Assessing the Climate Sensitivity of Soil Organic Carbon in China Based on Machine Learning and a Bottom-Up Framework
Abstract
:1. Introduction
2. Materials and Methods
2.1. SOC Data
2.2. Environmental Covariates
2.3. Data Preprocessing
2.4. Machine Learning Algorithms
2.4.1. Extreme Gradient Boosting (XGBoost)
2.4.2. Light Gradient Boosting Machine (LightGBM)
2.4.3. Gradient Boosting Machine (GBM)
2.4.4. Random Forest (RF)
2.4.5. Model Performance
2.5. SOCD Digital Soil Mapping
2.6. The Bottom-Up Approach for Vulnerability Analysis
3. Results
3.1. Statistical Analysis
3.2. Model Accuracy and Importance
3.3. Spatial Mapping and Uncertainty
3.4. Climate Sensitivity Analysis
4. Discussion
4.1. Model Performance Analysis
4.2. SOC Controlling Factors
4.3. Uncertainties and Prospect
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Hou, S.; Bai, Y.; Wang, C.; Zu, C.; Zhang, R.; Wang, X. Progress in the study of soil organic carbon and its active components. Jiangsu Agric. Sci. 2023, 51, 24–33. [Google Scholar] [CrossRef]
- Zhang, G.; Shi, Z.; Zhu, A.; Wang, Q.; Wu, K.; Shi, Z.; Zhao, Y.; Zhao, Y.; Pan, X.; Liu, F.; et al. Progress and Perspective of Studies on Soils in Space and Time. Acta Pedol. Sin. 2020, 57, 1060–1070. [Google Scholar]
- Wang, S.; Xu, L.; Adhikari, K.; He, N. Soil carbon sequestration potential of cultivated lands and its controlling factors in China. Sci. Total Environ. 2023, 905, 167292. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Z.; Ding, J.; Zhu, C.; Chen, X.; Wang, J.; Han, L.; Ma, X.; Xu, D. Bivariate empirical mode decomposition of the spatial variation in the soil organic matter content: A case study from NW China. Catena 2021, 206, 105572. [Google Scholar] [CrossRef]
- Li, H.; Wu, Y.; Liu, S.; Xiao, J.; Zhao, W.; Chen, J.; Alexandrov, G.; Cao, Y. Decipher soil organic carbon dynamics and driving forces across China using machine learning. Glob. Change Biol. 2022, 28, 3394–3410. [Google Scholar] [CrossRef]
- Zhang, L.; Heuvelink, G.B.M.; Mulder, V.L.; Chen, S.; Deng, X.; Yang, L. Using process-oriented model output to enhance machine learning-based soil organic carbon prediction in space and time. Sci. Total Environ. 2024, 922, 170778. [Google Scholar] [CrossRef]
- Su, H. Dimensionality reduction for hyperspectral remote sensing: Advances, challenges, and prospects. Natl. Remote Sens. Bull. 2022, 26, 1504–1529. [Google Scholar] [CrossRef]
- McBratney, A.B.; Mendonça Santos, M.L.; Minasny, B. On digital soil mapping. Geoderma 2003, 117, 3–52. [Google Scholar] [CrossRef]
- Zhu, A.; Yang, L.; Fan, N.; Tsang, C.-y.; Zhang, G. The review and outlook of digital soil mapping. Prog. Geogr. 2018, 37, 66–78. [Google Scholar]
- Popa, A.; Popa, I.; Badea, O.; Bosela, M. Non-linear response of Norway spruce to climate variation along elevational and age gradients in the Carpathians. Environ. Res. 2024, 252, 119073. [Google Scholar] [CrossRef]
- Zhang, Z.; Ding, J.; Zhu, C.; Wang, J.; Ge, X.; Li, X.; Han, L.; Chen, X.; Wang, J. Historical and future variation of soil organic carbon in China. Geoderma 2023, 436, 116557. [Google Scholar] [CrossRef]
- Sun, Z.; Xue, L.; Xu, Y.; Wang, Z. Overview of deep learning. Appl. Res. Comput. 2012, 29, 2806–2810. [Google Scholar]
- Zhang, Z.; Ding, J.; Zhu, C.; Shi, H.; Chen, X.; Han, L.; Wang, J. Changes in soil organic carbon stocks from 1980–1990 and 2010–2020 in the northwest arid zone of China. Land Degrad. Dev. 2022, 33, 2713–2727. [Google Scholar] [CrossRef]
