Imperial College London


Faculty of EngineeringDepartment of Earth Science & Engineering

Senior Lecturer in Data Science and Machine Learning



r.arcucci Website




Royal School of MinesSouth Kensington Campus





Data Assimilation ± Machine Learning = Data Learning

Elected member of the WMO (World Meteorological Organization), Rossella contributes to the development of AI models for Climate and Environmental impact as part of the data assimilation and observing systems working group.

Rossella is a Senior Lecturer in Data Science and Machine Learning at Imperial College London where she leads the Data Assimilation and Machine Learning (Data Learning) Group.

Rossella has been with the Data Science Institute at Imperial College since 2017, where she has created the Data Learning Group which is now a focal point for researchers and students of several departments at Imperial and other Universities in UK and Europe. 

Since February 2022, she is the elected speaker of the Artificial Intelligence Network of Excellence at Imperial College, where she represents ~300 academics working on AI.

She collaborates with the Leonardo Centre at Imperial College Business School, where she contributes to the development of integrative, just and sustainable models of economic and social development by discovering, testing and diffusing new logics of business enterprise.

The models Rossella has developed have produced impact in many applications such as finance (to estimate optimal parameters of economic models), social science (to merge twitter and pooling data to better estimate the sentiment of people), engineering (to optimise the placement of sensors and reduce the costs), geoscience (to improve accuracy of forecasting), climate changes and others. She has developed accurate and efficient models with data analysis, fusion and data assimilation for incomplete, noisy or Big Data problems, always including uncertainty quantifications and minimizations. 

She works on numerical and parallel techniques for accurate and efficient Data Assimilation and Machine Learning models. Efficiency is achieved by virtue of designing models specifically to take full advantage of massively parallel computers.

She finished her PhD in Computational and Computer Science in February 2012. She received the acknowledgement of Marie Sklodowska-Curie fellow from European Commission Research Executive Agency in Brussels in February 2017. 


She is CO-I of several funded projects:


She organises the annual workshop on Machine Learning and Data Assimilation for Dynamical Systems (MLDADS), a thematic track of the A-ranked International Conference on Computational Science (ICCS). Enjoy the videos of the previous editions of MLDADS




Zhou H, Cheng S, Arcucci R, 2024, Multi-fidelity physics constrained neural networks for dynamical systems, Computer Methods in Applied Mechanics and Engineering, Vol:420, ISSN:0045-7825

Hu J, Zhu K, Cheng S, et al., 2024, Explainable AI models for predicting drop coalescence in microfluidics device, Chemical Engineering Journal, Vol:481, ISSN:1385-8947

Cheng S, Liu C, Guo Y, et al., 2024, Efficient deep data assimilation with sparse observations and time-varying sensors, Journal of Computational Physics, Vol:496, ISSN:0021-9991

Kalaiarasan G, Kumar P, Tomson M, et al., 2024, Particle number size distribution in three different microenvironments of London, Atmosphere, Vol:15, ISSN:2073-4433

Liu C, Cheng S, Ding W, et al., 2023, Spectral Cross-Domain Neural Network With Soft-Adaptive Threshold Spectral Enhancement., Ieee Trans Neural Netw Learn Syst, Vol:PP

More Publications