Spatial dynamics of soil organic carbon and total nitrogen concerning aggregate size fractions using machine learning models

Abstract

Spatial distribution of soil organic carbon (SOC), and total nitrogen (TN) contents in different aggregate fractions (DAFs) were investigated by applying multiple machine learning models (MLMs) i.e., cubist (CB), support vector regression (SVR), and random forest (RF), along with environmental variables in the framework of digital soil mapping (DSM). One hundred samples were taken from the soil surface layer (0−15 cm) in the Aji-Chai watershed, in northwestern Iran. TN and SOC were measured in three soil aggregate sizes (macro, meso, and micro-aggregates). Among the studied machine learning models (MLMs), the RF model revealed exceptional performance and the lowest uncertainty for predicting SOC and TN contents in DAFs. The R² values for the prediction of SOC in DAFs were 0.86 for SOC_macro, 0.83 for SOC_meso, and 0.81 for SOC_micro. For the TN content in different fractions, the R² values were ordered as 0.70 for TN_macro, 0.71 for TN_meso, and 0.73 for TN_micro, respectively. Variable importance analysis (VIA) results indicated that factors like vegetation indices such as Corrected transformed vegetation index (CTVI), and normalized difference vegetation index (NDVI), followed by topographic attributes, had a substantial impact in exploring SOC and TN contents in DAFs. In macro-aggregates, the highest SOC and TN contents were found in dense pasture, semi-dense vegetation, and orchards. Conversely, in meso- and micro-aggregates, the lowest contents were observed in rainfed agricultural lands, sparse pastures, and barren regions, respectively. The modeling results open new windows in the field of soil fertility and physics intending to link the content of SOC and TN variation in DAFs. Ultimatly, the RF model demonstrates strong predictive capabilities for SOC and TN contents in DAFs, achieving impressive R² values. Influential factors include vegetation indices and topography. The resulting prediction maps significantly enhance spatial planning and guide sustainable land management practices, effectively linking soil quality indicators to specific land-use types for improved soil health.

Graphical abstract

Keywords

remote sensing / machine learning / aggregates fraction / spatial distribution / sustainable soil management

Highlight

	● RF model outperformed other MLMs in predicting SOC and TN in different aggregate fractions.
	● The highest SOC and TN in macro-aggregates were observed in dense pasture, semi-dense, and orchards.
	● Vegetation indices and topography played a key role in SOC and TN contents in aggregates.
	● Modeling results offer insights into land use planning and sustainable land management practices.

References

[1] Ajami, M., Heidari, A., Khormali, F., Gorji, M., Ayoubi, S., 2016. Environmental factors controlling soil organic carbon storage in loess soils of a subhumid region, northern Iran. Geoderma281, 1–10.

[2] An, Y., Shim, W., Jeong, G., 2023. High-resolution digital soil maps of forest soil nitrogen across South Korea using three machine learning algorithms. Forests14, 1141.

[3] Andy, J., Reuter, H.I., Nelson, A., Guevara, E., 2008. Hole-Filled SRTM for the Globe Version 4, Available from the CGIAR-CSI SRTM 90m Database [Online]. Available at the website of SRTM Data.

[4] Ayoubi, S., Mirbagheri, Z., Mosaddeghi, M.R., 2020. Soil organic carbon physical fractions and aggregate stability influenced by land use in humid region of northern Iran. International Agrophysics34, 343–353.

[5] Bakhshandeh, E., Hossieni, M., Zeraatpisheh, M., Francaviglia, R., 2019. Land use change effects on soil quality and biological fertility: a case study in northern Iran. European Journal of Soil Biology95, 103119.

[6] Bardgett, R.D., Streeter, T.C., Bol, R., 2003. Soil microbes compete effectively with plants for organic-nitrogen inputs to temperate grasslands. Ecology84, 1277–1287.

[7] 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 Classification12, 937–952.

[8] 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. AgriEngineering6, 396–408.

