To support the uptake of MOOD innovations, WP6 will implement a dynamic knowledge transfer and capacity building addressing young researchers (PhD candidates), professionals, and technical staff through an exciting summer school on June 20th, 21st and 22nd, 2022 in Montpellier (France). Throughout a three-day full-immersion training, expert lecturers will promote developed software and computing techniques, tools and datasets.

Day 1 – 20 June
Introduction to disease data and epidemic intelligence

CEST time	Session	Speakers	Summary
8:30-9:00	Welcome coffee	⛾	Room Badiane
9:00-9:30	Introduction to the Summer School	Elena Arsevska – CIRAD, Tom Hengl –OpenGeoHub	Welcome to the Summer School
9:30-10:30	Basics of surveillance and epidemic intelligence activities: an overview and the example of TBE 📹	Timothée Dub – THL Henna Mäkelä – THL	We will discuss the basics of infectious disease surveillance (event-based and indicator-based surveillance, active versus passive surveillance), as well as the advantages and limitations of each type of system, followed by the example of how surveillance activities for TBE are conducted in Finland. By the end of this lecture, participants should be aware of the limitations and quality issues that can occur when using surveillance data for comparison and/or modelling.
10:30-11:00	Coffee break	⛾	Room Vanilla
11:00-12:30	Reproducible research in R 📹	Facundo Muñoz – CIRAD, France	In this session, we will describe tools and workflows to cumulatively improve the reproducibility of analyses performed in R. R is a mature, world-class, open-source statistical computing and data-analysis platform with a huge community of users from all areas of science and industry. Yet, most researchers rely only on its most basic scripting features, missing the opportunity to unleash its full potential, in particular concerning reproducible research workflows. Specifically, we will discuss encoding and platform-specific packages, the advantages of organising code into functions, using project directories and relative paths, reproducible reports with RMarkdown, controlling package versions with Renv, organising code into a pipeline with targets, keeping track of changes from various collaborators with git, reproducibly publishing results with Continuous Integration in Git(Hu|La)b pages, reproducing the complete environment with docker, and controlling versions of the complete software stack with GNU Guix.
12:30-13:30	Lunch	🍽	Room Vanilla
13:30-15:00	How to build a dashboard to visualize covariate metadata collected from the literature 📹	Francesca Dagostin – Fondazione Edmund Mach	This lecture will give an overview of how to extract relevant information from published literature, with a special focus on metadata related to covariates affecting disease emergence. Since data retrieved from literature are often complex and tricky to explore, the practical session will show the participants how to organize them into relational tables in order to build customizable and ready-to-share dashboards, which allow to efficiently visualize and summarize the information collected.
15:00- 15:30	Coffee break	⛾	Room Vanilla
15:30- 17:00	Time-series analysis of disease data 📹	Timothée Dub – THL Tom Hengl – OpenGeoHub	In this session, we will discuss the basics of Time Series Analysis, including with panel data. We will look into how to take into account seasonality, how to identify a trend and how to investigate the relationship between two-time series, with a focus on practical tips and R packages. By the end of this lecture, participants will be able to analyze surveillance data, identify seasonality and investigate potential trends.
17:00-17:30	Aperitif / light dinner	⛾	Room Vanilla
17:30-19:00	Crash course in R	Tom Hengl – OpenGeoHub	Optional course
19:10-19:40	Transport to Montpellier	🚌	Shuttle bus service
20:00-21:00	Happy hour	🍹	Networking and socializing in the city centre. Venue to be defined.

