数字农科院2.0

High-performance prediction of soil organic carbon using automatic hyperparameter optimization method in the yellow river delta of China

文献类型： 外文期刊

作者： Yingqiang Song;Feng Wang;Weihao Yang;Ruilin Liang;Dexi Zhan;Meiyan Xiang;Xiaohang Yang;Rui Xu;Miao Lu

作者机构：

关键词： Deep learning;Farmland;Hyperparameter;Machine learning;Soil organic carbon

期刊名称： Computers and Electronics in Agriculture

ISSN： 0168-1699

年卷期： 2025 年 236 卷

页码：

收录情况： SCIE（2025版） ; ; EI（2025版）

摘要： Using machine learning (ML) and deep learning (DL) models to predict the spatial variability of soil organic carbon (SOC) is crucial for advancing carbon emission reduction strategies. However, inadequate hyperparameter tuning remains a key limitation, reducing the model fitting performance and prediction accuracy. Notably, high-performance models enabled by automatic hyperparameter optimization (AHPO) represent a novel approach to explain the complex relationships between environmental factors and SOC. In this study, we analyzed the prediction performance of ML models, such as gradient boosting decision tree (GBDT) and extreme gradient boosting (XGB), and DL models, including deep forest (DF) and convolutional neural network (CNN). These models were optimized using nature-inspired algorithms (grey wolf optimization (GWO) and hunter-prey optimization (HPO)) and mathematical-approximation algorithms (Bayesian optimization (BO) and tree-structured Parzen estimator (TPE). Furthermore, we derived the linear and nonlinear driving effects of environmental factors (soil, vegetation, texture, climate, and terrain) on SOC. We also identified direct and indirect response pathways using SHapley additive interpretation (SHAP), variogram decomposition (VD), hierarchical partitioning (HP), and structural equation model (SEM). Our results show that prediction models optimized with mathematical approximation algorithms, such as BO-DF (R2 = 0.76) and TPE-DF (R2 = 0.82), demonstrated the strongest nonlinear fitting ability between environmental factors and SOC. AHPO algorithms significantly improved the prediction performance of DL models, with R2 values for the four optimization methods increasing from 0.72 to 0.82. The generalization verification results indicate that the TPE-optimized model demonstrates strong robustness and achieves the highest accuracy (R2 > 0.7) for SOC prediction. The AHPO prediction model's hyperparameter combination achieves a balance between similarity and distinctiveness, where key performance-determining hyperparameters exhibit significant variation (i.e. non-similarity), enabling high-performance SOC predictions. The spatial mapping using the TPE-DF model revealed that areas with high SOC content are primarily concentrated in the southern and northeastern regions of the study area. Moreover, when the model's prediction accuracy (R2) exceeds 0.75, SHAP analysis identifies SoilAN, SoilAP, SoilAK, TMP, and PRE as the most influential environmental factors driving nonlinear changes in SOC. Similarly, VD and HP analyses highlight a synergistic linear contribution of soil and climate factors, accounting for 99.1 % of the variability in SOC. Interestingly, the path analysis further indicates that regional climate warming leads to surface soil desiccation and salinization, which significantly alters the SOC decomposition environment. High salt stress negatively affects microorganisms and crop root activity, ultimately enhancing SOC accumulation in surface soil. Overall, AHPO-empowered ML and DL methods exhibit strong feasibility for analyzing the response relationship between environmental factors and SOC. Therefore, these methods provide robust support for high-performance and high-precision SOC monitoring across spatial scales.

分类号：

  • 相关文献

[1]Assessing the impact of multi-source environmental variables on soil organic carbon in different land use types of China using an interpretable high-precision machine learning method. Feng Wang,Ruilin Liang,Shuyue Li,Meiyan Xiang,Weihao Yang,Miao Lu,Yingqiang Song. 2024

[2]HPO-empowered machine learning with multiple environment variables enables spatial prediction of soil heavy metals in coastal delta farmland of China. Yingqiang Song,Dexi Zhan,Zhenxin He,Wenhui Li,Wenxu Duan,Zhongkang Yang,Miao Lu. 2023

[3]Evaluation of Spatial Variability of Soil Nutrients in Saline–Alkali Farmland Using Automatic Machine Learning Model and Hyperspectral Data. Meiyan Xiang,Qianlong Rao,Xiaohang Yang,Xiaoqian Wu,Dexi Zhan,Jin Zhang,Miao Lu,Yingqiang Song. 2025

