Overall, the findings from this study highlight the need for continuous monitoring and management of SOC to mitigate risks related to soil degradation and to promote sustainable agricultural practices. Also, the methodology and framework that applied in this research can be used as useful guideline for land manager, young pedometrisians, expert in digital soil mapping, and decision makers for preparing the high detailed maps of other key soil properties such as (soil texture component: Sand, Silt, Clay, Gypsum, calcium carbonate equivalent, soil EC, available phosphorus and potassium that directly affecting on soil quality index in the similar zones with study area.

کلیدواژه‌ها [English]

• Digital Mapping
• Environmental variables
• Machine learning algorithms
• Temporal and spatial variability

©2025 The author(s). This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0).

مراجع

1. Adedeji, O.H. (2019). Geospatial information as a tool for soil resource information, management and decision support in Nigeria. Journal of Applied Sciences and Environmental Management, 23(12), 2107-2116. https://doi.org/4314/ jasem.v23i12.5
2. Adeniyi, O.D., Brenning, A., & Maerker, M. (2024). Spatial prediction of soil organic carbon: Combining machine learning with residual kriging in an agricultural lowland area (Lombardy region, Italy). Geoderma, 448, 116953. https://doi.org/10.1016/j.geoderma.2024.116953
3. Afshar, F.A., Ayoubi, S., & Jafari, A. (2018). The extrapolation of soil great groups using multinomial logistic regression at regional scale in arid regions of Iran. Geoderma, 315, 36-48. https://doi.org/10.1016/j.geoderma. 2017.11.030
4. Behrens, T., Zhu, A.X., Schmidt, K., & Scholten, T. (2010). Multi-scale digital terrain analysis and feature selection for digital soil mapping. Geoderma, 155(3-4), 175-185. https://doi.org/10.1016/j.geoderma.2009.07.010
5. Ben Brahim, A., & Limam, M. (2018). Ensemble feature selection for high dimensional data: a new method and a comparative study. Advances in Data Analysis and Classification, 12(4), 937-952. https://doi.org/10.1007/s11634-017-0285-y
6. Benslama, A., Lucas, I.G., Jordan Vidal, M.M., Almendro-Candel, M.B., & Navarro-Pedreño, J. (2024). Carbon and nitrogen stocks in topsoil under different land use/land cover types in the southeast of Spain. AgriEngineering, 6(1), 396-408. https://doi.org/10.3390/agriengineering6010024
7. Canero, F.M., Rodriguez-Galiano, V., & Aragones, D. (2024). Machine learning and feature selection for soil spectroscopy. An evaluation of random forest wrappers to predict soil organic matter, clay, and carbonates. Heliyon, 10(9). https://doi.org/10.1016/j.heliyon.2024.e30228
8. Charman, P.E.V., & Roper, M.M. (2007). Soil organic matter. In: Charman, P.E.V. and Murphy, B.W., Eds., Soils—Their Properties and Management, 3rd Edition, Oxford University Press, Melbourne, 276-285.
