Rapid characterization of heavy metals in soil using a novel integrated strategy for near-infrared spectroscopy models
文献类型： 外文期刊
作者： Guo, Hairong;Guo, Mingdian;Liu, Yujia
作者机构：
关键词： Near infrared;Soil;Heavy metal;Integrated model;Machine learning;Deep learning
期刊名称： SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
ISSN： 1386-1425
年卷期： 2025 年 350 卷
页码：
收录情况： SCIE（2025版） ; ; EI（2025版）
摘要： As one of the critical natural resources sustaining human survival and sustainable development, soil quality directly underpins ecological security and the sustainability of agricultural production. Given the escalating severity of soil pollution, particularly heavy metals (HMs) contamination, the development of a standardized, efficient, and high-precision technology for acquiring soil HMs information has become an urgent necessity. Traditional research approaches have typically focused on using diverse models to independently predict and analyze different physical and chemical properties of soil. The research focus has largely centered on comparing the performance of various models, while overlooking the fundamental challenges of single models, such as limitations in universality and insufficient reproducibility. In this study, linear and nonlinear modeling approaches were employed, combined with multi-step spectral data processing procedures, to construct near-infrared spectral prediction models for HMs (taking Pb, Cd, and Cr in soil as examples). Furthermore, the inversion methods of soil HM contents and model selection were analyzed. On this basis, by integrating the model averaging strategy and weighted fusion strategy respectively, the limitations and instability of single model estimation were addressed by leveraging the operational characteristics of six sub-models. The results indicated that the complex architecture and parameter settings of nonlinear algorithms exhibit greater potential for inverting soil biochemical properties. Assigning different weights based on the predictive performance of sub-models can correct outliers occurring in single-model estimation. After applying the weighted fusion strategy, the average prediction errors for Pb, Cd, and Cr in soil were reduced to 2.12 %, 5.35 %, and 3.51 %, respectively. Compared with single-model prediction, the residual prediction deviations of the test set were improved by 0.43, 0.15, and 0.20, respectively. The integration strategy elevates the reference-level single models to a practically applicable level, thereby providing new insights for the subsequent development and optimization of soil regression models.
分类号：
- 相关文献
作者其他论文 更多>>
-
Fusion optimization: enhancing the efficacy of soil available heavy metal content prediction models leveraging novel near-infrared and mid-infrared spectroscopy technology
作者：Guo, Hairong;Guo, Mingdian;Liu, Yujia
关键词：Near-infrared;Mid-infrared;Fusion model;Heavy metal;Soil;Machine learning
-
Dietary fenugreek leaf powder improves growth performance, immune function, antioxidant status, and intestinal health in yellow-feathered broilers
作者：Cao, Hao;Qiu, Zhengying;He, Xin;Bai, Qiyu;Ge, Shaoguang;Shi, Xiongwei;Liu, Yujia;Xin, Ruihua
关键词：Yellow-feathered broiler;Fenugreek leaf powder;Growth performance;Antioxidant capacity;Gut microbiota
-
Mitigating selenium stress in Cyphomandra betacea seedlings through salicylic acid-induced growth and selenium uptake
作者：Li, Rui;Dai, Zhen;Liu, Yujia;Zhang, Ran;Cao, Yunfan;Yang, Qian;Liu, Xinglin;Zhang, Jing;Yi, Yingjin;Lin, Lijin
关键词：fruit trees;growth;physiology;plant growth regulator;selenium stress
-
Editing of eIF(iso)4E.c confers resistance against Turnip mosaic virus in Brassica rapa
作者：Liu, Yujia;Xin, Xiaoyun;Li, Peirong;Wang, Weihong;Yu, Yangjun;Zhao, Xiuyun;Zhang, Deshuang;Wang, Jiao;Zhang, Fenglan;Zhang, Shujiang;Yu, Shuancang;Su, Tongbing
关键词：Brassica rapa;eIF(iso)4E.c;TuMV;Ribo-seq
-
Rapid detection of chemical oxygen demand, pH value, total nitrogen, total phosphorus, and ammonia nitrogen in biogas slurry by near infrared spectroscopy
作者：Qiu, Jialing;Guo, Hairong;Xue, Yinghao;Liu, Qingyu;Xu, Zhiyu;He, Li
关键词：
-
A Novel NIR-Based Strategy for Rapid Freshness Assessment of Preserved Eggs
作者：Guo, Hairong;Bao, Zheng;Zhang, Shuoyao;Ran, Yi;Ning, Ruiting;Li, Yue;Zhang, Jichuan;Li, Jiarui;Liu, Qingyu;He, Li
关键词：Near infrared spectroscopy;Preserved egg;Total volatile base nitrogen;Interval successive projection algorithm;Partial least squares regression;Support vector machine regression
-
Gbabr1 Is Associated With Verticillium W.ilt Resistance In Cotton
作者：Shi, Yuzhen;Qin, Runkuan;Long, Lu;Zhang, Yuanyuan;Mo, Jianchuan;Cai, Yingfan;Cheng, Jieru;Chu, Zongyan;Liu, Yujia;Long, Lu;Wang, Weina;Wang, Weina;Liu, Xin;Li, Bo;Wang, Chenxiao;Xie, Yuanhui;Sun, Quan;Yuan, Youlu;Xu, Lingling
关键词：Gossypium barbadense; GbABR1; Transcription factor; Verticillium wilt; Function