ORIGINAL RESEARCH article
Front. Environ. Sci.
Sec. Environmental Informatics and Remote Sensing
This article is part of the Research TopicModeling for Environmental Pollution and Change, Volume IIView all 5 articles
Estimation of Heavy Metals in Agricultural Soil using Near-Infrared Spectroscopy with Improved Evolutionary Method
Provisionally accepted
- 1Guangzhou Huashang College, Guangzhou, China
- 2Mathematics Teaching and Research Group, Rongxian Experimental Senior Middle School, Yulin, China
- 3Guilin University of Technology, Guilin, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Monitoring and real-time detection of soil heavy metal pollution are crucial to ensuring the safety of agricultural food products. Conventional methods for determining heavy metal concentrations primarily require time and costs. This study investigates intelligent modeling approaches to serve online detection of soil heavy metal contamination. Based on Internet of Things communication, large-scale near-infrared (NIR) spectral data were collected from distributed sensors for federated analysis. In chemometric studies, the improved binary firefly algorithm (IBFA) is proposed for evolutionary variable selection, and the modified method of maximum information coefficient (MMIC) is designed to estimate the nonlinear correlation of unevenly distributed samples. Experimental soil data is collected from the Karst geology (in north side of Guangxi ZAR, China). The NIR calibration model is established by fusion of IBFA and the MMIC methods (denoted as IBFA+MMIC). The fusion model is applied for quantitative prediction targeting on four different heavy metals in the Karst soil samples. Results show that the IBFA+MMIC model is able to observe the high correlation coefficients over 0.9 and absolutely low prediction errors during model training, and is tested with the correlations very close to 0.9, while the testing errors are acceptably low. By comparison, these results outperform the counterpart models established by other cross combinations of FA/IBFA and MIC/MMIC. In summary, the proposed modeling methodology is effectively validated to be applicable for NIR quantitative analysis of different heavy metal contents in Karst soil data. Meanwhile, it provides critical technical support for the federated analytical performance of distributed sensing data, thereby facilitating precision soil management practices.
Keywords: distributed sensing, evolutionary method, Firefly algorithm(FA), Modified maximum information coefficient (MMIC), near-infrared spectroscopy, Soil heavy metal
Received: 29 Jun 2025; Accepted: 08 Dec 2025.
Copyright: © 2025 Hong, Zhang, Lin, Meng, Hou and Chen. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Huazhou Chen
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.