9. Chen, T., & Guestrin, C. (2016). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794). https://doi.org/10.1145/ 2939672.2939785
10. Fathizad, H., Ardakani, M.A.H., Heung, B., Sodaiezadeh, H., Rahmani, A., Fathabadi, A., & Taghizadeh-Mehrjardi, R. (2020). Spatio-temporal dynamic of soil quality in the central Iranian desert modeled with machine learning and digital soil assessment techniques. Ecological Indicators, 118, 106736. https://doi.org/10.1016/j.ecolind.2020. 106736
11. Fathizad, H., Taghizadeh-Mehrjardi, R., Hakimzadeh Ardakani, M.A., Zeraatpisheh, M., Heung, B., & Scholten, T. (2022). Spatiotemporal assessment of soil organic carbon change using machine-learning in arid regions. Agronomy, 12(3), 628. https://doi.org/10.3390/agronomy12030628
12. Fathy, H., Heydari, M., Fathizad, H., Hosseinzadeh, J., Najafifar, A., Mousavi, S.R., & Heung, B. (2025). From forest to farmland: Tracking time series variations in soil quality in semiarid oak forest. Geoderma Regional, 42, e00974. https://doi.org/10.1016/j.geodrs.2025.e00974
13. Garosi, Y., Ayoubi, S., Nussbaum, M., & Sheklabadi, M. (2022). Effects of different sources and spatial resolutions of environmental covariates on predicting soil organic carbon using machine learning in a semi-arid region of Iran. Geoderma Regional, 29, https://doi.org/10.1016/j.geodrs.2022.e00513
14. Hoyle, F.C., O’Leary, R.A., & Murphy, D.V. (2016). Spatially governed climate factors dominate management in determining the quantity and distribution of soil organic carbon in dryland agricultural systems. Scientific Reports, 6(1), 31468. https://doi.org/10.1038/srep31468
15. Hamzehpour, N., Shafizadeh-Moghadam, H., & Valavi, R. (2019). Exploring the driving forces and digital mapping of soil organic carbon using remote sensing and soil texture. Catena, 182, https://doi.org/10.1016/j. catena.2019.104141
16. Kasraei, B., Schmidt, M.G., Zhang, J., Bulmer, C.E., Filatow, D.S., Pennell, T., & Heung, B. (2024). A framework for optimizing environmental covariates to support model interpretability in digital soil mapping. Geoderma, 445, 116873. https://doi.org/10.1016/j.geoderma.2024.116873
17. Kulikova, A.I., Chechenkov, P.D., Osipova, M.S., Shopina, O.V., & Semenkov, I.N. (2023). Comparative analysis of the results of traditional and digital large-scale soil mapping on the example of a key site in the Smolenskoe Poozerye National Park. Eurasian Soil Science, 56(3), 271-277. https://doi.org/10.1134/s1064229322602281
18. Laban, P., Metternicht, G., & Davies, J. (2018). Soil biodiversity and soil organic carbon: keeping drylands alive. Gland, Switzerland: IUCN, 10. https://doi.org/10.2305/IUCN.CH.2018.03.en
19. Lamichhane, S., Kumar, L., & Wilson, B. (2019). Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: A review. Geoderma, 352, 395-413. https://doi.org/10.1016/j.geoderma. 2019.05.031
20. Lotfollahi, L., Delavar, M.A., Biswas, A., Fatehi, S., & Scholten, T. (2023). Spectral prediction of soil salinity and alkalinity indicators using visible, near-, and mid-infrared spectroscopy. Journal of Environmental Management, 345, 118854. https://doi.org/10.1016/j.jenvman.2023.118854
21. Ma, Z., Shi, Z., Zhou, Y., Xu, J., Yu, W., & Yang, Y. (2017). A spatial data mining algorithm for downscaling TMPA 3B43 V7 data over the Qinghai–Tibet Plateau with the effects of systematic anomalies removed. Remote Sensing of Environment, 200, 378-395. https://doi.org/10.1016/j.rse.2017.08.023
22. Madani, K. (2007, May). Water Transfer and watershed development: A system dynamics approach. In World Environmental and Water Resources Congress 2007: Restoring Our Natural Habitat (pp. 1-15). https://doi.org/ 1061/40927(243)551
23. Mantero, P., Moser, G., & Serpico, S.B. (2005). Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Transactions on Geoscience and Remote Sensing, 43(3), 559-570. http://doi.org/1109/TGRS.2004.842022
24. Mallah, S., Delsouz Khaki, B., Davatgar, N., Poppiel, R.R., & Demattê, J.A. (2022). Digital mapping of topsoil texture classes using a hybridized classical statistics–artificial neural networks approach and relief data. AgriEngineering, 5(1), 40-64. https://doi.org/10.3390/agriengineering5010004
25. Masoudi, R., Mousavi, S.R., Rahimabadi, P.D., Panahi, M., & Rahmani, A. (2023). Assessing data mining algorithms to predict the quality of groundwater resources for determining irrigation hazard. Environmental Monitoring and Assessment, 195(2), 319. https://doi.org/ 10.1007/s10661-022-10909-9
