Prediction of heavy metals adsorption by hydrochars and identification of critical factors using machine learning algorithms

Zhao, Fei; Tang, Lingyi; Jiang, Hanfeng; Mao, Y.; Song, Wenjing; Chen, Haoming

doi:10.1016/j.biortech.2023.129223

Cited by 19 publications

(6 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study conducted by Chen et al involved the development of four ML models for predicting the maximum adsorption capacity of hydrothermal carbon as well as an exploration of the key factors influencing its adsorption capacity. The results indicated that the gradient boosting decision tree model exhibited exceptional predictive capabilities [15]. The efficacy of ML techniques in addressing intricate nonlinear problems has been well established, demonstrating exceptional performance across various domains and, thus, enabling the application of machine learning in the field of tribology [16][17][18][19].…”

Section: Introductionmentioning

confidence: 93%

Prediction of the Tribological Properties of Polytetrafluoroethylene Composites Based on Experiments and Machine Learning

Yan,

Du,

Ren

et al. 2024

Polymers

View full text Add to dashboard Cite

Because of the complex nonlinear relationship between working conditions, the prediction of tribological properties has become a difficult problem in the field of tribology. In this study, we employed three distinct machine learning (ML) models, namely random forest regression (RFR), gradient boosting regression (GBR), and extreme gradient boosting (XGBoost), to predict the tribological properties of polytetrafluoroethylene (PTFE) composites under high-speed and high-temperature conditions. Firstly, PTFE composites were successfully prepared, and tribological properties under different temperature, speed, and load conditions were studied in order to explore wear mechanisms. Then, the investigation focused on establishing correlations between the friction and wear of PTFE composites by testing these parameters through the prediction of the friction coefficient and wear rate. Importantly, the correlation results illustrated that the friction coefficient and wear rate gradually decreased with the increase in speed, which was also proven by the correlation coefficient. In addition, the GBR model could effectively predict the tribological properties of the PTFE composites. Furthermore, an analysis of relative importance revealed that both load and speed exerted a greater influence on the prediction of the friction coefficient and wear rate.

show abstract

Section: Introductionmentioning

confidence: 93%

Prediction of the Tribological Properties of Polytetrafluoroethylene Composites Based on Experiments and Machine Learning

Yan,

Du,

Ren

et al. 2024

Polymers

View full text Add to dashboard Cite

show abstract

“…A decision tree is a typical classification method that has significant potential for applications in the field of information encryption and signal perception. 63 Here, due to the different fluorescence and phosphorescence properties of β-CD-p-BA/ PU and β-CD+p-BA/PU at different excitation wavelengths, we have developed a message encryption system by integrating them (Videos S3, S4). Since the two materials above have the same color in daylight, the information seen under normal conditions without UV light exposure is the number "8" (Figure 5a).…”

Section: ■ Information Encryption and Intelligent Control Systemmentioning

confidence: 99%

Jellyfish-Inspired Self-Healing Luminescent Elastomers Based on Borate Nanoassemblies for Dual-Model Encryption

Zhou,

Yang,

Liu

et al. 2024

Nano Lett.

View full text Add to dashboard Cite

Responsive luminescent materials that reversibly react to external stimuli have emerged as prospective platforms for information encryption applications. Despite brilliant achievements, the existing fluorescent materials usually have low information density and experience inevitable information loss when subjected to mechanical damage. Here, inspired by the hierarchical nanostructure of fluorescent proteins in jellyfish, we propose a self-healable, photoresponsive luminescent elastomer based on dynamic interface-anchored borate nanoassemblies for smart dual-model encryption. The rigid cyclodextrin molecule restricts the movement of the guest fluorescent molecules, enabling long room-temperature phosphorescence (0.37 s) and excitation wavelength-responsive fluorescence. The building of reversible interfacial bonding between nanoassemblies and polymer matrix together with their nanoconfinement effect endows the nanocomposites with excellent mechanical performances (tensile strength of 15.8 MPa) and superior mechanical and functional recovery capacities after damage. Such supramolecular nanoassemblies with dynamic nanoconfinement and interfaces enable simultaneous material functionalization and self-healing, paving the way for the development of advanced functional materials.

show abstract

“…The term "biochar" derives from the combination of "bio-," which stands for "biomass," and "char," meaning "charcoal." In recent years, BC has received widespread attention due to its potential application in carbon sequestration, soil amendment/remediation, wastewater treatment, and catalysis [2][3][4][5][6][7][8][9][10][11]. In particular, several ground-breaking studies have been carried out to investigate the potential of BC in alternative energy production and in the recovery of value-added chemicals/by-products [3].…”

Section: Introductionmentioning

confidence: 99%

Biochar-Derived Persistent Free Radicals: A Plethora of Environmental Applications in a Lights and Shadows Scenario

Alfei,

Pandoli

2024

Preprint

View full text Add to dashboard Cite

Biochar (BC) is a carbonaceous material obtained by pyrolysis at 200−1000 °C in the limited presence of O2 of different vegetable and animal biomass feedstocks. BC has demonstrated great potential, mainly in environmental applications, due to its high sorption ability and persistent free radicals (PFRs) content. These characteristics enable BCs to carry out the direct and PFRs-mediated removal/degradation of environmental organic and inorganic contaminants. The types of PFRs possibly present in BC depend mainly on the pyrolysis temperature and the kind of pristine biomass. Since they also can cause ecological and human damage, a systematic evaluation of the environmental behavior, risks, or management techniques of BC-derived PFRs is urgent. PFRs generally could consist of a mixture of carbon- and oxygen-centered radicals, and of oxygenated carbon-centered radicals, depending on the pyrolytic conditions. Here, to promote a more productive and beneficial use of BC and related PFRs and stimulate further studies to make them environmentally safer and less hazardous to humans, we have first reviewed the most common methods used to produce BC, its main environmental applications, the primary mechanisms by which BC remove xenobiotics, as well as the reported mechanisms for PFRs formation in BCs. Secondly, we have discussed the PFRs environmental migration and transformation; we have reported the main PFRs-mediated applications of BCs to degrade inorganic and organic pollutants, the correlated environmental potential risks, and the possible strategies to limit them.

show abstract

Prediction of heavy metals adsorption by hydrochars and identification of critical factors using machine learning algorithms

Cited by 19 publications

References 42 publications

Prediction of the Tribological Properties of Polytetrafluoroethylene Composites Based on Experiments and Machine Learning

Prediction of the Tribological Properties of Polytetrafluoroethylene Composites Based on Experiments and Machine Learning

Jellyfish-Inspired Self-Healing Luminescent Elastomers Based on Borate Nanoassemblies for Dual-Model Encryption

Biochar-Derived Persistent Free Radicals: A Plethora of Environmental Applications in a Lights and Shadows Scenario

Contact Info

Product

Resources

About