Day 2 – June 21
Covariate data and media data for disease intelligence

CEST time	Session	Speakers	Summary
8:30-9:00	Q&A session from the previous day		A moment to discuss lessons learnt and ask questions about the previous day.
9:00-10:30	Mining Media Data 📹	Mathieu Roche – TETIS, CIRAD Mehtab Alam Syed – TETIS, CIRAD Nejat Arini – INRAE	First, we will present an overview of NLP (Natural Language Processing) approaches in order to mine media data for EBS systems. The second part will focus on textual classification issues based on data science approaches. Finally, original representations of results will be presented for highlighting new knowledge for EBS systems. A part of these different techniques will be applied in the context of the AMR hackathon.
10:30-11:00	Coffee break	⛾	Room Vanilla
11:00-12:30	Using digital surveillance tools for near real-time mapping of the risk of infectious disease spread 📹	Dr. Sangeeta Bhatia –  Imperial College London, UK	ProMED is a longstanding informal disease surveillance network. It has a worldwide network of clinicians, who send in reports of any unusual health events in plants, animals, or humans. These reports are then vetted by subject matter experts at ProMED before being shared with ProMED’s subscribers. ProMED emails usually contain a wealth of quantitative information about outbreak events. However, this information has so far not been utilised in real-time outbreak analysis. Using the West African Ebola epidemic as a case study, I will demonstrate the challenges of using data extracted from ProMED for real-time analysis. We will use a cleaned data set for the same epidemic that was collated by the World Health Organization as a benchmark to understand what can be inferred in real-time using digital disease surveillance data. Data and code available at this link.
12:30-13:30	Lunch	🍽	Room Vanilla
13:30-15:00	Covariate data and spatial mapping 📹	William Wint –ERGO Cedric Marsboom – AVIAgis	This talk will first touch on why we use maps at all and then look at the factors (“covariates”)  that drive disease occurrence.  The session will examine what these covariates might be and identify the environmental, agricultural, socio-economic, ecological and climatic parameters that can best contribute to spatial modelling. It is also important to know where these data can be found, what are the pros and cons of different data sources for the common covariate variables,  and what datasets can be used for different types of models.  The available covariate data are not always in a form that is convenient for spatial modellers and the session will provide examples of the processing and selection needed to provide modellers with what they need. Finally, the use of selected covariates in spatial models will be discussed and illustrated with worked examples.  It is intended that the session will include interactive elements and participants will be asked to help provide answers to questions posed during the session.
15:00-15:30	Coffee break	⛾	Room Vanilla
15:30-17:00	Building modelling datasets and Machine Learning in R 📹	Tom Hengl – OpenGeoHub Leandro Parente – OpenGeoHub	In this block, participants will learn how to use state-of-the-art Machine Learning algorithms in R (mlr, mlr3) for the purpose of building models and producing spatial and spatiotemporal predictions. We will use some of the disease datasets and covariate layers (MOOD study area) mentioned in the previous sections, then show step-by-step how to run spatial spatiotemporal overlays, optimize models, run model diagnostics, produce and visualize predictions (as maps or animations). The block is based on the R bookdown.
17:00-18:00	Transport to Montpellier	🚌	Shuttle bus service.
18:10-19:00	Happy hour	🍹	Networking and socializing in the city centre. Venue to be defined.

Day 3 – June 22
AMR Hackathon

The emergence and spread of drug-resistant pathogens have led to antimicrobial resistance (AMR) now being considered a major public health concern. To date, AMR surveillance in Europe and elsewhere is mainly relying on indicator-based surveillance, involving structured data collection according to clear case definitions. Seeking to support the early detection, assessment, and monitoring of current and future AMR threats across Europe, the MOOD project aims to explore the opportunities of mining unstructured surveillance data including those from media sources.

In this hackathon, we will form interdisciplinary teams that will work collectively on a technical challenge. A task and a data corpus will be presented to your team on the day of the hackathon. Your team will be challenged to develop new technical solutions that will mine and/or visualise unstructured media data. The main objective of the task involves the development and testing of classification approaches that will automatically identify text on AMR events and types of AMR issues (e.g. animal, food, etc.) in unstructured data (e.g. news, tweets) and classify these events by relevance for epidemic intelligence purposes. Eligible methods will largely involve those covered during the summer school, but usage of methodology beyond those covered is more than welcome.