[4]Spatial Mapping of Soil CO2 Flux in the Yellow River Delta Farmland of China Using Multi-Source Optical Remote Sensing Data. Wenqing Yu,Shuo Chen,Weihao Yang,Yingqiang Song,Miao Lu. 2024

[5]Retrieval of chromium and mercury concentrations in agricultural soils: Using spectral information, environmental covariates, or a fusion of both?. Li Wang,Yong Zhou,Xiao Sun,Shangrong Wu,Lang Xia,Jing Sun,Yan Zha,Peng Yang. 2024

[6]Spatial Prediction of Soil Water Content by Bayesian Optimization–Deep Forest Model with Landscape Index and Soil Texture Data. Weihao Yang,Ruofan Zhen,Fanyue Meng,Xiaohang Yang,Miao Lu,Yingqiang Song. 2024

[7]Spatial variability of soil salinity in coastal saline-alkali farmlands: A novel approach integrating a stacked model with the reconstructed in-situ hyperspectral feature. Dexi Zhan,Yunting Liu,Weihao Yang,Miao Lu,Yingqiang Song. 2025

[8]Significant Improvement in Soil Organic Carbon Estimation Using Data-Driven Machine Learning Based on Habitat Patches. Yu W.,Zhou W.,Wang T.,Xiao J.,Peng Y.,Li H.,Li Y.. 2024

[9]Estimation of Soil Organic Carbon Density on the Qinghai–Tibet Plateau Using a Machine Learning Model Driven by Multisource Remote Sensing. Qi Chen,Wei Zhou,Wenjiao Shi. 2024

[10]Automatic freezing-tolerant rapeseed material recognition using UAV images and deep learning. Lili Li,Jiangwei Qiao,Jian Yao,Jie Li,Li Li. 2022

[11]Semi-Supervised Transformation and Deep Embedding-Based Anomaly Identification for Agricultural Internet of Things. Xiang Yin,Letian Wang,Weikuan Jia,Chengqian Jin. 2021

[12]Dairy farming in the era of artificial intelligence: trend or a real game changer?. Oscar R. Espinoza-Sandoval,Juan Carlos Angeles-Hernandez,Manuel Gonzalez-Ronquillo,Navid Ghavipanje,Naifeng Zhang,A. R. Bayat,Gonzalo Hervás,Ahmed E. Kholif,Marcello Mele,Juan J. Loor,Sokratis Stergiadis,Einar Vargas-Bello-Pérez. 2024

[13]Data-driven insights for enhanced cellulose conversion to 5-hydroxymethylfurfural using machine learning. Yanming Qiao,Ehsan Kargaran,Hao Ji,Meysam Madadi,Saeed Rafieyan,Dan Liu. 2025

[14]Recent advances of machine learning in the geographical origin traceability of food and agro-products: A review. Li, Jiali,Qian, Jianping,Chen, Jinyong,Ruiz-Garcia, Luis,Dong, Chen,Chen, Qian,Liu, Zihan,Xiao, Pengnan,Zhao, Zhiyao. 2025

[15]Rapid characterization of heavy metals in soil using a novel integrated strategy for near-infrared spectroscopy models. Guo, Hairong,Guo, Mingdian,Liu, Yujia. 2025

[16]A comparative study highlights superiority of LSTM in crop genomic prediction. Ruiqing Pan,Yaolong Yang,Yuanyuan Zhang,Qun Xu,Yue Feng,Junyu Chen,Wei Li,Shoupu He,Xinghua Wei,Mengchen Zhang. 2025

[17]Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data. Yingqiang Song,Mingzhu Ye,Zhao Zheng,Dexi Zhan,Wenxu Duan,Miao Lu,Zhenqi Song,Dengkuo Sun,Kaizhong Yao,Ziqi Ding. 2023

[18]Spatial variability of soil geochemical elements using a novel ecological factor-incorporated interpretable machine learning model in China's coastal saline-alkali farmlands. Jiazheng Li,Yunting Liu,Xiaohang Yang,Miao Lu,Yingqiang Song. 2025

[19]Analysis of land use change and its driving force in the Longitudinal Range-Gorge Region. Ll ZhengHai,Song GuoBao,Bao YaJing,Song GuoBao,Lo HaiYan,Ll ZhengHai,Wang HaiMei,Xu Tian,Cheng Yan.

[20]Study on Environmental Risk and Economic Benefits of Rotation Systems in Farmland of Erhai Lake Basin. Tang Qiu-xiang,Ren Tian-zhi,Schweers, Wilko,Liu Hong-bin,Lei Bao-kun,Zhang Gui-long,Lin Tao. 2012

作者其他论文 更多>>