header

Multi-scale Spatio-Temporal Analysis
of Research Data

Objectives

The general objectives of MuSTARD are:

Our aim is to provide a common framework of computational tools and services that promote the digital transformation in strategic sectors, following the first priority axis (“Transformación Digital e Inteligencia Artificial”) of Strategic Action 4 (“AE4: Mundo Digital, Industria, Espacio y Defensa”) as described in the “Plan Estatal de Investigación Científica, Técnica y de Innovación 2021-2023”. Furthermore, we can locate the project into the priority axes “Proyectos Tractores de Digitalización Sectorial” and “Economía del Dato e Inteligencia Artificial” identified in the “Plan España Digital 2025”.

MuSTARD is completely aligned with the national strategy about digitalization in strategic sectors, and in turn with the corresponding international programs, mainly Clusters 4, 1 and 5 associated with the Global Challenges in the Pillar II of Horizon Europe. In addition, MuSTARD’s diverse fields of application and multidisciplinary research team follow the spirit of the present Call ‘Proyectos de Generación de Conocimiento 2023” in “Capítulo 1 (aspectos generales), Artículo 2 (finalidad de las ayudas)” where the aim of promoting synergies between research groups and multidisciplinary collaborations is encouraged.


A list of research applications of interest in this project follows:

  • Precision medicine for cancer.Time-resolved analysis of spatial omics represents one of the most powerful approaches today to understand cancer propagation in both time and space. Unfortunately, there are no computational tools that can readily combine the spatio-temporal nature of this new type of data with powerful statistical inference. Providing new algorithms that can handle such a complex spatio-temporal structure is an urgent need in cancer (and other diseases) research.

  • Climate change.Gathering data from disparate environmental contexts is necessary for understanding the importance of biodiversity and the effects of major environmental challenges, like climate change. However, the combination of spatio-temporal ecological data sources is extremely complex, and the research on climate change requires computational means with solid statistical support to provide convincing answers for researchers, policymakers, and the general public.

  • Volcano-seismic activity.The derivation of computational tools to identify volcanic activity risks from time series data coming from a set of spatially distributed sensors poses relevant challenges that are common to the study of climate change. In particular, the requirement for multi-scale spatio-temporal tools coupled with sound statistical techniques to understand historical data.

  • Human mobility models.The study of human mobility is especially important for applications such as understanding social behavior, traffic forecasting, urban planning, and epidemic modeling. Spatio-temporal analysis can provide the necessary tools to answer the questions of what is happening, and when and where it happens. Finding highly discriminative features in the data obtained, and facilitating exploratory data analysis through visualization approaches is of high interest.