[9] Bimüller, C., Kreyling, O., Kölbl, A., Von Lüetzow, M., Kögel-Knabner, I., 2016. Carbon and nitrogen mineralization in hierarchically structured aggregates of different size. Soil and Tillage Research160, 23–33.

[10] Bouasria, A., Bouslihim, Y., Gupta, S., Taghizadeh-Mehrjardi, R., Hengl, T., 2023. Predictive performance of machine learning model with varying sampling designs, sample sizes, and spatial extents. Ecological Informatics78, 102294.

[11] Breiman, L., 2001. Random forests. Machine Learning45, 5–32.

[12] Bremner, J.M., 1960. Determination of nitrogen in soil by the Kjeldahl method. The Journal of Agricultural Science55, 11–33.

[13] Bruce, R.C., Rayment, G.E., 1982. Analytical methods and interpretations used by the agricultural chemistry branch for soil and land use surveys. Queensland Department of Primary Industries. Bulletin QB82004.

[14] Chen, L., Ren, C.Y., Li, L., Wang, Y.Q., Zhang, B., Wang, Z.M., Li, L.F., 2019. A comparative assessment of geostatistical, machine learning, and hybrid approaches for mapping topsoil organic carbon content. ISPRS International Journal of Geo-Information8, 174.

[15] Chen, S.D., Arrouays, D., Mulder, V.L., Poggio, L., Minasny, B., Roudier, P., Libohova, Z., Lagacherie, P., Shi, Z., Hannam, J., Meersmans, J., Richer-De-forges, A.C., Walter, C., 2022. Digital mapping of GlobalSoilMap soil properties at a broad scale: a review. Geoderma409, 115567.

[16] Corsi, S., Friedrich, T., Kassam, A., Pisante, M., de Moraes Sà, J., 2012. Soil organic carbon accumulation and greenhouse gas emission reductions from conservation agriculture: a literature review. Food and Agriculture Organization of the United Nations (FAO), (Rome).

[17] Da Silva, B.C., De Mello Prado, R., Baio, F.H.R., Campos, C.N.S., Teodoro, L.P.R., Teodoro, P.E., Santana, D.C., Fernandes, T.F.S., Da Silva Junior, C.A., De Souza Loureiro, E., 2024. New approach for predicting nitrogen and pigments in maize from hyperspectral data and machine learning models. Remote Sensing Applications: Society and Environment33, 101110.

[18] Deng, L., Wang, G.L., Liu, G.B., Shangguan, Z.P., 2016. Effects of age and land-use changes on soil carbon and nitrogen sequestrations following cropland abandonment on the Loess Plateau, China. Ecological Engineering90, 105–112.

[19] Dou, Y.X., Yang, Y., An, S.S., Zhu, Z.L., 2020. Effects of different vegetation restoration measures on soil aggregate stability and erodibility on the loess Plateau, China. CATENA185, 104294.

[20] Egan, G., Crawley, M.J., Fornara, D.A., 2018. Effects of long-term grassland management on the carbon and nitrogen pools of different soil aggregate fractions. Science of the Total Environment 613–614, 613–614.

[21] Even, R.J., Cotrufo, M.F., 2024. The ability of soils to aggregate, more than the state of aggregation, promotes protected soil organic matter formation. Geoderma442, 116760.

[22] Fasaeiyan, N., Jung, S., Boudreault, R., Arenson, L.U., Maghoul, P., 2024. A review on mathematical modeling of microbial and plant induced permafrost carbon feedback. Science of the Total Environment939, 173144.

[23] Fissore, C., Dalzell, B.J., Berhe, A.A., Voegtle, M., Evans, M., Wu, A., 2017. Influence of topography on soil organic carbon dynamics in a Southern California grassland. CATENA149, 140–149.

[24] Ganuza, A., Almendros, G., 2003. Organic carbon storage in soils of the Basque Country (Spain): The effect of climate, vegetation type and edaphic variables. Biology and Fertility of Soils37, 154–162.