- Shuai, M.; Tong, T.; Chunyang, Y.; Sweetie, W.; Mei, Z.; Mengmeng, T.; Tianpei, C.; Youhua, M.; Qiang, W. Advances in digital soil mapping based on machine learning. J. Agric. Resour. Environ. 2023, 41, 774. [Google Scholar] [CrossRef]
- Hengl, T.; de Jesus, J.M.; MacMillan, R.A.; Batjes, N.H.; Heuvelink, G.B.M.; Ribeiro, E.; Samuel-Rosa, A.; Kempen, B.; Leenaars, J.G.B.; Walsh, M.G.; et al. SoilGrids1km—Global Soil Information Based on Automated Mapping. PLoS ONE 2014, 9, e105992. [Google Scholar] [CrossRef]
- Zhang, G.-l.; Liu, F.; Song, X.-d. Recent progress and future prospect of digital soil mapping: A review. J. Integr. Agric. 2017, 16, 2871–2885. [Google Scholar] [CrossRef]
- Geremew, B.; Tadesse, T.; Bedadi, B.; Gollany, H.T.; Tesfaye, K.; Aschalew, A.; Tilaye, A.; Abera, W. Evaluation of RothC model for predicting soil organic carbon stock in north-west Ethiopia. Environ. Chall. 2024, 15, 100909. [Google Scholar] [CrossRef]
- Zhou, Y.; Chen, S.; Zhu, A.X.; Hu, B.; Shi, Z.; Li, Y. Revealing the scale- and location-specific controlling factors of soil organic carbon in Tibet. Geoderma 2021, 382, 114713. [Google Scholar] [CrossRef]
- Padarian, J.; Minasny, B.; McBratney, A.B. Machine learning and soil sciences: A review aided by machine learning tools. Soil 2020, 6, 35–52. [Google Scholar] [CrossRef]
- Pathak, R.; Dasari, H.P.; Ashok, K.; Hoteit, I. Effects of multi-observations uncertainty and models similarity on climate change projections. npj Clim. Atmos. Sci. 2023, 6, 144. [Google Scholar] [CrossRef]
- Thuiller, W.; Guéguen, M.; Renaud, J.; Karger, D.N.; Zimmermann, N.E. Uncertainty in ensembles of global biodiversity scenarios. Nat. Commun. 2019, 10, 1446. [Google Scholar] [CrossRef] [PubMed]
- Wang, Q.; Shan, Y.; Shi, W.; Zhao, F.; Li, Q.; Sun, P.; Wu, Y. Assessing spatiotemporal variations of soil organic carbon and its vulnerability to climate change: A bottom-up machine learning approach. Clim. Smart Agric. 2024, 1, 100025. [Google Scholar] [CrossRef]
- Singh, R.; Kumar, R. Vulnerability of water availability in India due to climate change: A bottom-up probabilistic Budyko analysis. Geophys. Res. Lett. 2015, 42, 9799–9807. [Google Scholar] [CrossRef]
- Zhao, F.; Wu, Y.; Qiu, L.; Sun, Y.; Sun, L.; Li, Q.; Niu, J.; Wang, G. Parameter Uncertainty Analysis of the SWAT Model in a Mountain-Loess Transitional Watershed on the Chinese Loess Plateau. Water 2018, 10, 690. [Google Scholar] [CrossRef]
- Xu, L.; Nianpeng, H.; Yu, G. A dataset of carbon density in Chinese terrestrial ecosystems (2010s). CSData 2019, 4, 90–96. [Google Scholar] [CrossRef]
- Zhu, C.; Li, Y.; Ding, J.; Rao, J.; Xiang, Y.; Ge, X.; Wang, J.; Wang, J.; Chen, X.; Zhang, Z. Spatiotemporal analysis of AGB and BGB in China: Responses to climate change under SSP scenarios. Geosci. Front. 2025, 16, 102038. [Google Scholar] [CrossRef]
- Chan, Y.; Liang, T.; Zhang, Y.; Wang, Y.; Yuan, D.; Zhu, J.; Li, D. Spatial Prediction of Soil Thicknesses in Sichuan Province Based on Feature-Ensemble Learning. Soils 2023, 55, 894–902. [Google Scholar] [CrossRef]
- Wang, S.C.; Huo, Y.; Mu, X.; Jiang, P.; Zhu, L.; Xun, S.; He, B.; Wu, W. Estimation of surface NO2 concentration in China based on extreme gradient boosted tree and deep learning methods. Acta Sci. Circumstantiae 2023, 43, 298–308. [Google Scholar] [CrossRef]
- Chen, T.; Jiao, J.; Zhang, Z.; Lin, H.; Zhao, C.; Wang, H. Soil quality evaluation of the alluvial fan in the Lhasa River Basin, Qinghai-Tibet Plateau. Catena 2022, 209, 105829. [Google Scholar] [CrossRef]
