Nature-based solutions to substitute fossile resources and address global change
Lecturer: Benoît Gabrielle - Agro-ParisTech
Natural ecosystems and the services they provide are a key to address current environmental challenges, such as climate change, the preservation of air and water quality, and the transition toward a low-carbon economy. Engineering these services via the management of ecosystems, land-use planning or the integration of plants in urban environments can « pave the way towards a more resource efficient, competitive and greener economy » (EU Research Agenda, 2015). Nature-based solutions include for example the production of bio-based alternatives to fossile-based products, the mitigation of heat waves in cities via the presence of vegetation, the enhacement of carbon storage in ecosystems or the management of watersheds to reduce flood risks.
The aim of the course is to raise the awareness of these solutions, with a particular focus on biomass production and transformation into fuels, materials and chemicals to substitute fossile resources, and to equip them with key concepts and know-hows on the design and assessment of such solutions. The course will provide students with a detailed understanding of the issues associated with the development of nature-based solutions to meet our needs for food and energy, mitigate climate change or air pollution, and methods to their sustainability along the environmental and economic dimensions.
Langue du cours : Anglais
Credits ECTS : 4
De nombreux systèmes biomédicaux et biologiques se présentent naturellement sous la forme de graphes : connectomes cérébraux, réseaux d’interactions protéine-protéine, réseaux de régulation génétique, graphes moléculaires, réseaux de similarité entre patients et graphes de population. Ce module initie les étudiants aux fondements mathématiques et informatiques de l’apprentissage automatique sur les graphes, en mettant particulièrement l’accent sur le génie biomédical, les neurosciences computationnelles, la bio-informatique et l’analyse des données biologiques.
Le cours aborde d'abord les principes fondamentaux de la théorie des graphes, des représentations de graphes et de l'apprentissage basé sur les graphes. Il présente ensuite les méthodes essentielles du traitement du signal sur les graphes et des réseaux neuronaux sur les graphes, notamment l'analyse de Fourier sur les graphes, le filtrage de graphes, la convolution de graphes, la transmission de messages, la classification des nœuds, la classification des graphes et la prédiction des liens. Une attention particulière est accordée aux applications biomédicales telles que l'imagerie cérébrale fonctionnelle, la connectivité structurelle et fonctionnelle, l'analyse des données omiques, la classification des maladies et la prédiction des interactions protéine-protéine.
Ce module fait le lien entre le traitement classique des signaux basé sur les graphes et les réseaux neuronaux graphiques modernes. Le traitement des signaux sur les graphes fournit des outils permettant d'analyser des signaux définis sur des domaines irréguliers, tels que les signaux d'activité cérébrale représentés sur des graphes de connectivité cérébrale, en utilisant des concepts tels que les transformées de Fourier sur les graphes et les filtres graphiques. Plus généralement, les méthodes basées sur les graphes sont de plus en plus utilisées dans les systèmes biologiques, qu'il s'agisse de graphes de population au niveau des patients ou de graphes moléculaires et omiques.
Objectifs du cours :
- Introduction to the concept of data stream processing
- Learning the basics on and how to use Data Stream Management Systems (DSMS)
- Understanding the main sampling techniques used for stream processing : sampling, sketching, etc.
- Understanding and using the main data stream processing algorithms
Syllabus :
This course deals with the algorithms and softwares commonly used to process large data streams. It aims at understanding the main difficulties and specificities of this type of data, knowing what different types of streams exist, what are the theoretical models and practical algorithms to analyze them, and what are the right tools to process these streams.
After an introduction of what data streams are from a conceptual point of view, this class covers the question of data stream processing from two different angles:
- A Machine Learning and Data Mining approach to cover the theoretical and algorithmic difficulties of learning from data streams: online learning vs incremental and batch learning, and sampling techniques.
- A more practical approach with an introduction to the various systems and software that are used to handle these data.
In terms of organization, the course will consist of an alternance of lectures and practical sessions. Finally, during the last class the students will have to present a recent research article of their choice on the subject of data stream processing.
Prérequis :
- Basics in SQL language
- Basics in Machine Learning (supervised and unsupervised)
- A knowledge of Java programming is recommended but not mandatory
Évaluation :
- The practical sessions will make ⅔ of the mark
- The research paper presentation will make ⅓ of the mark
Understanding and use the spatialization in LCA II
The aim of Life Cycle Assessment (LCA) course option is to describe why and how the spatialization can be useful and used in LCA. It provides the fundamental notions required to perform spatialized LCA, to use spatialization tools and to interpret and use spatialized LCA results in decision-making process. Students will have to carry out a specific question concerning spatialization in LCA.
Teaching staff
- Lynda Aissani, Research Engineer, INRAE
- Pierre Thiriet, Research Engineer, INRAE
- Samuel Le Féon, Research Engineer, INRAE
Course outline
- Why spatialize LCA?
- Exploring the need to spatialise and contextualise LCA using a small case study
- Based on a case study
- With some theoretical elements
- Bringing to light the problem of implementing the spatialisation of LCA
- How to spatialize?
- Work on 4 issues to be resolved (geographical grid, indicators, data required and tools required)
- With some theoretical elements for each of the 4 issues
- Work in groups to solve them at the end of the day
- Making progress on resolving the problem of implementing the spatialization of LCA
- With which tools?
- Based on the 4 points resolved in the previous lesson, implement the method using tools based on a combination of theory and practice.
- Work in groups to solve a question on the spatialization of LCA
- Understand the contribution of tools (R, possibly QGIS) to operationalise the resolution of the problem and be able to draw on the methodological lessons of the course
- Oral presentation of case study resolution
- Students present the solution for their question concerning spatialization
The module includes 10 hours of courses and 10 hours of practical work.
--------------------------------------------
Level required: Basic knowledge of LCA
Language: English
Credits ECTS: 3
Supervisor: Lynda Aissani