[25] Gunarathna, M.H.J.P., Sakai, K., Nakandakari, T., Momii, K., Kumari, M.K.N., 2019. Machine learning approaches to develop pedotransfer functions for tropical Sri Lankan soils. Water11, 1940.

[26] Guntiñas, M.E., Leirós, M.C., Trasar-Cepeda, C., Gil-Sotres, F., 2012. Effects of moisture and temperature on net soil nitrogen mineralization: a laboratory study. European Journal of Soil Biology48, 73–80.

[27] Heung, B., Ho, H.C., Zhang, J., Knudby, A., Bulmer, C.E., Schmidt, M.G., 2016. An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping. Geoderma265, 62–77.

[28] Jeong, G., Choi, K., Spohn, M., Park, S.J., Huwe, B., Ließ, M., 2017. Environmental drivers of spatial patterns of topsoil nitrogen and phosphorus under monsoon conditions in a complex terrain of South Korea. PLoS One12, e0183205.

[29] Jiang, X., Wright, A.L., Wang, X., Liang, F., 2011. Tillage-induced changes in fungal and bacterial biomass associated with soil aggregates: a long-term field study in a subtropical rice soil in China. Applied Soil Ecology48, 168–173.

[30] John, K., Bouslihim, Y., Ofem, K.I., Hssaini, L., Razouk, R., Okon, P.B., Isong, I.A., Agyeman, P.C., Kebonye, N.M., Qin, C.Z., 2022. Do model choice and sample ratios separately or simultaneously influence soil organic matter prediction? International Soil and Water Conservation Research 10, 470–486. DOI:10.1016/j.iswcr.2021.11.003.

[31] John, K., Isong, I.A., Kebonye, N.M., Ayito, E.O., Agyeman, P.C., Afu, S.M., 2020. Using machine learning algorithms to estimate soil organic carbon variability with environmental variables and soil nutrient indicators in an alluvial soil. Land9, 487.

[32] Kaur, B., Singh, B., Kaur, N., Singh, D., 2018. Phytoremediation of cadmium-contaminated soil through multipurpose tree species. Agroforestry Systems92, 473–483.

[33] Khosravani, P., Baghernejad, M., Moosavi, A.A., FallahShamsi, S.R., 2023. Digital mapping to extrapolate the selected soil fertility attributes in calcareous soils of a semiarid region in Iran. Journal of Soils and Sediments23, 4032–4054.

[34] King, A.E., Congreves, K.A., Deen, B., Dunfield, K.E., Voroney, R.P., Wagner-Riddle, C., 2019. Quantifying the relationships between soil fraction mass, fraction carbon, and total soil carbon to assess mechanisms of physical protection. Soil Biology and Biochemistry135, 95–107.

[35] Kou, D., Yang, G.B., Li, F., Feng, X.H., Zhang, D.Y., Mao, C., Zhang, Q.W., Peng, Y.F., Ji, C.J., Zhu, Q.A., Fang, Y.T., Liu, X.Y., Xu-Ri, Li, S.Q., Deng, J., Zheng, X.H., Fang, J.Y., Yang, Y.H., 2020. Progressive nitrogen limitation across the Tibetan alpine permafrost region. Nature Communications11, 3331.

[36] Lal, R., 2018. Digging deeper: A holistic perspective of factors affecting soil organic carbon sequestration in agroecosystems. Global Change Biology24, 3285–3301.

[37] Lamichhane, S., Kumar, L., Wilson, B., 2019. Digital soil mapping algorithms and covariates for soil organic carbon mapping and their implications: a review. Geoderma352, 395–413.

[38] Lee, S., Lee, S., Shin, J., Yim, J., Kang, J., 2020. Assessing the carbon storage of soil and litter from national forest inventory data in South Korea. Forests11, 1318.

