From physics and biology to seismology and economics, the behaviour of countless systems is determined by impactful yet unlikely transitions between metastable states known as rare events, the study of which is essential for understanding and controlling the properties of these systems. Classical computational methods to sample rare events remain prohibitively inefficient and are bottlenecks for enhanced samplers that require prior data. Here we introduce a physics-informed machine learning framework, normalizing Flow enhanced Rare Event Sampler (FlowRES), which uses unsupervised normalizing flow neural networks to enhance Monte Carlo sampling of rare events by generating high-quality non-local Monte Carlo proposals. We validated FlowRES by sampling the transition path ensembles of equilibrium and non-equilibrium systems of Brownian particles, exploring increasingly complex potentials. Beyond eliminating the requirements for prior data, FlowRES features key advantages over established samplers: no collective variables need to be defined, efficiency remains constant even as events become increasingly rare and systems with multiple routes between states can be straightforwardly simulated.
Dr. Ni is an associate professor in the School of Chemistry, Chemical Engineering and Biotechnology in Nanyang Technological University, Singapore. He received his Ph.D of Physics in 2012 from Utrecht University (The Netherlands) working with Prof. Marjolein Dijkstra focusing on the computational study on the self-assembly of colloidal systems. From 2012 to 2014, he did his postdoc with Profs. Martien A.Cohen Stuart and Peter G. Bolhuis focusing on the self-assembly of fibril-forming polypeptides. In 2014 he was awarded the NWO VENl fellowship which is the most prestigious personal grant for young scientists in the Netherlands to start independent research lines. In 2016, he was awarded the Best Research Prize by the European Cooperation in Science and Technology(COST) Action - Flowing Matter [An annual prize for European Early Stage Researchers in soft matter within eight years after the date of PhD]. His research has been published in a number of top scientific journals, including Science, Nature, Nature Machine Intelligence, Nature Communications, Science Advances, PNAS, PRL, etc.