- Ju, Y. Carbon Emission Forecasting in China Based on Spatio-Temporal LightGBM Models. Master’s Thesis, Nanjing Post and Communications University, Nanjing, China, 2023. [Google Scholar]
- Friedman, J.H.J.A.o.S. Greedy function approximation: A gradient boosting machine. Ann. Stat. 2001, 29, 1189–1232. [Google Scholar] [CrossRef]
- Natekin, A.; Knoll, A. Gradient boosting machines, a tutorial. Front. Neurorobotics 2013, 7, 21. [Google Scholar] [CrossRef] [PubMed]
- Speiser, J.L.; Miller, M.E.; Tooze, J.; Ip, E. A comparison of random forest variable selection methods for classification prediction modeling. Expert Syst. Appl. 2019, 134, 93–101. [Google Scholar] [CrossRef] [PubMed]
- Zhang, Z.; Ding, J.; Zhu, C.; Wang, J.; Li, X.; Ge, X.; Han, L.; Chen, X.; Wang, J. Exploring the inter-decadal variability of soil organic carbon in China. Catena 2023, 230, 107242. [Google Scholar] [CrossRef]
- Li, C.; Frolking, S.; Frolking, T.A. A model of nitrous oxide evolution from soil driven by rainfall events: 1. Model structure and sensitivity. J. Geophys. Res. Atmos. 1992, 97, 9759–9776. [Google Scholar] [CrossRef]
- Piao, S.; Ciais, P.; Huang, Y.; Shen, Z.; Peng, S.; Li, J.; Zhou, L.; Liu, H.; Ma, Y.; Ding, Y.; et al. The impacts of climate change on water resources and agriculture in China. Nature 2010, 467, 43–51. [Google Scholar] [CrossRef] [PubMed]
- Yaduvanshi, A.; Nkemelang, T.; Bendapudi, R.; New, M. Temperature and rainfall extremes change under current and future global warming levels across Indian climate zones. Weather Clim. Extrem. 2021, 31, 100291. [Google Scholar] [CrossRef]
- Song, X.-D.; Wu, H.-Y.; Ju, B.; Liu, F.; Yang, F.; Li, D.-C.; Zhao, Y.-G.; Yang, J.-L.; Zhang, G.-L. Pedoclimatic zone-based three-dimensional soil organic carbon mapping in China. Geoderma 2020, 363, 114145. [Google Scholar] [CrossRef]
- Zhang, X.; Xue, J.; Chen, S.; Wang, N.; Shi, Z.; Huang, Y.; Zhuo, Z. Digital Mapping of Soil Organic Carbon with Machine Learning in Dryland of Northeast and North Plain China. Remote Sens. 2022, 14, 2504. [Google Scholar] [CrossRef]
- Li, Y.; Ru, s.; Zhao, T.; Yuan, J.; Liu, Y.; Lu, G.; Zhang, P. Advances in digital soil mapping methods. Chin. Agric. Sci. Bull. 2024, 40, 146–153. [Google Scholar] [CrossRef]
- Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. [Google Scholar]
- Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.-Y. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. In Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA, 4–9 December 2017. [Google Scholar]
- Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. [Google Scholar] [CrossRef]
- Wang, M.; Guo, X.; Zhang, S.; Xiao, L.; Mishra, U.; Yang, Y.; Zhu, B.; Wang, G.; Mao, X.; Qian, T.; et al. Global soil profiles indicate depth-dependent soil carbon losses under a warmer climate. Nat. Commun. 2022, 13, 5514. [Google Scholar] [CrossRef] [PubMed]
- Ai, J.; Zhang, Z.; Yang, C.; Cao, J.; Zhou, Z.; Ge, X.; Chen, X.; Wang, J. Unveiling the Dynamic Patterns and Driving Forces of Soil Organic Carbon in Chinese Croplands From 1980 to 2020. Land Degrad. Dev. 2025, 1085–3278. [Google Scholar] [CrossRef]
- Chen, X.; Liu, J.; Deng, Q.; Chu, K.W.; Zhou, G.; Zhang, D. Effects of precipitation intensity on soil organic carbon fractions and their distribution under subtropical forests of South China. Chin. J. Appl. Ecol. 2010, 21, 1210–1216. [Google Scholar] [CrossRef]
