Aims & Scope

Aims

AI for Energy and Environment (AIEE) is a gold open-access journal, and aspires to become a premier global journal at the intersection of artificial intelligence (AI) and the energy and environmental sciences. It is dedicated to fostering the deep integration of theoretical, experimental, computational, and AI-driven approaches to accelerate discovery, design, and application in these fields. The journal bridges foundational disciplines such as physics, chemistry, mechanics, environmental science and engineering, and materials science and engineering, while incorporating emerging AI-driven experimental techniques, computational methodologies, and practical applications. It serves both interdisciplinary researchers and newcomers to the field. Although energy and environment derived by AI is still in its early developmental stages, it is reshaping multiple dimensions of energy and environmental sciences at an exponential pace, with its full synergistic potential yet to be fully realized. This journal aims to establish itself as a knowledge exchange hub for AI scientists, engineers, and researchers specializing in energy, environment, materials, chemistry, and physics. It is published quarterly online by Scilight Press.

Driven by advancements in data science, the internet, computer engineering, and digital technologies, the discovery and maturation of cutting-edge energy and environmental technologies have been significantly accelerated. By integrating AI into next-generation energy and environmental materials research, a new paradigm for discovery and optimization in these fields can be established. This integration is poised to substantially enhance the methodological frameworks of energy and environmental research. Leveraging AI, researchers can efficiently analyze large-scale datasets from experiments, simulations, manufacturing, industry, delivering material knowledge and technologies in a user-friendly manner to scientists, product developers, and manufacturers in the energy and environmental sectors. AIEE is expected to rapidly develop a more robust ecosystem based on energy and environmental informatics, creating opportunities and challenges for next-generation technologies and discoveries while advancing more efficient energy and environmental performance and mechanisms.

Scope

This journal is committed to building a platform for showcasing, exchanging, and publishing interdisciplinary research at the nexus of AI and energy, environmental sciences, breaking down barriers between energy technology, environmental science and engineering, materials science and engineering, data science and engineering, and artificial intelligence. Additionally, it focuses on innovative methodologies to address challenges posed by data noise, uncertainty, limited sample sizes, and other complexities, facilitating a qualitative leap from data to knowledge.  

Topics of interest include, but are not limited to:

  • Data acquisition, database construction, and multi-source data fusion for energy or environmental materials
  • Machine learning and statistical learning for energy or environmental technology
  • AI-driven discovery of next-generation energy or environmental materials  
  • AI-driven design and performance optimization of energy or environmental materials  
  • AI-driven advancements in energy or environmental technologies  
  • AI-driven cross-scale integrated computation and prediction for energy or environmental systems
  • AI-driven prediction of structure-property-application relationships in energy or environmental materials
  • AI synergy in energy or environmental technology research
  • High-throughput computation/simulation/prediction of energy and environmental materials using AI
  • High-throughput experimental techniques for energy and environmental materials
  • Software development and code implementation for computational modeling and machine learning algorithms in energy or environmental materials  

The journal strongly encourages authors to submit core digital data, along with any self-developed software toolkits to support the conclusions.