Stacked Ensemble Machine Learning for Range-Separation Parameters

Density functional theory-based high-throughput materials and drug discovery has achieved tremendous success in recent decades, but its power on organic semiconducting molecules suffered catastrophically from the self-interaction error until the nonempirical but expensive optimally tuned range-separated hybrid (OT-RSH) functionals were developed. An OT-RSH transitions from a short-range (semi)local functional to a long-range Hartree-Fock exchange at a distance characterized by a molecule-specific range-separation parameter (omega). Herein, we propose a stacked ensemble machine learning model that provides an accelerated alternative of OT-RSH based on system-dependent structural and electronic configurations. We trained ML-omega PBE, the first functional in our series, using a database of 1970 molecules with sufficient structural and functional diversity, and assessed its accuracy and efficiency using another 1956 molecules. Compared with nonempirical OT-omega PBE, ML-omega PBE reaches a mean absolute error of 0.00504a(0)(-1) for optimal omega's, reduces the computational cost by 2.66 orders of magnitude, and achieves comparable predictive power in optical properties.

Automated summary

The use of machine learning models has accelerated high-throughput materials and drug discovery based on density functional theory. Compared to nonempirical methods, this new approach has significantly improved in terms of computational efficiency, accuracy, and predictive power.