- Qian, Z. A Review of Research on Soil Organic Carbon Stocks and Their Drivers. J. Guangdong Seric. 2022, 56, 35–38. [Google Scholar]
- Cheng, W.; Zhou, C.; Li, B.; Shen, Y.; Zhang, B. Structure and contents of layered classification system of digital geomorphology for China. J. Geogr. Sci. 2011, 21, 771–790. [Google Scholar] [CrossRef]
Name | Abridge | Descriptive |
---|---|---|
Elevation | Slope | A geomorphic area where the surface line is at an angle to the horizon. |
Slope direction | Aspect | The angle between the projection of the normal to the tangent plane of a point on the horizontal plane and the due north direction of the point. |
Flat curvature | PC | The downhill direction of the maximum rate of change of each image element. |
Contour curvature | PrC | Geometric normal curvature along a slope line. |
Convergence index | CI | Describing terrain relief and topographic patterns and calculating the difference between the elevation of each image element and its neighboring elevations to compute the terrain position index. |
Depths of a valley | VD | Depth of the deepest valley in the contour curve over the base length. |
Slope position | RSP | The location of a geographic thing relative to some geographic thing. |
LS-Factor | LS | Parameters or indicators set for the study and expression of geomorphological features. |
Analytical Mountain Shadows | AH | The Mountain Shadows tool obtains an assumed illumination of a surface by determining the illumination for each image element in the raster. |
Closed depression | CD | Low-lying areas of fields that do not have outlets to accumulate or receive runoff are part of closed depressions. |
Total catchment area | TCA | The entire land area of a river or lake that provides surface runoff is called a watershed, river basin, or catchment area. |
Topographic humidity index | TWI | Physical indicators of the influence of regional topography on runoff flow direction and accumulation. |
Channel network basic level | CNB | Calculate the vertical distance to the basic level of the channel network. |
Channel network distance | CND | Calculate the vertical distance to the basic level of the channel network. |
RMSE (Kg C m−2) | R2 | Time (s) | Index | |
---|---|---|---|---|
XGB | 2.06 | 0.59 | 164.4 | 0.55 |
LGB | 2.1 | 0.58 | 175.2 | 0.53 |
RF | 2.0 | 0.61 | 2700 | 0.25 |
GBM | 2.33 | 0.48 | 2136.6 | 0.22 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Li, F.; Cao, J.; Ma, B.; Han, F.; Geng, J.; Zhong, J.; Wang, L.; Ma, Y. Assessing the Climate Sensitivity of Soil Organic Carbon in China Based on Machine Learning and a Bottom-Up Framework. Sustainability 2025, 17, 3965. https://doi.org/10.3390/su17093965
Li F, Cao J, Ma B, Han F, Geng J, Zhong J, Wang L, Ma Y. Assessing the Climate Sensitivity of Soil Organic Carbon in China Based on Machine Learning and a Bottom-Up Framework. Sustainability. 2025; 17(9):3965. https://doi.org/10.3390/su17093965
Chicago/Turabian StyleLi, Fujie, Jinhua Cao, Bin Ma, Feng Han, Jianyang Geng, Junhui Zhong, Longlong Wang, and Yu Ma. 2025. "Assessing the Climate Sensitivity of Soil Organic Carbon in China Based on Machine Learning and a Bottom-Up Framework" Sustainability 17, no. 9: 3965. https://doi.org/10.3390/su17093965
APA StyleLi, F., Cao, J., Ma, B., Han, F., Geng, J., Zhong, J., Wang, L., & Ma, Y. (2025). Assessing the Climate Sensitivity of Soil Organic Carbon in China Based on Machine Learning and a Bottom-Up Framework. Sustainability, 17(9), 3965. https://doi.org/10.3390/su17093965