Answers are grounded in this paper and cite their sources.
Artificial intelligence (AI) is rapidly expanding the engineer’s toolkit, but how do we decide when it is the right tool for the job? This article looks beyond the hype to consider how machine learning (ML), physics-based models and statistical methods can each support better engineering decisions. Using examples from flood forecasting, risk assessment and infrastructure monitoring, it shows where AI can create genuine value: accelerating computationally demanding simulations, extracting insight from large spatial datasets and identifying complex patterns in observations. It also explores the growing potential of hybrid modelling, where ML complements established engineering methods by refining predictions or emulating physics-based models at much greater speed.
No takes yet. Share an insight, caveat, or question.
Roberts et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: