Predicting Spin-Crossover Behavior in Metal-Organic Frameworks from Limited and Noisy Data Using Quantile Active Learning

TL;DR

This paper presents a data-efficient machine learning approach using Quantile Regression Tree-based Active Learning to identify spin-crossover metal-organic frameworks from limited and noisy data, significantly accelerating materials discovery.

Contribution

The study introduces a novel active learning strategy that effectively handles noisy and scarce data to predict SCO behavior in MOFs, reducing computational costs and improving screening accuracy.

Findings

Active learning selected 200 MOFs for evaluation.

The Random Forest model recovered 82% of true positives.

The approach identified new high-confidence SCO MOFs.

Abstract

Spin-crossover (SCO) metal-organic frameworks (MOFs) hold great promise for sensing, spintronics, and gas-related applications, however, only a small number of SCO-active examples are known among the thousands of MOFs already synthesized. Computational screening enhanced by machine learning offers a powerful route to uncover these hidden candidates much more rapidly than trial-and-error experiments. However, progress is limited by the computational complexity of obtaining accurate adiabatic energy differences, as these typically require separate geometry optimizations for both spin states, a process that is technically challenging, prone to convergence failures, and difficult to automate at scale. To mitigate these issues, we introduce a data-efficient strategy based on Quantile Regression Tree-based Active Learning, designed to navigate large chemical spaces while remaining robust to noisy and scarce labels obtained from unrelaxed geometries. After actively selecting a 200-sized subset of representative MOFs for electronic-structure evaluation, a Random Forest regressor trained on this data accurately identifies SCO-relevant candidates despite label noise, recovering 82% of true positives with only two false negatives. Applying the model to the unlabeled dataset yields a new collection of high-confidence SCO MOFs, which we denote pSCO-105. This work shows that spin crossover can be reliably identified from limited and imperfect data through smart training-set selection, enabling accelerated screening of SCO MOFs.