[39] Lehmann, J., Kleber, M., 2015. The contentious nature of soil organic matter. Nature528, 60–68.

[40] Li, H.W., Wu, Y.P., Liu, S.G., Xiao, J.F., Zhao, W.Z., Chen, J., Alexandrov, G., Cao, Y., 2022. Decipher soil organic carbon dynamics and driving forces across china using machine learning. Global Change Biology28, 3394–3410.

[41] Li, Z.W., Liu, F., Peng, X.Y., Hu, B.G., Song, X.D., 2023. Synergetic use of DEM derivatives, sentinel-1 and sentinel-2 data for mapping soil properties of a sloped cropland based on a two-step ensemble learning method. Science of the Total Environment866, 161421.

[42] Liang, S., Chen, M., Xiao, S.B., Luo, Y.J., Yu, Z.F., Xu, H.T., 2021. Characteristics of nitrogen and phosphorus output in the small karst watershed of the Yangtze river in western Hubei. Resources and Environment in the Yangtze Basin30, 2471–2481.

[43] Liang, Y., 2021. Emerging threats to the stability of soil aggregates. Freie Universitaet Berlin, Berlin, Germany.

[44] Lv, H.Y., Feng, Q., 2019. A review of random forests algorithm. Journal of the Hebei Academy of Sciences36, 37–41.

[45] Ma, Z.Q., Shi, Z., Zhou, Y., Xu, J.F., Yu, W., Yang, Y.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 Environment200, 378–395.

[46] Mahjenabadi, V.A.J., Mousavi, S.R., Rahmani, A., Karami, A., Rahmani, H.A., Khavazi, K., Rezaei, M., 2022. Digital mapping of soil biological properties and wheat yield using remotely sensed, soil chemical data and machine learning approaches. Computers and Electronics in Agriculture197, 106978.

[47] Mason, R.E., Craine, J.M., Lany, N.K., Jonard, M., Ollinger, S.V., Groffman, P.M., Fulweiler, R.W., Angerer, J., Read, Q.D., Reich, P.B., Templer, P.H., Elmore, A.J., 2022. Evidence, causes, and consequences of declining nitrogen availability in terrestrial ecosystems. Science376, eabh3767.

[48] Minasny, B., McBratney, A.B., 2006. A conditioned Latin hypercube method for sampling in the presence of ancillary information. Computers & Geosciences32, 1378–1388.

[49] 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 Science14, 1309171.

[50] 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. CATENA232, 107392.

[51] Mousavi, S.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. Measurement201, 111706.

[52] Mustafa, A., Xu, M.G., Shah, S.A.A., Abrar, M.M., Sun, N., Wang, B.R., Cai, Z.J., Saeed, Q., Naveed, M., Mehmood, K., Núñez-Delgado, A., 2020. Soil aggregation and soil aggregate stability regulate organic carbon and nitrogen storage in a red soil of southern China. Journal of Environmental Management270, 110894.

[53] Naresh, R.K., Timsina, J., Bhaskar, S., Gupta, R.K., Singh, A.K., Dhaliwal, S.S., Rathore, R.S., Kumar, V., Singh, P., Singh, S.P., Tyagi, S.., 2017. Effects of tillage, residue and nutrient management on soil organic carbon dynamics and its fractions, soil aggregate stability and soil carbon sequestration: A review. EC Nutrition12, 53–80.

[54] Nawar, S., Mouazen, A.M., 2019. On-line vis-NIR spectroscopy prediction of soil organic carbon using machine learning. Soil and Tillage Research190, 120–127.

[55] Ogle, S.M., Olander, L., Wollenberg, L., Rosenstock, T., Tubiello, F., Paustian, K., Buendia, L., Nihart, A., Smith, P., 2014. Reducing greenhouse gas emissions and adapting agricultural management for climate change in developing countries: providing the basis for action. Global Change Biology20, 1–6.

