Machine learning assisted adsorption performance evaluation of biochar on heavy metal

Highlights

● A machine learning path for predicting biochar adsorption efficiency was constructed.

● Stacking model has exhibited better prediction accuracy and generalization ability.

● The proposed method could be used to optimize the preparation conditions of biochars.

Abstract

Heavy metals (HMs) represent pervasive and highly toxic environmental pollutants, known for their long latency periods and high toxicity levels, which pose significant challenges for their removal and degradation. Therefore, the removal of heavy metals from the environment is crucial to ensure the water safety. Biochar materials, known for their intricate pore structures and abundant oxygen-containing functional groups, are frequently harnessed for their effectiveness in mitigating heavy metal contamination. However, conventional tests for optimizing biochar synthesis and assessing their heavy metal adsorption capabilities can be both costly and tedious. To address this challenge, this paper proposes a data-driven machine learning (ML) approach to identify the optimal biochar preparation and adsorption reaction conditions, with the ultimate goal of maximizing their adsorption capacity. By utilizing a data set comprising 476 instances of heavy metal absorption by biochar, seven classical integrated models and one stacking model were trained to rapidly predict the efficiency of heavy metal adsorption by biochar. These predictions were based on diverse physicochemical properties of biochar and the specific adsorption reaction conditions. The results demonstrate that the stacking model, which integrates multiple algorithms, allows for training with fewer samples to achieve higher prediction accuracy and improved generalization ability.

Graphical abstract

Keywords

Machine learning / Biochar / Heavy metal / Adsorption efficiency

References

[1] Ahneman D T , Estrada J G , Lin S , Dreher S D , Doyle A G . (2018). Predicting reaction performance in C–N cross-coupling using machine learning. Science, 360(6385): 186–190

[2] Arora R . (2019). Adsorption of heavy metals: a review. Materials Today: Proceedings, 18: 4745–4750

[3] Balabin R M , Lomakina E I . (2011). Support vector machine regression (SVR/LS-SVM): an alternative to neural networks (ANN) for analytical chemistry? Comparison of nonlinear methods on near infrared (NIR) spectroscopy data. Analyst (London), 136(8): 1703–1712

[4] Breiman L . (2001). Random forests. Machine Learning, 45(1): 5–32

[5] Chen A , Zhang X , Zhou Z . (2020). Machine learning: accelerating materials development for energy storage and conversion. InfoMat, 2(3): 553–576

[6] Chen T , He T , Benesty M , Khotilovich V , Tang Y , Cho H , Chen K , Mitchell R , Cano I , Zhou T . (2015). Xgboost: extreme gradient boosting. R package version 0.4–2, 1(4): 1–4

[7] Greener J G , Kandathil S M , Moffat L , Jones D T . (2022). A guide to machine learning for biologists. Nature Reviews. Molecular Cell Biology, 23(1): 40–55

[8] GuoGWangHBellDBiYGreerK (2003). KNN model-based approach in classification. In: Robert M, Zahir T, eds. On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE. Berlin: Springer

[9] Jordan M I , Mitchell T M . (2015). Machine learning: Trends, perspectives, and prospects. Science, 349(6245): 255–260

[10] Kingsford C, Salzberg S L (2008). What are decision trees? Nature Biotechnology, 26(9): 1011–1013

[11] Lakshmi D , Akhil D , Kartik A , Gopinath K P , Arun J , Bhatnagar A , Rinklebe J , Kim W , Muthusamy G . (2021). Artificial intelligence (AI) applications in adsorption of heavy metals using modified biochar. Science of the Total Environment, 801: 149623

[12] Liu K , Guan X , Li C , Zhao K , Yang X , Fu R , Li Y , Yu F . (2022). Global perspectives and future research directions for the phytoremediation of heavy metal-contaminated soil: a knowledge mapping analysis from 2001 to 2020. Frontiers of Environmental Science & Engineering, 16(6): 73

[13] Mahesh B . (2020). Machine learning algorithms: a review. International Journal of Scientific Research, 9: 381–386

