Perspective: Towards sustainable exploration of chemical spaces with machine learning

TL;DR

This paper discusses the sustainability challenges in AI-driven molecular discovery, emphasizing resource-efficient strategies like multi-fidelity models, physics constraints, and open data to promote responsible scientific progress.

Contribution

It highlights emerging methods and workflows that improve efficiency and sustainability in AI-based chemical space exploration, integrating physics and practical considerations.

Findings

Large quantum datasets enable benchmarking but increase energy costs.

Strategies like multi-fidelity models and active learning improve efficiency.

Hierarchical workflows with physics constraints optimize resource use.

Abstract

Artificial intelligence is transforming molecular and materials science, but its growing computational and data demands raise critical sustainability challenges. In this Perspective, we examine resource considerations across the AI-driven discovery pipeline--from quantum-mechanical (QM) data generation and model training to automated, self-driving research workflows--building on discussions from the ``SusML workshop: Towards sustainable exploration of chemical spaces with machine learning'' held in Dresden, Germany. In this context, the availability of large quantum datasets has enabled rigorous benchmarking and rapid methodological progress, while also incurring substantial energy and infrastructure costs. We highlight emerging strategies to enhance efficiency, including general-purpose machine learning (ML) models, multi-fidelity approaches, model distillation, and active learning. Moreover, incorporating physics-based constraints within hierarchical workflows, where fast ML surrogates are applied broadly and high-accuracy QM methods are used selectively, can further optimize resource use without compromising reliability. Equally important is bridging the gap between idealized computational predictions and real-world conditions by accounting for synthesizability and multi-objective design criteria, which is essential for practical impact. Finally, we argue that sustainable progress will rely on open data and models, reusable workflows, and domain-specific AI systems that maximize scientific value per unit of computation, enabling efficient and responsible discovery of technological materials and therapeutics.