Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview.

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the 'recomposition' of chemical mixtures.

Sensitivity of pollutant concentrations in urban streets to asphalt and traffic-related emissions.

The higher concentrations of atmospheric particles, such as black carbon (BC) and organic matter (OM), detected in streets compared to the urban background are predominantly attributed to road traffic. The integration of this source of pollutant in air quality models nevertheless entails a high degree of uncertainty and some other sources may be missing. Through sensitivity scenarios, the impacts on pollutant concentrations of sensitivities related to traffic and road-asphalt emissions are evaluated.

Artificial intelligence-driven design of fuel mixtures.

High-performance fuel design is imperative to achieve cleaner burning and high-efficiency engine systems. We introduce a data-driven artificial intelligence (AI) framework to design liquid fuels exhibiting tailor-made properties for combustion engine applications to improve efficiency and lower carbon emissions. The fuel design approach is a constrained optimization task integrating two parts: (i) a deep learning (DL) model to predict the properties of pure components and mixtures and (ii) search algorithms to efficiently navigate in the chemical space.

Electrifying passenger road transport in India requires near-term electricity grid decarbonisation.

Battery-electric vehicles (BEV) have emerged as a favoured technology solution to mitigate transport greenhouse gas (GHG) emissions in many non-Annex 1 countries, including India. GHG mitigation potentials of electric 4-wheelers in India depend critically on when and where they are charged: 40% reduction in the north-eastern states and more than 15% increase in the eastern/western regions today, with higher overall GHGs emitted when charged overnight and in the summer. Self-charging gasoline-electric hybrids can lead to 33% GHG reductions, though they haven't been fully considered a mitigation option in India.