[14] Mao M , Yan T , Shen J , Zhang J , Zhang D . (2021). Capacitive removal of heavy metal Ions from wastewater via an electro-adsorption and electro-reaction coupling process. Environmental Science & Technology, 55(5): 3333–3340

[15] Natekin A , Knoll A . (2013). Gradient boosting machines, a tutorial. Frontiers in Neurorobotics, 7: 21–42

[16] Ni B J , Huang Q S , Wang C , Ni T Y , Sun J , Wei W . (2019). Competitive adsorption of heavy metals in aqueous solution onto biochar derived from anaerobically digested sludge. Chemosphere, 219: 351–357

[17] PavlyshenkoB (2018). Using Stacking Approaches for Machine Learning Models. IEEE International Conference on Data Stream Mining & Processing. New York: IEEE

[18] Qiao H , Qiao Y , Sun C , Ma X , Shang J , Li X , Li F , Zheng H . (2023). Biochars derived from carp residues: characteristics and copper immobilization performance in water environments. Frontiers of Environmental Science & Engineering, 17(6): 72

[19] Qin H , Hu T , Zhai Y , Lu N , Aliyeva J . (2020). The improved methods of heavy metals removal by biosorbents: a review. Environmental Pollution, 258: 113777

[20] Qiu B , Tao X , Wang H , Li W , Ding X , Chu H . (2021). Biochar as a low-cost adsorbent for aqueous heavy metal removal: a review. Journal of Analytical and Applied Pyrolysis, 155: 105081

[21] Rahimi M , Abbaspour-Fard M H , Rohani A . (2021). Machine learning approaches to rediscovery and optimization of hydrogen storage on porous bio-derived carbon. Journal of Cleaner Production, 329: 129714

[22] Rebuffi S A , Gowal S , Calian D A , Stimberg F , Wiles O , Mann T A . (2021). Data augmentation can improve robustness. Advances in Neural Information Processing Systems, 34: 29935–29948

[23] Santos J L , Mäki-Arvela P , Monzón A , Murzin D Y , Centeno M Á . (2020). Metal catalysts supported on biochars: Part I. Synthesis and characterization. Applied Catalysis B: Environmental, 268: 118423

[24] SeberG ALeeA J (2003). Linear Regression Analysis. New York: John Wiley & Sons

[25] ToyaoTMaenoZTakakusagiSKamachiTTakigawaIShimizuK I (2020 ). Machine learning for catalysis informatics: recent applications and prospects. ACS Catalysis, 10(3): 2260−2297

[26] Wang X , Sheng Y , Ning J , Xi J , Xi L , Qiu D , Yang J , Ke X . (2023). A critical review of machine learning techniques on thermoelectric materials. Journal of Physical Chemistry Letters, 14(7): 1808–1822

[27] ZarJ H (2005). Sepearman Rank Correlation. New York: John Wiley & Sons

[28] Zhang M , Song G , Gelardi D L , Huang L , Khan E , Masek O , Parikh S J , Ok Y S . (2020). Evaluating biochar and its modifications for the removal of ammonium, nitrate, and phosphate in water. Water Research, 186: 116303

[29] ZhouZ H (2021). Machine Learning. Berlin: Springer Nature

Acknowledgements

This work was financially supported by the National Key Research and Development Program of China (No. 2021YFC1808902), the National Natural Science Foundation of China (No. 42307546), the Key Research and Development Program of Shaanxi Province (China) (Nos. 2019NY200, 2020ZDLNY06-06, and 2020ZDLNY07-10), and the Agricultural Technology Innovation Driven Program of Shaanxi Province (China) (No. NYKJ-2022-XA-02). All the data that support the results of this study are available from the corresponding author.

Conflict of Interests

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Electronic Supplementary Material

Supplementary material is available in the online version of this article at https://doi.org/10.1007/s11783-024-1815-4 and is accessible for authorized users.

Data Accessibility Statement

The data and the code that support the findings of this study are openly available in Github at https://github.com/pwYan/adsorption.

RIGHTS & PERMISSIONS

2024 Higher Education Press 2024