[56] Okolo, C.C., Gebresamuel, G., Zenebe, A., Haile, M., Eze, P.N., 2020. Accumulation of organic carbon in various soil aggregate sizes under different land use systems in a semi-arid environment. Agriculture, Ecosystems & Environment297, 106924.

[57] Parsaie, F., Farrokhian Firouzi, A., Mousavi, S.R., Rahmani, A., Sedri, M.H., Homaee, M., 2021. Large-scale digital mapping of topsoil total nitrogen using machine learning models and associated uncertainty map. Environmental Monitoring and Assessment193, 162.

[58] Paul, B.K., Vanlauwe, B., Ayuke, F., Gassner, A., Hoogmoed, M., Hurisso, T.T., Koala, S., Lelei, D., Ndabamenye, T., Six, J., Pulleman, M.M., 2013. Medium-term impact of tillage and residue management on soil aggregate stability, soil carbon and crop productivity. Agriculture, Ecosystems & Environment164, 14–22.

[59] Peng, G., Bing, W., Guangpo, G., Guangcan, Z., 2013. Spatial distribution of soil organic carbon and total nitrogen based on GIS and geostatistics in a small watershed in a hilly area of northern China. PLoS One8, e83592.

[60] Peri, P.L., Rosas, Y.M., Ladd, B., Toledo, S., Lasagno, R.G., Pastur, G.M., 2019. Modeling soil nitrogen content in South Patagonia across a climate gradient, vegetation type, and grazing. Sustainability11, 2707.

[61] Poggio, L., De Sousa, L.M., Batjes, N.H., Heuvelink, G.B.M., Kempen, B., Ribeiro, E., Rossiter, D., 2021. SoilGrids 2.0: Producing soil information for the globe with quantified spatial uncertainty. SOIL 7, 217–240.

[62] Ren, W., 2019. Towards an integrated agroecosystem modeling approach for climate-smart agriculture management. In: Wendroth, O., Lascano, R.J., Ma, L., eds. Bridging among Disciplines by Synthesizing Soil and Plant Processes. Madison: ASA, CSSA, SSSA, 127–144.

[63] Rezaei, M., Mousavi, S.R., Rahmani, A., Zeraatpisheh, M., Rahmati, M., Pakparvar, M., Jahandideh Mahjenabadi, V.A., Seuntjens, P., Cornelis, W., 2023. Incorporating machine learning models and remote sensing to assess the spatial distribution of saturated hydraulic conductivity in a light-textured soil. Computers and Electronics in Agriculture209, 107821.

[64] Rossel, R.A.V., Lee, J., Behrens, T., Luo, Z., Baldock, J., Richards, A., 2019. Continental-scale soil carbon composition and vulnerability modulated by regional environmental controls. Nature Geoscience12, 547–552.

[65] 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 Assessment193, 815.

[66] Sarker, J.R., Singh, B.P., Cowie, A.L., Fang, Y.Y., Collins, D., Dougherty, W.J., Singh, B.K., 2018. Carbon and nutrient mineralisation dynamics in aggregate-size classes from different tillage systems after input of canola and wheat residues. Soil Biology and Biochemistry116, 22–38.

[67] Shrestha, D.L., Solomatine, D.P., 2006. Machine learning approaches for estimation of prediction interval for the model output. Neural Networks 19(2), 225–235.

[68] Soil Survey Staff, 2022. Keys to soil taxonomy. 13th ed. United States Department of Agriculture Natural Resources Conservation Service.

[69] Somasundaram, J., Chaudhary, R.S., Awanish Kumar, D., Biswas, A.K., Sinha, N.K., Mohanty, M., Hati, K.M., Jha, P., Sankar, M., Patra, A.K., Dalal, R., Chaudhari, S.K., 2018. Effect of contrasting tillage and cropping systems on soil aggregation, carbon pools and aggregate-associated carbon in rainfed Vertisols. European Journal of Soil Science69, 879–891.

