Artificial intelligence in fluid dynamics and thermal transport: A comprehensive review of methods, challenges, and emerging applications
Bibliographic record
Abstract
Artificial intelligence (AI) is a transformative tool in fluid dynamics and thermal transport, unlocking new possibilities for modeling, prediction, diagnostics, and system optimization. AI-driven approaches, ranging from deep learning and machine learning to physics-informed neural networks, are increasingly combined with traditional methods to address challenges that are difficult to solve using solely physics-based models. Notably, recent developments have demonstrated the potential of AI in reconstructing turbulent flows, enhancing heat transfer performance, and enabling real-time simulations across a wide range of thermal-fluid systems. This includes complex configurations, such as multiphase flows and compact heat exchangers, where conventional modeling techniques often have limitations due to nonlinear interactions, multiscale behaviors, and geometric complexities. This review provides a structured synthesis of current advances for AI thermal-fluid sciences. Contributions are categorized by flow regimes, such as laminar, turbulent, and multiphase, and transport phenomena, including conduction, convection, radiation, and phase change. Key technical challenges, such as the scarcity of high-fidelity datasets, robust generalization across varying flow and boundary conditions, and integration of physical laws into data-driven frameworks are considered. Finally, emerging research directions with strong potential to accelerate innovation in the field, including AI-assisted turbulence modeling, flow reconstruction from sparse measurements, data-driven design of high-efficiency heat exchangers, and intelligent control of multiphase and reactive flow systems are presented.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".