26. Matinfar, H.R., Maghsodi, Z., Mousavi, S.R., & Rahmani, A. (2021). Evaluation and prediction of topsoil organic carbon using machine learning and hybrid models at a Field-scale. Catena, 202, https://doi.org/10.1016/ j.catena.2021.105258
27. Mousavi, S.R., Sarmadian, F., Angelini, M.E., Bogaert, P., & Omid, M. (2023). Cause-effect relationships using structural equation modeling for soil properties in arid and semi-arid regions. Catena, 232, https://doi.org/ 10.1016/j.catena.2023.107392
28. Mousavi,R., Sarmadian, F., Omid, M., & Bogaert, P. (2022). Three-dimensional mapping of soil organic carbon using soil and environmental covariates in an arid and semi-arid region of Iran. Measurement, 201, 111706. https://doi.org/10.1016/j.measurement.2022.111706
29. Mousavi, S.R., Jahandideh Mahjenabadi, V.A., Khoshru, B., & Rezaei, M. (2024). Spatial prediction of winter wheat yield gap: agro-climatic model and machine learning approaches. Frontiers in Plant Science, 14, https://doi.org/10.3389/fpls.2023.1309171
30. Muslim, W.A., Albayati, T.M., & Al-Nasri, S.K. (2022). Decontamination of actual radioactive wastewater containing 137Cs using bentonite as a natural adsorbent: equilibrium, kinetics, and thermodynamic studies. Scientific Reports, 12(1), 13837. https://doi.org/10.1038/s41598-022-18202-y
31. Nelson, M.A., Bishop, T.F.A., Triantafilis, J., & Odeh, I.O.A. (2011). An error budget for different sources of error in digital soil mapping. European Journal of Soil Science, 62(3), 417-430. https://doi.org/10.1111/j.13652389.2011. 01365.x
32. Parras‐Alcántara, L., Díaz‐Jaimes, L., & Lozano‐García, B. (2015). Management effects on soil organic carbon stock in Mediterranean open rangelands—treeless grasslands. Land Degradation & Development, 26(1), 22-34. https://doi.org/10.1002/ldr.2269
33. Rabbi, S.M.F., Roy, B.R., Miah, M.M., Amin, M.S., & Khandakar, T. (2014). Spatial variability of physical soil quality index of an agricultural field. Applied and Environmental Soil Science, 2014(1), 379012. https://doi.org/ 10.1155/2014/379012
34. Rahmani, A., Sarmadian, F., & Arefi, H. (2022). Digital mapping of top-soil thickness and associated uncertainty using machine learning approach in some part of arid and semi-arid lands of Qazvin plain. Iranian Journal of Soil and Water Research, 53(3), 585-602. https://doi.org/10.47176/jwss.24.2.32993
35. Rossel, R.V., & McBratney, A.B. (2008). Diffuse reflectance spectroscopy as a tool for digital soil mapping. In Digital soil mapping with limited data (pp. 165-172). Dordrecht: Springer Netherlands. https://doi.org/10.1007/ 978-1-4020-8592-5_13
36. Rostaminia, M., Rahmani, A., Mousavi, S.R., Taghizadeh-Mehrjardi, R., & Maghsodi, Z. (2021). Spatial prediction of soil organic carbon stocks in an arid rangeland using machine learning algorithms. Environmental Monitoring and Assessment, 193, 1-17. https://doi.org/10.1007/s10661-021-09543-8
37. Schillaci, C., Acutis, M., Lombardo, L., Lipani, A., Fantappie, M., Märker, M., & Saia, S. (2017). Spatio-temporal topsoil organic carbon mapping of a semi-arid Mediterranean region: The role of land use, soil texture, topographic indices and the influence of remote sensing data to modelling. Science of the Total Environment, 601, 821-832. https://doi.org/10.1016/j.scitotenv.2017.05.239
38. Song XiaoDong, S.X., Liu Feng, L.F., Zhang GanLin, Z.G., Li DeCheng, L.D., Zhao YuGuo, Z.Y., & Yang JinLing, Y.J. (2017). Mapping soil organic carbon using local terrain attributes: a comparison of different polynomial models. https://doi.org/10.1016/S1002-0160(17)60445-4
39. Su, L., Heydari, M., Jaafarzadeh, M.S., Mousavi, S.R., Rezaei, M., Fathizad, H., & Heung, B. (2024). Incorporating forest canopy openness and environmental covariates in predicting soil organic carbon in oak forest. Soil and Tillage Research, 244, https://doi.org/10.1016/j.still.2024.106220
40. Taghizadeh-Mehrjardi, R., Neupane, R., Sood, K., & Kumar, S. (2017). Artificial bee colony feature selection algorithm combined with machine learning algorithms to predict vertical and lateral distribution of soil organic matter in South Dakota, USA. Carbon Management, 8(3), 277-291. https://doi.org/10.1080/17583004.2017.1330593
41. Tibshirani, R.J., & Efron, B. (1993). An introduction to the bootstrap. Monographs on Statistics and Applied Probability, 57(1), 1-436.
