I was lucky to get a ticket to this well-attended EngTalk at the Institute of Engineering and Technology.
The idea of an Intelligent Digital Avatar conjures up many images from a complete virtual world that one can safely define, develop and play in to rogue robots running amok and destroying mankind. The reality is much less dramatic but no less far reaching and exciting.
This year’s Turing Talk will be delivered by Mark Girolami; an academic statistician and the Sir Kirby Laing Professorship of Civil Engineering at the University of Cambridge.
Mark will discuss Digital Twins and chart their history to present day technological capability, looking at some of the advances being made and the opportunities along with the open challenges faced to realise the potential of Digital Twins.
The historical part of this talk was very interesting, with examples from 100BC (the Antikythera, the Greek instrument used to predict astronomical positions and eclipses), Kelvin’s mechanical device for predicting tides (used up to 1940, including D-day landings) to weather balloons to model and predict atmospheric pressure.
Mark’s premise was that, whilst 2015 was about BigData, 2020 is about Digital twins – layering mathematical models over complex data streams in order to extract useful information. He stressed the importance of the provenance of information, error checking and acknowledging bias in such models. He was also keen to point out that models should not be used to blindly infer causation (an observed effect might be caused by some outside factor that was not understood or included in the model).