AI for materials discovery
Using machine learning to predict which new materials will have desired properties before synthesizing them in a lab.
Learn first
Traditional materials discovery works by making a substance, measuring its properties, adjusting, and repeating — a slow cycle that can take years per candidate. ML-based discovery inverts this: a model trained on known materials predicts properties across a vast space of possible compositions, so researchers synthesize only the candidates most likely to work. The hard part is that training data is sparse and biased toward materials already studied, so predictions far from known examples are unreliable. Experimental validation remains the only way to confirm a claim.
In megatrends
Related players
Finds citing this concept
Overall = breadth + depth + substance + ½·novelty + freshness (a small boost that halves each week)
The catalyst claim that grew in transit
An AI lab says it found platinum-free electrolysis catalysts at parity — and as the boast traveled from podcast to summit stage, its cost claim quietly multiplied tenfold with no new data behind it.
How this connects
Tap a node to open it