Skip to main content
SpringerLink
Log in

Enhancing lead adsorption capacity prediction in biochar: a comparative study of machine learning models and parameter optimization

  • Research Article
  • Published:
Environmental Science and Pollution Research Aims and scope Submit manuscript

Abstract

Machine learning models for predicting lead adsorption in biochar, based on preparation features, are currently lacking in the environmental field. Existing conventional models suffer from accuracy limitations. This study addresses these challenges by developing back-propagation neural network (BPNN) and random forest (RF) models using selected features: preparation temperature (T), specific surface area (BET), relative carbon content (C), molar ratios of hydrogen to carbon (H/C), oxygen to carbon (O/C), nitrogen to carbon (N/C), and cation exchange capacity (CEC). The RF model outperforms BPNN, improving R2 by 10%. Additional features and particle swarm optimization enhance the RF model’s accuracy, resulting in an 8.3% improvement in R2, a decrease in RMSE by up to 56.1%, and a 55.7% reduction in MAE. The importance ranking of features places CEC > C > BET > O/C > H/C > N/C > T, highlighting the significance of CEC in lead adsorption. Strengthening the complexation effect may improve lead removal in biochar. This study contributes valuable insights for predicting and optimizing lead adsorption in biochar, addressing the accuracy gap in existing models. It lays the foundation for future investigations and the development of effective biochar-based solutions for sustainable lead removal in water remediation.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

References

  • Balyan AK, Ahuja S, Lilhore UK, Sharma SK, Manoharan P, Algarni AD, Elmannai H, Raahemifar K (2022) A hybrid intrusion detection model using ega-pso and improved random forest method. Sensors 22:5986

    Article  Google Scholar 

  • Bhagat SK, Paramasivan M, Al-Mukhtar M, Tiyasha T, Pyrgaki K, Tung TM, Yaseen ZM (2021) Prediction of lead (Pb) adsorption on attapulgite clay using the feasibility of data intelligence models. Environ Sci Pollut Res 28:31670–31688

    Article  CAS  Google Scholar 

  • Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  • Cantrell KB, Hunt PG, Uchimiya M, Novak JM, Ro KS (2012) Impact of pyrolysis temperature and manure source on physicochemical characteristics of biochar. Bioresour Technol 107:419–428

    Article  CAS  Google Scholar 

  • Cao H, Xin Y, Yuan Q (2016) Prediction of biochar yield from cattle manure pyrolysis via least squares support vector machine intelligent approach. Bioresour Technol 202:158–164

    Article  CAS  Google Scholar 

  • Chen C, Wang Z, Ge Y, Liang R, Hou D, Tao J, Yan B, Zheng W, Velichkova R, Chen G (2023) Characteristics prediction of hydrothermal biochar using data enhanced interpretable machine learning. Bioresour Technol 377:128893

    Article  CAS  Google Scholar 

  • Dai Y, Khandelwal M, Qiu Y, Zhou J, Monjezi M, Yang P (2022) A hybrid metaheuristic approach using random forest and particle swarm optimization to study and evaluate backbreak in open-pit blasting. Neural Comput Applic 34:6273–6288

    Article  Google Scholar 

  • Ghaedi AM, Baneshi MM, Vafaei A, Nejad ARS, Tyagi I, Kumar N, Galunin E, Tkachev AG, Agarwal S, Gupta VK (2018) Comparison of multiple linear regression and group method of data handling models for predicting sunset yellow dye removal onto activated carbon from oak tree wood. Environ Technol Innov 11:262–275

    Article  Google Scholar 

  • Goh AT (1995) Back-propagation neural networks for modeling complex systems. Artif Intell Eng 9:143–151

    Article  Google Scholar 

  • Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20:832–844

    Article  Google Scholar 

  • Iwendi C, Bashir AK, Peshkar A, Sujatha R, Chatterjee JM, Pasupuleti S, Mishra R, Pillai S, Jo O (2020) COVID-19 patient health prediction using boosted random forest algorithm. Front Public Health 8:357

    Article  Google Scholar 

  • Kanungo D, Naik B, Nayak J, Baboo S, Behera H (2015) An improved PSO based back propagation learning-MLP (IPSO-BP-MLP) for classification, Computational Intelligence in Data Mining-Volume 1: Proceedings of the International Conference on CIDM, 20-21 December 2014. Springer, pp 333–344

    Google Scholar 

  • Ke B, Nguyen H, Bui X-N, Bui H-B, Nguyen-Thoi T (2021) Prediction of the sorption efficiency of heavy metal onto biochar using a robust combination of fuzzy C-means clustering and back-propagation neural network. J Environ Manage 293:112808

    Article  CAS  Google Scholar 

  • Kennedy J, Eberhart R (1995) Particle swarm optimization, Proceedings of ICNN'95-international conference on neural networks. IEEE, pp 1942–1948

    Book  Google Scholar 

  • Kooh MRR, Thotagamuge R, Chau Y-FC, Mahadi AH, Lim CM (2022) Machine learning approaches to predict adsorption capacity of Azolla pinnata in the removal of methylene blue. J Taiwan Inst Chem Eng 132:104134

    Article  CAS  Google Scholar 

  • Li Y, Feng T, Wang Q (2020) Adsorption of lead in aqueous solution by crayfish shell-derived biochar. Indust Safety Environ Protect 46:93–96

    Google Scholar 

  • Mahesh B (2020) Machine learning algorithms-a review. Int J Sci Res 9:381–386

    Google Scholar 

  • Nieto PG, García-Gonzalo E, Lasheras FS, Paredes-Sánchez JP, Fernández PR (2019) Forecast of the higher heating value in biomass torrefaction by means of machine learning techniques. J Comput Appl Math 357:284–301

    Article  Google Scholar 

  • Saidulu D, Srivastava A, Gupta AK (2023) Elucidating the performance of integrated anoxic/oxic moving bed biofilm reactor: assessment of organics and nutrients removal and optimization using feed forward back propagation neural network. Bioresour Technol 371:128641

  • Seko A, Hayashi H, Nakayama K, Takahashi A, Tanaka I (2017) Representation of compounds for machine-learning prediction of physical properties. Physical Review B 95:144110

    Article  Google Scholar 

  • Shariati M, Mafipour MS, Mehrabi P, Bahadori A, Zandi Y, Salih MN, Nguyen H, Dou J, Song X, Poi-Ngian S (2019) Application of a hybrid artificial neural network-particle swarm optimization (ANN-PSO) model in behavior prediction of channel shear connectors embedded in normal and high-strength concrete. Appl Sci 9:5534

    Article  CAS  Google Scholar 

  • Soares APMR, de Oliveira CF, de Farias Silva CE, da Silva Gonçalves AH, de Souza Abud AK (2020) Random Forest as a promising application to predict basic-dye biosorption process using orange waste. J Environ Chem Eng 8:103952

    Article  Google Scholar 

  • Wang Y, Li L, D-d S, Liu W-t (2020) Copper and lead ion adsorption characteristics of modified corn stalk biochars. J Agro-Environ Sci 39:1303–1313

    Google Scholar 

  • Xiao X (2018) The study of biochar multi-level structures, structure-application relationships and sorption behaviors. Dissertation, Zhejiang University

  • Xu R, Pang Y (2020) Adsorption characteristics of rice husk biochar on low-concentration Pb (II) from water. Ind Water Treat 40:35–38

    Google Scholar 

  • Yuan J-H, Xu R-K, Zhang H (2011) The forms of alkalis in the biochar produced from crop residues at different temperatures. Bioresour Technol 102:3488–3497

    Article  CAS  Google Scholar 

  • Zhan Y, Luo Y, Deng X, Grieneisen ML, Zhang M, Di B (2018) Spatiotemporal prediction of daily ambient ozone levels across China using random forest for human exposure assessment. Environ Pollut 233:464–473

    Article  CAS  Google Scholar 

  • Zhang Y, Lin J, Liu Y, Xia J, Tong S (2015) Adsorption capability of biochar to lead lon. Environ Prot Chem Indus 35:177–181

    CAS  Google Scholar 

  • Zheng X, Nguyen H (2022) A novel artificial intelligent model for predicting water treatment efficiency of various biochar systems based on artificial neural network and queuing search algorithm. Chemosphere 287:132251

    Article  CAS  Google Scholar 

  • Zhu X, Li Y, Wang X (2019) Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions. Bioresour Technol 288:121527

    Article  CAS  Google Scholar 

Download references

Funding

This work was partially supported by the Natural Science Foundation of Hubei Province (No. 2022CFB052), the Engineering Research Center of Urban Disasters Prevention, and Fire Rescue Technology of Hubei Province.

Author information

Authors and Affiliations

  1. School of Civil Engineering, Wuhan University, Wuhan, China

    Jiatong Liang, Mingxuan Wu, Zhangyi Hu, Manyu Zhao & Yingwen Xue

Authors
  1. Jiatong Liang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingxuan Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhangyi Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Manyu Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yingwen Xue
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Jiatong Liang: conceptualization, data curation, methodology, software, writing—original draft. Mingxuan Wu: visualization, formal analysis, writing—review and editing. Zhangyi Hu: formal analysis, writing—review and editing. Manyu Zhao: writing—review and editing. Yingwen Xue: conceptualization, financial support, methodology, writing—review and editing.

Corresponding author

Correspondence to Yingwen Xue.

Ethics declarations

Ethical approval

We understand the critical importance of maintaining research integrity and upholding ethical standards in scientific publishing. To ensure the credibility of our work, we adhere to the following rules of good scientific practice: Our submitted work is original and has not been published elsewhere, in any form or language, except in cases where it builds upon previous research. We have not submitted the manuscript to more than one journal for simultaneous consideration. In the event of any prior publications or reuse of materials, we will provide full disclosure.

We pledge not to divide a single study into multiple parts to artificially increase the quantity of submissions or submit the same work to various journals over time. Each submission will present comprehensive and meaningful research outcomes.

We ensure that the results presented in the manuscript are accurate, transparent, and honest.

We avoid fabrication, falsification, and inappropriate data manipulation, including any image based alterations. Data acquisition, selection, and processing adhere to discipline-specific rules and ethical standards.

Consent to participate

All authors have approved to this submission to your esteemed journal. Its publication is also approved tacitly by the responsible authorities where the work was carried out. We agree that if accepted, the paper will not be published elsewhere in the same form, in English or in any other language, without the written consent of the Publisher.

Consent to publish

We confirm that publication of the paper has been tacitly approved by the relevant responsible authorities at the institution where the research was conducted.

Competing interests

The authors declare no competing interests.

Additional information

Responsible Editor: Tito Roberto Cadaval Jr

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

• Random forest shows superior performance in predicting lead adsorption by biochar.

• Particle swarm optimization brought significant improvements in model accuracy.

• The cation exchange capacity is vital in adsorbed lead biochar preparation.

• Offer insights for predicting and optimizing lead adsorption capacity in biochar.

Supplementary information

ESM 1

(DOCX 56 kb)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liang, ., Wu, M., Hu, Z. et al. Enhancing lead adsorption capacity prediction in biochar: a comparative study of machine learning models and parameter optimization. Environ Sci Pollut Res 30, 120832–120843 (2023). https://doi.org/10.1007/s11356-023-30864-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11356-023-30864-3

Keywords

Search

Navigation