Machine learning-based exploration of biochar for environmental management and remediation.

Biochar has a wide range of applications, including environmental management, such as preventing soil and water pollution, removing heavy metals from water sources, and reducing air pollution. However, there are several challenges associated with the usage of biochar for these purposes, resulting in an abundance of experimental data in the literature. Accordingly, the purpose of this study is to examine the use of machine learning in biochar processes with an eye toward the potential of biochar in environmental remediation. First, recent developments in biochar utilization for the environment are summarized. Then, a bibliometric analysis is carried out to illustrate the major trends (demonstrating that the top three keywords are heavy metal, wastewater, and adsorption) and construct a comprehensive perspective for future studies. This is followed by a detailed review of machine learning applications, which reveals that adsorption efficiency and capacity are the primary utilization targets in biochar utilization. Finally, a comprehensive perspective is provided for the future. It is then concluded that machine learning can help to detect hidden patterns and make accurate predictions for determining the combination of variables that results in the desired properties which can be later used for decision-making, resource allocation, and environmental management.

Structure and activity relationship for CO and O2 adsorption over gold nanoparticles using density functional theory and artificial neural networks.

In this work, the structure and activity relationship for CO and O(2) adsorption over Au(2) to Au(10) clusters was investigated using density functional theory (DFT) and artificial neural networks as a part of ongoing studies in the literature to understand CO oxidation over gold nanoparticles. The optimum structures for the anionic, neutral, and cationic clusters were determined first using DFT. The structural properties such as binding energy, highest occupied molecular orbital-lowest unoccupied molecular orbital gap, ionization potential, and electron affinity as well as the adsorption energies of CO and O(2) were calculated using the same method at various values of user defined descriptors such as the size and charge of the cluster, the presence or absence of unpaired electron, and the coordination number of the adsorption site. Then, artificial neural network models were constructed to establish the relationship between these descriptors and the structural properties, as well as between the structural properties and the adsorption energies. It was concluded that the neural network models can successfully predict the adsorption energies calculated using DFT. The statistically determined relative significances of user defined descriptors and the structural properties on the adsorption energies were also found to be in good agreement with the literature indicating that this approach may be used for the other catalytic systems as well.