 
At the end of the hackathon challenge, your team will present the developed methodology and outcomes to a jury, accompanied with underlying arguments on what makes your solution innovative and efficient.

CEST time	Session	Speakers	Summary
8:30-9:00	Introduction to the MOOD hackathon
9:00-10:30	MOOD hackathon presentation📹	Mathieu Roche – Tetis CIRAD, France Maguellone Teisseire – INRAE Esther van Kleef – Institute of Tropical Medicin	You will collaborate with other participants in an interdisciplinary team to design and to imagine new solutions to address the issues of AMR surveillance from the media. As an introduction, the tasks to achieve will be presented as well as the corpus on which you will work on. The main objective is to propose and test classification approaches in order to automatically identify texts (i.e. news, tweets) dealing with an AMR event and types of AMR issues (e.g. animal, food, etc.). Secondly, the teams with complementary skills will be formed and the jury will say some words on their expectations. Methods involved in the hackathon are mainly the ones presented during the two days of the summer school but you will be free to go out of the box. At the end of the two work sessions, participate online or face-to-face, you will present your methodology and some results to the jury by underlying what makes your solution innovative and efficient.
10:30-11:00	Coffee break	⛾	Room Vanilla
11:00-12:30	MOOD hackathon practicals 📹
12:30-13:30	Lunch	🍽	Room Vanilla
13:30-15:00	MOOD hackathon practicals 📹
15:00-15:30	Coffee break	⛾	Room Vanilla
15:30-17:30	Results and group discussion Feedback / Summer School evaluation
17:40- 18:00	Transport to Montpellier	🚌	Shuttle bus service
19:00	Closing dinner	🍽	The venue will be communicated to the participants.

Topics:

• Analytical methods for epidemiology in MOOD;
• Outbreak analysis;
• Data analytics;
• ID modelling;
• Machine Learning;
• Time-series analysis;

Registrations:

Registrations are open to MOOD partners and external participants. Please register by filling out this form.
Registration fees: There are no registration fees.
The event, coffee breaks and lunches are sponsored by the Europe Horizon-2020 project MOOD.

Important Dates:

• 1 April: Registrations open;
• 1 May: Registrations close;
• to be confirmed: distribution of the materials;
• 20 June: Summer School starts;
• 23 June: Summer School ends.

Venue:

Agropolis building
1000 Av. Agropolis, 34000 Montpellier, France

Room Badiane
Max capacity: 54

How to get there

With public transport:
– from Saint-Roch train station, which is located right in the centre of town, just 200 meters from the Place de la Comédie.
– from Montpellier Airport (Montpellier-Méditerranée Airport).It is located 7 km east-southeast of Montpellier in Mauguio.

Target communities:

Young researchers, such as PhD and postdoctoral researchers in the fields of analytical epidemiology, disease mapping, disease modelling, disease ecology, spatial prediction, One Health, R spatial epidemiology community. Summer School is open to MOOD partners and non-partners as well.

Technology in use:

• Zoom breakout rooms with Q&A, polls and similar;
• Mattermost channels for internal questions, screen sharing and markdown/code snippets;
• Computational notebooks on Github.com and Gitlab.com.

Activities planned:

• Lectures on 20-21 June;
• Keynote talks every day;
• Internal hackathon on 22 June;
• Happy hour (drinks) every day;
• Lunch & coffee breaks every day;

Video recordings:

All lectures will be video recorded using Zoom webinar functionality in HD quality. Subject to the approval of the presenters the videos will be uploaded to the TIB-Av Portal and MOOD website, and a DOI will be assigned to each talk. Lecturers will be asked to accept the general recording conditions and sign a license agreement. Copyright of the videos will be assigned to the presenters as in standard Open Access material.

Watch OpenGeoHub’s MOOD Science Webinar & Summer School 2020!

Frequently Asked Questions

Questions?

Get in touch:
media-office@opengeohub.org
mood-coordination@cirad.fr