42. Van Wambeke, A.R. (2000). The Newhall simulation model for estimating soil moisture and temperature regimes. Department of Crop and Soil Sciences. Cornell University, Ithaca, NY.
43. Vanwinckelen, G., & Blockeel, H. (2012). On estimating model accuracy with repeated cross-validation. In BeneLearn 2012: Proceedings of the 21st Belgian-Dutch conference on machine learning (pp. 39-44).
44. Vasiliniuc, I., Patriche, C.V., Pîrnău, R., & Roşca, B. (2013). Statistical spatial models of soil parameters. An approach using different methods at different scales. Environmental Engineering and Management Journal, 12(3), 457-464. https://doi.org/10.30638/eemj.2013.057
45. Voltz, M., Arrouays, D., Bispo, A., Lagacherie, P., Laroche, B., Lemercier, B., & Schnebelen, N. (2020). Possible futures of soil-mapping in France. Geoderma Regional, 23, https://doi.org/10.1016/j.geodrs.2020.e00334
46. Walkley, A., & Black, I.A. (1934). An examination of the Degtjareff method for determining soil organic matter, and a proposed modification of the chromic acid titration method. Soil Science, 37(1), 29-38. https://doi.org/10.1097/ 00010694-193401000-00003
47. Yang, L., Jia, W., Shi, Y., Zhang, Z., Xiong, H., & Zhu, G. (2020). Spatiotemporal differentiation of soil organic carbon of grassland and its relationship with soil physicochemical properties on the northern slope of Qilian mountains, China. Sustainability, 12(22), 9396. https://doi.org/10.3390/su12229396
48. Zaheri Abdehvand, Z., Karimi, D., Rangzan, K., & Mousavi, S.R. (2024). Assessment of soil fertility and nutrient management strategies in calcareous soils of Khuzestan province: a case study using the Nutrient Index Value method. Environmental Monitoring and Assessment, 196(6), 503. https://doi.org/10.1007/s10661-024-12665-4
49. Zeraatpisheh, M., Jafari, A., Bodaghabadi, M.B., Ayoubi, S., Taghizadeh-Mehrjardi, R., Toomanian, N., & Xu, M. (2020). Conventional and digital soil mapping in Iran: Past, present, and future. Catena, 188, https://doi.org/10.1016/j.catena.2019.104424
50. Zhao, S., Ayoubi, S., Mousavi, S.R., Mireei, S.A., Shahpouri, F., Wu, S.X., & Tian, C.Y. (2024). Integrating proximal soil sensing data and environmental variables to enhance the prediction accuracy for soil salinity and sodicity in a region of Xinjiang Province, China. Journal of Environmental Management, 364, 121311. https://doi.org/10.1016/j.jenvman.2024.121311
51. Zhou, T., Geng, Y., Chen, J., Liu, M., Haase, D., & Lausch, A. (2020). Mapping soil organic carbon content using multi-source remote sensing variables in the Heihe River Basin in China. Ecological Indicators, 114, 106288. https://doi.org/10.1016/j.ecolind.2020.106288