Artificial Intelligence for Sustainable Fuels and Applications in Thermal Engines

The transition to a sustainable energy future depends on the large-scale deployment of low- and zero-carbon fuels — including biofuels, synthetic fuels, non-carbon-based fuels, and solar fuels. Yet the design, production, and end-use optimization of these fuels present formidable scientific and engineering challenges: predicting the combustion behavior of novel fuel blends, accelerating chemical kinetic models for ammonia and hydrogen mixtures, and enabling real-time control of thermal engines running on highly variable bio- or synfuels.Artificial intelligence (AI) is transforming this landscape. Machine learning, deep learning, reinforcement learning, and physics-informed neural networks are driving breakthroughs across the entire sustainable fuel value chain — from AI-guided molecular discovery of next-generation biofuels and e-fuels, to surrogate modeling that accelerates reacting flow simulations by orders of magnitude, to digital twin-enabled autonomous control of gas turbines and internal combustion engines running on hydrogen or ammonia. Hybrid approaches that combine data-driven learning with physical constraints are opening new possibilities for smart, adaptive, and low-emission combustion systems.This Research Topic explores the cutting edge of AI applications in sustainable fuel science and engineering, with a particular focus on fuel generation, property prediction, combustion modeling, and end-use optimization in thermal engines. Contributions that leverage AI to accelerate the shift from fossil-based to truly sustainable fuel systems are welcome. Manuscripts focused solely on conventional fossil fuels, without a clear sustainable fuel context, fall outside the scope of Frontiers in Fuels.Areas within the scope of this collection include:o AI-driven discovery and design of sustainable fuels — including generative models and high-throughput virtual screening for novel fuel molecules, machine learning-assisted property prediction (e.g. cetane number, octane rating, energy density, viscosity), and data-driven blending optimization for bio-derived, synthetic, and hydrogen-carrier fuelso AI-enabled biomass conversion and biofuel production, including thermochemical and biochemical conversion, biofuel yield and product-quality prediction, and data-driven process optimizationo AI-assisted catalytic fuel synthesis and upgrading, CO₂-to-fuels, and renewable hydrogeno Machine learning for combustion kinetics, surrogate modeling, and CFD acceleration of sustainable fuels — encompassing AI-assisted chemical mechanism reduction, reaction rate prediction for e-fuels, ammonia, hydrogen, and biofuel blends, physics-informed neural networks for turbulent reacting flows, and surrogate models that replace computationally expensive CFD solvers in design and optimization loopso AI-enabled optimization and control of thermal engines using sustainable fuels — covering reinforcement learning and model predictive control for internal combustion engines and gas turbines, AI-based engine calibration and fuel-flexible adaptive control strategies, and neural network approaches to injection timing, ignition, and combustion phasing under variable fuel compositionso AI for emission prediction and aftertreatment management in sustainable fuel combustion — including machine learning models for NOₓ, soot, CO, and unburned hydrocarbon prediction, AI-driven optimization of selective catalytic reduction and particulate filter systems, and real-time sensor fusion approaches for on-board emission monitoringo Digital twins and AI-powered life-cycle integration for sustainable fuel systems — spanning physics-augmented digital twins for engine and fuel system monitoring, predictive maintenance, AI-assisted well-to-wheel and life-cycle assessment, and integrated supply chain optimization for sustainable fuel production and distribution. Topic editors: Huaiyu Wang, Cheng Shi Source: https://www.frontiersin.org/research-topics/83683/artificial-intelligence-for-sustainable-fuels-and-applications-in-thermal-engines