[70] Somasundaram, J., Reeves, S., Wang, W.J., Heenan, M., Dalal, R., 2017. Impact of 47 years of no tillage and stubble retention on soil aggregation and carbon distribution in a Vertisol. Land Degradation & Development28, 1589–1602.

[71] Sommer, R., Bossio, D., 2014. Dynamics and climate change mitigation potential of soil organic carbon sequestration. Journal of Environmental Management144, 83–87.

[72] Song, Y.Q., Yang, L.A., Li, B., Hu, Y.M., Wang, A.L., Zhou, W., Cui, X.S., Liu, Y.L., 2017. Spatial prediction of soil organic matter using a hybrid geostatistical model of an extreme learning machine and ordinary kriging. Sustainability9, 754.

[73] Sönmez, O., Turan, V., Kaya, C., 2016. The effects of sulfur, cattle, and poultry manure addition on soil phosphorus. Turkish Journal of Agriculture and Forestry40, 536–541.

[74] Sorenson, P.T., Quideau, S.A., Rivard, B., 2018. High resolution measurement of soil organic carbon and total nitrogen with laboratory imaging spectroscopy. Geoderma315, 170–177.

[75] Su, L., Heydari, M., Mousavi, S.R., Prévosto, B., 2024. Role of environmental and stand factors on forest dieback: an approach using structural equation modelling and machine learning. Forest Ecology and Management562, 121927.

[76] Su, Z.W., Lin, L., Chen, Y.M., Hu, H.H., 2022. Understanding the distribution and drivers of PM_2.5 concentrations in the Yangtze River delta from 2015 to 2020 using random forest regression. Environmental Monitoring and Assessment94, 284.

[77] Sumfleth, K., Duttmann, R., 2008. Prediction of soil property distribution in paddy soil landscapes using terrain data and satellite information as indicators. Ecological Indicators8, 485–501.

[78] Szabó, B., Szatmári, G., Takács, K., Laborczi, A., Makó, A., Rajkai, K., Pásztor, L., 2019. Mapping soil hydraulic properties using random-forest-based pedotransfer functions and geostatistics. Hydrology and Earth System Sciences23, 2615–2635.

[79] Taghizadeh-Mehrjardi, R., Nabiollahi, K., Kerry, R., 2016. Digital mapping of soil organic carbon at multiple depths using different data mining techniques in Baneh region, Iran. Geoderma266, 98–110.

[80] 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 Management8, 277–291.

[81] Taghizadeh-Mehrjardi, R., Schmidt, K., Toomanian, N., Heung, B., Behrens, T., Mosavi, A., Band, S.S., Amirian-Chakan, A., Fathabadi, A., Scholten, T., 2021. Improving the spatial prediction of soil salinity in arid regions using wavelet transformation and support vector regression models. Geoderma383, 114793.

[82] Tajik, S., Ayoubi, S., Zeraatpisheh, M., 2020. Digital mapping of soil organic carbon using ensemble learning model in mollisols of hyrcanian forests, northern Iran. Geoderma Regional20, e00256.

[83] Taylor, K.E., 2001. Summarizing multiple aspects of model performance in a single diagram. Journal of Geophysical Research: Atmospheres106, 7183–7192.

[84] Tedone, L., Verdini, L., De Mastro, G., 2023. Effects of different types of soil management on organic carbon and nitrogen contents and the stability index of a durum wheat-faba bean rotation under a mediterranean climate. Agronomy13, 1298.

[85] Thomas, C., De Brito, J., Cimentada, A., Sainz-Aja, J.A., 2020. Macro- and micro- properties of multi-recycled aggregate concrete. Journal of Cleaner Production245, 118843.

[86] Toro-Manríquez, M., Soler, R., Lencinas, M.V., Promis, Á., 2019. Canopy composition and site are indicative of mineral soil conditions in Patagonian mixed Nothofagus forests. Annals of Forest Science76, 117.

