Optoelectronic stability of halide perovskite material in hostile conditions such as water is rather limited, preventing them from further industrial deployment. Here, we optimize and perform machine learning analysis on CH₃NH₃PbI₃ materials with additives, solvents and post-treatment molecules using combined experimental and data-driven methods. A champion system consisting of a compatible tertiary molecular combination ‘calcein+PbBr₂ + DMSO’ active at diverse surfaces is identified, delivering a large aqueous photoelectrochemical (PEC) photocurrent of 10^-5A/cm² and an improved aqueous stability of 92.5%. Subsequently, machine interpretation is provided to decouple the multi-molecule contributions with the assistance of genetic programming (GP) and extra-trees (ET) machine learning models, highlighting the intricate molecular features for the target outputs. The post-hoc density functional theory (DFT) calculation suggests the presence of multiple hydrogen bond and anion··π surface interactions to stabilize the interfacial structures. The present ‘PEC + GP + ET + DFT’ approach is suggested to be an effective approach to design and comprehensively evaluate molecule-modified materials.

卤化物钙钛矿材料在水等恶劣条件下的光电稳定性相当有限，阻碍了它们进一步的工业部署。在这里，我们结合实验和数据，对含有添加剂、溶剂和后处理分子的 CH ₃ NH ₃ PbI ₃ 材料进行优化和机器学习分析 -驱动方法。确定了由兼容的三级分子组合“钙黄绿素+PbBr ₂ + DMSO”组成的冠军系统，该组合在不同表面具有活性，可提供 10 ^-5 A 的大水相光电化学 (PEC) 光电流/cm ² 且水稳定性提高至 92.5%。随后，在遗传编程（GP）和额外树（ET）机器学习模型的帮助下，提供机器解释来解耦多分子贡献，突出目标输出的复杂分子特征。事后密度泛函理论（DFT）计算表明存在多个氢键和阴离子··π表面相互作用来稳定界面结构。目前的“PEC + GP + ET + DFT”方法被认为是设计和综合评估分子修饰材料的有效方法。