AUTHOR=Tobias Arianna G. , Kittur Javeed 

TITLE=Strategic innovations and future directions in deep learning for engineering applications: a systematic literature review

JOURNAL=Frontiers in Education

VOLUME=Volume 10 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/education/articles/10.3389/feduc.2025.1583404

DOI=10.3389/feduc.2025.1583404

ISSN=2504-284X

ABSTRACT=BackgroundDeep learning (DL), a subset of machine learning and artificial intelligence (AI), is transforming engineering by addressing complex problems with innovative solutions. Despite its growing influence, a comprehensive review of current trends, applications, and research gaps in engineering disciplines is essential to understand its full potential, limitations, and potential educational implications.PurposeThis study systematically explores the state, trends, and future directions of deep learning applications in engineering, and potential educational implications. The primary research question is: “What are the current applications, trends, and research gaps in the use of deep learning across engineering disciplines, and how can these insights guide future innovations in engineering practice?”MethodA systematic literature review (SLR) was conducted in three phases: identification, screening, and synthesis. Articles were retrieved using the search term “deep learning + engineering” from databases like IEEE Xplore, Web of Science, and Google Scholar. After removing duplicates from an initial pool of 346 articles, abstracts and full texts were screened based on predefined exclusion criteria, narrowing the selection to 101 relevant studies. The synthesis categorized data into four themes: strategic methodologies, practical implementation, system optimization, and emerging applications.ResultsThe analysis revealed DL's significant impact on engineering disciplines, especially mechanical and electrical engineering, with applications such as predictive maintenance and automated grid management. Key trends include strategic deep learning model development, practical evaluation frameworks, and the optimization of efficiency. However, research gaps remain in scalability, model interpretability, and real-world implementation.ConclusionsThis study underscores DL's transformative potential in engineering while identifying critical research gaps and opportunities. It provides a framework for future research and industry applications, emphasizing the importance of strategic innovation and interdisciplinary collaboration to advance deep learning in engineering.