[87] Turan, V., 2022. Calcite in combination with olive pulp biochar reduces Ni mobility in soil and its distribution in chili plant. International Journal of Phytoremediation24, 166–176.

[88] Turan, V., Schröder, P., Bilen, S., Insam, H., Juárez, M.F.D., 2019. Co-inoculation effect of Rhizobium and Achillea millefolium L. oil extracts on growth of common bean (Phaseolus vulgaris L.) and soil microbial-chemical properties. Scientific Reports9, 15178.

[89] Van Geel, M., Yu, K., Peeters, G., Van Acker, K., Ramos, M., Serafim, C., Kastendeuch, P., Najjar, G., Ameglio, T., Ngao, J., Saudreau, M., Castro, P., Somers, B., Honnay, O., 2019. Soil organic matter rather than ectomycorrhizal diversity is related to urban tree health. PLoS One14, e0225714.

[90] Van Groenigen, K.J., Qi, X., Osenberg, C.W., Luo, Y.Q., Hungate, B.A., 2014. Faster decomposition under increased atmospheric CO₂ limits soil carbon storage. Science344, 508–509.

[91] 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 Science37, 29–38.

[92] Wang, B., Waters, C., Orgill, S., Gray, J., Cowie, A., Clark, A., Liu, D.L., 2018. High resolution mapping of soil organic carbon stocks using remote sensing variables in the semi-arid rangelands of eastern Australia. Science of the Total Environment630, 367–378.

[93] Wang, C., Zheng, M.M., Song, W.F., Wen, S.L., Wang, B.R., Zhu, C.Q., Shen, R.F., 2017. Impact of 25 years of inorganic fertilization on diazotrophic abundance and community structure in an acidic soil in southern China. Soil Biology and Biochemistry113, 240–249.

[94] Wang, M.Y., Shi, X.Z., Yu, D.S., Xu, S.X., Tan, M.Z., Sun, W.X., Zhao, Y.C., 2013. Regional differences in the effect of climate and soil texture on soil organic carbon. Pedosphere23, 799–807.

[95] Wang, R.M., Zou, R.Y., Liu, J.M., Liu, L., Hu, Y.M., 2021. Spatial distribution of soil nutrients in farmland in a hilly region of the pearl river delta in China based on geostatistics and the inverse distance weighting method. Agriculture11, 50.

[96] Wang, S., Adhikari, K., Zhuang, Q.L., Yang, Z.J., Jin, X.X., Wang, Q.B., Bian, Z.X., 2020a. An improved similarity-based approach to predicting and mapping soil organic carbon and soil total nitrogen in a coastal region of northeastern China. PeerJ8, e9126.

[97] Wang, S., Gao, J.H., Zhuang, Q.L., Lu, Y.Y., Gu, H.L., Jin, X.X., 2020b. Multispectral remote sensing data are effective and robust in mapping regional forest soil organic carbon stocks in a northeast forest region in China. Remote Sensing12, 393.

[98] Wang, T., Kang, F.F., Cheng, X.Q., Han, H.R., Ji, W.J., 2016. Soil organic carbon and total nitrogen stocks under different land uses in a hilly ecological restoration area of North China. Soil and Tillage Research163, 176–184.

[99] Wilding, L.P., 1985. Spatial variability: Its documentation, accomodation and implication to soil surveys. In: Proceedings of the Soil Spatial Variability. Las Vegas: Pudoc, 166–194.

[100] Wu, T.H., Wang, D., Mu, C.C., Zhang, W.X., Zhu, X.F., Zhao, L., Li, R., Hu, G.J., Zou, D.F., Chen, J., Wei, X.H., Wen, A.M., Shang, C.P., La, Y., Lou, P.Q., Ma, X., Wu, X.D., 2022. Storage, patterns, and environmental controls of soil organic carbon stocks in the permafrost regions of the Northern Hemisphere. Science of the Total Environment828, 154464.

