# 'Crafting Digital Twins' Seminar Series :::info **Today's Topic: Research Roundup** Date & Time: 2pm, hybrid at Alan Turing Institute, Margaret Hamilton Meeting Room Zoom Link: [Here](https://eur01.safelinks.protection.outlook.com/ap/t-59584e83/?url=https%3A%2F%2Fteams.microsoft.com%2Fl%2Fmeetup-join%2F19%3Ameeting_NjgzMGNiNGYtMjg5ZS00ZTVjLWE4MGQtYjBlNjRhYWY0YTRi%40thread.v2%2F0%3Fcontext%3D%257B%2522Tid%2522%3A%25224395f4a7-e455-4f95-8a9f-1fbaef6384f9%2522%2C%2522Oid%2522%3A%252270bc8ec4-6733-497e-9c2a-a2fd7c6a7a06%2522%257D&data=05%7C01%7Csarana%40turing.ac.uk%7C0efdba93509645bd8dda08dbf4d3c0c8%7C4395f4a7e4554f958a9f1fbaef6384f9%7C0%7C0%7C638372962734696386%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C3000%7C%7C%7C&sdata=zTdOmd8KpN9%2Bu%2FqRnWDNYho%2FIhouPYr2TOOFppxo%2BaE%3D&reserved=0) ::: **What?** [TRIC-DT Seminar Series](https://github.com/alan-turing-institute/tric-dt/tree/main/Seminars) is an interdisciplinary platform for [TRIC-DT](https://www.turing.ac.uk/research/research-projects/tric-dt) researchers & friends to **share and discuss the computational methods, algorithms, and models that underpin Digital Twin technology across diverse fields**. **When?** Thursdays afternoon (aiming for 1 or 2pm) Europe/London **Who?** ***Everyone** intersted in digital twin research* :::info ***If you don't receive email announcements about those seminars (start with [TRIC-DT Seminar Series] in subject matter - get in touch to be added to our mailing list!!!*** ---> digitaltwins@turing.ac.uk ::: --- ## Welcome, introduce yourself! **Name + Pronouns + your affiliation + your research area + an emoji ([emoji cheatsheet](https://github.com/ikatyang/emoji-cheat-sheet/blob/master/README.md))** *(Remember that this is a public document. You can use a pseudonym if you'd prefer.) Use the 🤫 emoji if you would not like to be included in our public archive* * **In-person**: [name=Sophie Arana] (TRIC DT Hub), * * * * **Remote**: [name=Kalle Westerling] (TRIC DT Hub) + he/they + The Alan Turing Institute + research application manager + :checkered_flag: * * James Byrne + he/him + British Antarctic Survey + Digital Infrastructure & Innovation + :gear: * * * * * * * --- ### Seminar Schedule | Date | Time | Topic | Room | Speakers | |------------|-------|-------|--------|-------------------| | 2023-12-14 | 14:00 | Research Roundup | Margaret Hamilton Meeting Room | all | | 2024-02-?? | 13:00 | Data ingress | Remote (Zoom) | tbc | | 2024-03-28 | 13:00 | Dynamic Knowledge Graphs | Remote (Zoom) | [Xiaoxue Shen](https://digitwin.ac.uk/team/xiaoxue-shen/) | ## Agenda | Time | Activity | | ---- | -------- | | 5 mins | Welcome & Updates | | 20 mins | Natural Environment (Ben Evans, Jonathan Smith, Martin Rogers, James Byrne) | | 20 mins | Health (Marina Strocchi, ? , ?, ?) | | 10 mins | Infrastructure (Ziad Ghauch & Xiaoxue Shen) | | 15 mins | Questions to audience | ## Q&A ### Questions for themes **Natural Environment** * what is the timescale of icebergs? * weeks to years [static objects make this varied]. (compare to milliseconds/microseconds for heart) * how can you tell which part of the iceberg? intensity of object? colour? * our segmentation can tell different tissues from intensity of colour. * sat radar = icebergs are bright scatters into two polarisations of back scatter. we're not looking at individual level. we;d like to be able to track child objects from a broken iceberg. * availability of training data for satellite data? * in health, data is not the problem. * 2d, not 3d? * yes, no depth in the data we use * How do the physics-based dynamics of ocean currents feed into iceberg tracking model? * can the models be used to track oil spills in the ocean? * is the under-water continuation of icebergs not a problem? * How far in the future can you predict given the input data. Don't you need very recent data? **Health** * availability of products for operational use? * (compared: we have individual pipelines currently) * (how do we assess the impact of those tools?) * **Infrastructure** * * * ### General Discussion _What format would you like the Seminar Series to have?_ * internal theme talks * external speaker? or a mix? * Journal club? - not favoured * more hands-on collab sessions? * Health: more in person sessions!! _Suggestions for topics & speakers?_ * potential overlap with tracking icebergs and tracking cells / blood clots * deep learning models are used to track heart movement, could potentially overlap with tracking of iceberg break-up and * availability of training data for satellite data / deep learning models trained on imagery? * image processing problems * pipelining features into a system that learns things about bigger things. * what is a digital twin? (we all want to build something transferrable rather than something isolated) --> library of metadata about modules that people are building. Interfaces built for them. “Do cardiac guys already have this? We can reach out to them then! * if I worked where I work today, but 20 years from now - what would that look like? what do I do?” --> could give us a north star for where we’re going. * interest from health group to have session on knowledge graph * Segmentation & Motion tracking algorithms * main difference about segmentation is that cardiac group knows the geometry of the heart in contrast to icebergs * but other examples from health that might fit better: on tracking movement of blood clots using fluid dynamics models (Marina mentioned talk on this?) * threshold-based segmentation * In cardiac twin: segmentation purely deep learning based on a lot of labeled data. For icebergs, labeled data is scarce. * Emulators: Parameterization estimation & prediction * Gaussian modelling * Explainability: * not so necessary for the segmentation as this can be visually checked * image processing for direct prediction (eg clinical trials), that's when explainability could help * emulators: interaction between parameters is captured in graph models (part of emulator pipeline) to inform treatment decisions / drug trials * knowledge graphs: rosehips (Keith worden) * interest from health group to have session on knowledge graph _What frequency would you attend the Seminar Series at?_ * consensus: can be less often if in-person * ”just getting in the same room with some downtime is a good place to start.“ ---- ### Link List ✨ #### All Slidedecks & past recordings * Nov 23rd - Emulators: [Recroding](https://thealanturininstitute-my.sharepoint.com/:f:/g/personal/sarana_turing_ac_uk/EqJlp-4ukL5FqcNW3mx5t9sBBMhMdDEpwn3ZB2Zq9R8Mdw?e=NnK9R9) & [autoemulate slidedeck](https://zenodo.org/records/10174843) #### General links * [TRIC-DT website](https://www.turing.ac.uk/research/research-projects/tric-dt) * [Seminar series page](https://github.com/alan-turing-institute/tric-dt/tree/main/Seminars) and [suggested topics](https://github.com/alan-turing-institute/tric-dt/issues?q=is%3Aopen+is%3Aissue+label%3A%22seminar+series%22) * [TRIC-DT Glossary](https://hackmd.io/npUXO9llSDqagVM3SntR_w) * [HackMD guide](https://hackmd.io/@turingway/hackmd-guide) ### Code of conduct * [Take a moment to read this](https://www.turing.ac.uk/events/policies-and-guidelines) ---