Themed collection Machine learning and artificial neural networks: Celebrating the 2024 Nobel Prize in Physics

With increased awareness of artificial intelligence-based algorithms coupled with the non-stop creation of material databases, artificial intelligence (AI) can facilitate fast development of high-performance electrochemical energy storage systems (EESSs).

Artificial Neural Networks (NN) are already heavily involved in methods and applications for frequent tasks in the field of computational chemistry such as representation of potential energy surfaces (PES) and spectroscopic predictions.

This review summarises recent advances in the use of machine learning for predicting friction and wear in tribological systems, material discovery, lubricant design and composite formulation. Potential future applications and areas for further research are also discussed.

Natural products (NPs) are primarily recognized as privileged structures to interact with protein drug targets.

Evaluating the advantages and limitations of applying machine learning for prediction and optimization in porous media, with applications in energy, environment, and subsurface studies.

AI enabled imaging technology advances the precision, early detection, and personalizes treatment through analysis and interpretation of medical images.

Machine learning techniques for the development of neuromorphic materials for bioengineering solutions by developing energy-efficient hardware, enhancing neuron models, and learning algorithms.

This review offers a guideline for selecting the ML-based inverse design method, considering data characteristics and design space size. It categorizes challenges and underscores the proper methods, with a focus on composites and its manufacturing.

Molecular descriptors and machine learning are useful tools for extracting structure–property relationships from large, complex polymer data, and accelerating the design of novel polymers with tailored functionalities.

This review discusses three types of soft matter and liquid molecular materials, namely hydrogels, liquid crystals and gas bubbles in liquids, which are explored with an emergent machine learning approach.

This review compares machine learning approaches for property prediction of materials, optimization, and energy storage device health estimation. Current challenges and prospects for high-impact areas in machine learning research are highlighted.

The cross-fertilisation between the listed disciplines with a long standing knowledge on the application of artificial intelligence protocols and electron microscopy for materials science can entail the next breakthroughs in the field.

Machine learning (ML) integrated density functional theory (DFT) calculations have recently been used to accelerate the design and discovery of heterogeneous catalysts such as single atom catalysts (SACs) through the establishment of deep structure–activity relationships.

Understand and optimize industrial processes via machine learning and chemical engineering principles.

Neural networks are used to predict iridium phosphor excited state properties at accuracy competitive with TDDFT, enabling high-throughput screening.

Recurrent neural networks as a machine learning tools are gaining popularity in chemical, physical and materials applications searching for viable methods in the structure and energetics analyses of systems ranging from crystals to soft matter.

This paper presents the use of a machine learning approach to predict the performance of a Gaza wastewater treatment plant.

Our work introduces an innovative deep machine learning framework to significantly accelerate novel materials discovery, as demonstrated by its application to the La–Si–P system where new ternary and quaternary compounds were successfully identified.

We report the development of machine learning model for the calculation of carbon dioxide solubilities in deep solvent solvents. This model helps to predict and accelerate the development of carbon capture solvents with ideal experimental conditions.

Artificial neural networks trained on 23 density functional approximations (DFAs) from multiple rungs of “Jacob's ladder” enable the prediction of where each DFA has zero curvature for chemical discovery.

Ensemble-hybrid ML models can explain and predict the variability in water quality parameters and living microorganism behavior in natural streams with satisfactory prediction accuracies based on specific physicochemical parameters.

Supervised machine learning models are trained on experimental data to predict the mechanical properties of composite materials. Results show that these techniques are reasonably accurate and generalizable.

Reduced graphene oxide/metal organic framework based electrochemical sensor coupled with machine learning for sensitive detection of penta-chlorophenol.

Detection of bronchiectasis from exhaled breath.

A novel technology of doping potassium ions to enhance the synaptic characteristics of synaptic thin-film transistors. The classifier of Spiking Neural Network with significant energy efficiency was successfully operated based on the proposed device.

A supervised machine learning algorithm is developed to determine the concentrations of chemical species in multicomponent solutions from their Fourier transform infrared (FTIR) spectra.