Automatic Prediction and Characterisation of Complex Chemical Reactions

大约90%的化工过程使用催化来控制反应活性和选择性，然而新催化剂的设计往往依赖于知情的反复试验才能取得进展。该项目将通过开发基于网络理论、大数据和机器学习的新模拟工具来直接应对催化剂设计的挑战。我们将开发新的计算方法来自动发现化学反应，使我们能够建立微观动力学模型来预测真实世界实验室实验的结果。这种多尺度方法将为催化剂的设计和优化提供一条新的直接途径。

Around 90% of all chemical processes use catalysis to control reactivity and selectivity, yet the design of new catalysts too often depends on informed trial-and-error to make progress. This project will directly address the challenge of catalyst design by developing new simulation tools based on network theory, big data and machine learning. We will develop new computational methods for auto-discovery of chemical reactions, enabling us to build microkinetic models to predict the outcomes of real-world laboratory experiments. This multi-scale approach will provide a new direct route towards catalyst design and optimization.