Artificial intelligence for eco-design: a systematic review
Bibliographic record
Abstract
Eco-design integrates environmental considerations into product design, recognizing 80% of sustainability impacts determined at the design phase. Artificial intelligence (AI) provides powerful tools for optimizing designs, assessing environmental impacts, and supporting circular economy, making eco-design proactive. Despite AI use in sustainable product development, no review has synthesized these efforts. Therefore, we conducted a systematic review using the PRISMA method, covering 38 studies from 2014 to 2024 applied AI in eco-design. This is the first review to consider all life-cycle stages with eco-design practices, integrating Ellen MacArthur circularity principles, United Nations sustainable development goals (SDGs), life cycle assessment (LCA), industrial applications, and AI methods. Our findings reveal: 1- an imbalanced focus across product life-cycle stages, with most studies addressing design and end-of-life, while production, use-life, and distribution remain underexplored. 2- Common eco-design practices include recycling, energy reduction, and disassembly, with less focus on non-hazardous materials, waste minimization, and remanufacturing. 3- While neural networks and hybrid AI methods are commonly applied for material compatibility and emissions prediction, more advanced AI-based approaches such as generative AI and LLMs have yet to be used in design, LCA, and circularity analysis. 4- No study applies all four Ellen MacArthur Technosphere circular economy strategies. 5- Researchers rarely couple LCA with cradle-to-cradle assessments or embed their results in real-time design simulations. 6- Case studies mostly focus on electronics and household appliances, with limited application in automotive, aviation, maritime, and healthcare. 7- SDG consideration mainly centers on SDGs 12 and 13, with more attention needed for other SDGs.
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 | 0.010 | 0.051 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.006 |
| Bibliometrics | 0.013 | 0.013 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
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".