[101] Xu, Y.M., Li, B., Shen, X.B., Li, K., Cao, X.Y., Cui, G.N., Yao, Z.L., 2022. Digital soil mapping of soil total nitrogen based on landsat 8, sentinel 2, and WorldView-2 images in smallholder farms in Yellow River Basin, China. Environmental Monitoring and Assessment194, 282.

[102] Xu, Y.M., Wang, X.X., Bai, J.H., Wang, D.W., Wang, W., Guan, Y.N., 2020. Estimating the spatial distribution of soil total nitrogen and available potassium in coastal wetland soils in the Yellow River Delta by incorporating multi-source data. Ecological Indicators111, 106002.

[103] Yang, R.M., Zhang, G.L., Liu, F., Lu, Y.Y., Yang, F., Yang, F., Yang, M., Zhao, Y.G., Li, D., 2016. Comparison of boosted regression tree and random forest models for mapping topsoil organic carbon concentration in an alpine ecosystem. Ecological Indicators60, 870–878.

[104] Yang, Y.H., Li, M.J., Wu, J.C., Pan, X.Y., Gao, C.M., Tang, D.W.S., 2022. Impact of combining long-term subsoiling and organic fertilizer on soil microbial biomass carbon and nitrogen, soil enzyme activity, and water use of winter wheat. Frontiers in Plant Science12, 788651.

[105] Yost, J.L., Hartemink, A.E., 2019. Soil organic carbon in sandy soils: a review. Advances in Agronomy158, 217–310.

[106] Yu, X.Y., Zhao, G.X., Chang, C.Y., Yuan, X.J., Wang, Z.R., 2019. Random forest classifier in remote sensing information extraction: a review of applications and future development. Remote Sensing Information34, 8–14.

[107] Zapata-Rios, X., Brooks, P.D., Troch, P.A., McIntosh, J., Guo, Q.H., 2016. Influence of terrain aspect on water partitioning, vegetation structure and vegetation greening in high‐elevation catchments in northern new mexico. Ecohydrology9, 782–795.

[108] 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. Geoderma338, 445–452.

[109] Zeraatpisheh, M., Garosi, Y., Reza Owliaie, H., Ayoubi, S., Taghizadeh-Mehrjardi, R., Scholten, T., Xu, M., 2022. Improving the spatial prediction of soil organic carbon using environmental covariates selection: a comparison of a group of environmental covariates. CATENA208, 105723.

[110] Zeraatpisheh, M., Jafari, A., Bodaghabadi, M.B., Ayoubi, S., Taghizadeh-Mehrjardi, R., Toomanian, N., Kerry, R., Xu, M., 2020. Conventional and digital soil mapping in Iran: Past, present, and future. CATENA188, 104424.

[111] Zhang, L., Gao, F., Liu, D.Y., Wang, L., Xiang, R., Ye, C.H., Kang, C., Liu, C., Xiao, H., Xia, Z.Y., 2023. Estimating sheet erosion on purple soil hillslope treated with polyacrylamide (PAM) in the three gorges reservoir area. Journal of Hydrology: Regional Studies49, 101510.

[112] Zhang, Y., Sui, B., Shen, H.O., Ouyang, L., 2019. Mapping stocks of soil total nitrogen using remote sensing data: a comparison of random forest models with different predictors. Computers and Electronics in Agriculture160, 23–30.

[113] Zhao, Z.D., Zhao, M.S., Lu, H.L., Wang, S.H., Lu, Y.Y., 2023. Digital mapping of soil ph based on machine learning combined with feature selection methods in East China. Sustainability15, 12874.

[114] Zhou, T., Geng, Y.J., Chen, J., Sun, C.L., Haase, D., Lausch, A., 2019. Mapping of soil total nitrogen content in the middle reaches of the Heihe River Basin in China using multi-source remote sensing-derived variables. Remote Sensing11, 2934.

RIGHTS & PERMISSIONS

Higher Education Press