An Intermediate-Aided\nPerovskite Phase Purification\nfor High-Performance Solar Cells

In\nrecent years, perovskite solar cells (PSCs) have garnered considerable\nattention as a prime candidate for next-generation photovoltaic technology.\nEnsuring the structural stability of perovskites is crucial to the\noperational reliability of these devices. However, the nonphotoactive\nyellow phase (δ-FAPbI<sub>3</sub>) of formamidine (FA)-based\nperovskites is more favorable in thermodynamics, making it challenging\nto achieve pure α phase in crystallization. Herein, we introduce\na language machine learning approach to analyze suitable additives\nto achieve the desired phase purification. By fast analyzing ∼10<sup>6</sup> abstracts in chemistry and materials science, our approach\nidentifies aminoguanidine (AG) hydrochloride as a promising candidate\nfor intermediate phase formation during nucleation. The experiments\nconfirm that AG forms a novel one-dimensional intermediate phase (AGPbI<sub>3</sub>), which suppresses the solvent intermediate phase and δ-phase\nformation and promotes development of the α-phase. Consequently,\nthe efficiency of the solar cells increased from 23.99 to 25.46%.\nThe long-term thermal stability and photostability were significantly\nenhanced owing to the purified α-phase, maintaining 82% of the\ninitial efficiency after 1056 h aging at 85 °C and 94.6% of the\ninitial efficiency after 835 h of illumination in an N<sub>2</sub> atmosphere, respectively. This strategy also enhanced the performance\nof flexible solar cells, increasing their efficiency from 21.24 to\n22.86%. This work is designed to fast explore new intermediate phases\nin improving the efficiency and operation stability of thin-film solar\ncells.