Perovskite crystals harvest sunlight almost as well as silicon, but cost pennies. Their trouble is an inborn fragility: from warmth and ordinary water in the air, they “get sick.” Inside, disorder builds up, and the shiny plate turns cloudy, losing its abilities within a couple of days.
Artificial intelligence becomes a diagnostic doctor. It performs spectroscopy — shining a light beam through the crystal and spotting micro-cracks before they appear. Then it sifts through thousands of additive recipes and finds a “medicine”—tiny particles that stitch up the lattice’s weak spots. In one experiment, the algorithm suggested embedding gold droplets, and the material lasted ten times longer.
A review of research showed: AI’s main talent is linking scattered observations into a sharp forecast. Already, such panel cells run trouble-free for thousands of hours, and in the future, algorithms will take over routine testing to speed up production.
Lev Perovsky collected minerals and never suspected his name would go down in physics history: the mineral he discovered now inspires the creation of cheap solar energy.