we use
original data
to create value

Our mission is to produce original and actionable data delivered in tailor made platforms.

read more

in a data-driven world

We are a company committed to a major revolution : using data as a raw material to bring about radical changes

in a data opening global movement

unique opportunities and new challenges arise every day

our mission is to produce original data

producing unique data is our way of enriching this huge pool of opportunities

by developing artificial intelligence for good

creating original data requires permanent investment in artificial intelligence

and building efficient and robust digital infrastructures

our objective is to build infrastructures from original data

In the energy, renovation, construction, insurance, green finance and culture fields, we gather technical and scientific partners in public and private projects to build digital platforms that enable environmentally friendly economic development.

our expertise

we produce original data

We collect available, non-personal data to generate a unique data library of original data using our AI tools.

Open data is an unprecedented opportunity for value creation. Building unique datasets and making them actionable allow for the emerging of new opportunities.

producing
original data

using our AI tools and from images, texts and structured data, we create original datasets

connecting
heterogeneous datasets

through our relationship engine and the creation of datasets, the data we produce becomes relevant, categorised by business sectors, with geo-tracking at the right level of granularity

making data actionable

Through integration in information systems of our clients or through development of tailored platforms, data is a tool for decision making or for building new opportunities.

Our datasets are actionable according to the constraints and needs of our clients and partners.

business opportunity
sheets and clusters

we deliver opportunity sheets and cluster sheets directly in the tools of our clients through tailored solutions and interfaces.

building
tailored platforms

we develop platforms allowing our partners to use by themselves our databases and AI tools to generate their own sheets and clusters to create value, in their current projects or in new ones.

  • using our AI tools and from images, texts and structured data, we create original datasets

  • through our relationship engine and the creation of datasets, the data we produce becomes relevant, categorised by business sectors, with geo-tracking at the right level of granularity

  • we deliver opportunity sheets and cluster sheets directly in the tools of our clients through tailored solutions and interfaces.

  • we develop platforms allowing our partners to use by themselves our databases and AI tools to generate their own sheets and clusters to create value, in their current projects or in new ones.

platforms

Our specific platforms allow us to gather complementary key actors around relevant data, in order to generate economies of scale and create new and better services. The platform hence becomes a genuine asset, a mutualized infrastructure dedicated to the exploitation and the creation of value upon the relevant data.

We accelerate exchange, reuse and valorisation of data through tailored platforms.

example ?

team

Grégory Labrousse
CEO

Pierre Lescure
Co-Founder & Board Member

Lila Tretikov
Co-Founder & Board Member

Pierre-Alain De Mallerey
Board member

Emmanuel Bacry
Co-Founder & Board member

Éric Euvrad
Board member

Raoul Saada
Strategic deployment - Finance

Sebastián Sachetti
Senior Strategic Deployment

Nicolas Berthelot
Data Strategy Lead

Louis Petros
Knowledge Strategy Lead

Gaël Grasset
Chief Technical Officer

Servane Khaouli
HR Business Partner

Alexandre Bacchus
Operations Manager Data Science

Stéphane Gaïffas
Scientific Committee Member – Machine Learning

Duccio Piovani
Research Lead Data Science

Charles Hutin-Persillon
Data Strategist

Aymeric Flegeo
Data Engineer

Guillaume Larcher
Developer Product

Vincent De Chillaz
Data Quality Analyst

  • Grégory Labrousse

    CEO

    President of nam.R, serial entrepreneur, specialised in environment and cost reduction consulting. Founder of a group specialised in green finance, agro-ecology and eco-tourism.

  • Pierre Lescure

    Co-Founder & Board Member

    Author of a seminal 2013 report on France's digital economy, which highlighted (among other things) the importance of data and data openness, Pierre has played a part in the creation of many companies that represent the cutting edge of their respective technologies (Molotov.tv, Canal +). Pierre is a director of the Kudelski cybersecurity group and the Lagardère group, as well as president of the Cannes Film Festival.

  • Lila Tretikov

    Co-Founder & Board Member

    Lila is Chief Executive Officer of the Terrawatt Initiative, the ‘armed forces’ of the International Solar Alliance, launched with the support of the President of the French Republic. Former president of the Wikimedia Foundation, where she spearheaded Wikipedia’s digitisation and Artificial Intelligence projects, Lila is a recognised machine learning expert with an impressive career (Chief Product Officer of SugarCRM, CEO of Raskspace...). She was nominated for Most Powerful Woman on Forbes’ 2014 ‘World's Most Powerful Women’ list and the San Francisco Chronicle's ‘21 Most Powerful Women in Bay Area Technology’ list. She received a Stevie Award for Women in Business, and is a member of the Young Leaders of the World Economic Forum.

  • Pierre-Alain De Mallerey

    Board member

    Graduate of France's ENA (Senghor) and École Polytechnique, and a French finance inspector, Pierre-Alain was ministerial advisor and then General Manager of the MutRé. A renowned data specialist, he is President of insurance broker Santiane. Pierre-Alain joined the board of nam.R in 2017.

  • Emmanuel Bacry

    Co-Founder & Board member

    Director of Research at CNRS, Paris Dauphine University and professor and Head of the Data Science & Big Data initiative at École Polytechnique, Emmanuel is also in charge of Big Data processing for France's national Social Security database

  • Éric Euvrad

    Board member

    Director and Chairman of the audit committee for the Atari group, Eric began his career at Arthur Andersen, where he participated in the development of its restructuring practices. He then joined Lucien Deveaux after its takeover of the Bidermann Group, whose turnaround he led, before launching an Internet start-up that he sold in 2002. After this, he joined LBO Gigastore, a non-food discount brand, where he remained at the helm until it was sold in 2008. Eric manages a consulting firm specialized in radical change and co-leads a training group.

  • Raoul Saada

    Strategic deployment - Finance

    Graduate of the École Polytechnique and expert in financial intermediation and restructuring, Raoul participated in the creation of equity broker Finacor and the EuroMTN market. He specialises in green finance, and has contributed to several project financing structures.

  • Sebastián Sachetti

    Senior Strategic Deployment

    Former student of the National School of Administration and outstanding polyglot — he speaks French, English, Italian, Spanish and Portuguese — Sebastian has held prominent positions in both private and public sector organizations, working at the crossroads of finance, culture and computer science. Responsible for the design and implementation of the Culture Pass before joining our team, Sebastian develops nam.R's original platforms.

  • Nicolas Berthelot

    Data Strategy Lead

    A recognized expert and thought leader, Nicolas began processing socio-economic databases from a very early age. He has been with nam.R since its inception, where he is building its Data Library, a project unique in size, scope and innovative quality. A graduate of Sciences Po Paris, Nicolas is one of the first in France to receive a degree in data strategy (Sorbonne University - UPMC). At nam.R, he leads the Data Sourcing and Data Strategy teams.

  • Louis Petros

    Knowledge Strategy Lead

    Passionate about economics, strategy and public affairs, Louis joined nam.R when it was formed. Before nam.R, he worked at EDF Trading in London and for France's National Assembly and Ministry of Defence. Louis holds a master's degree from the London School of Economics. He is responsible for creating nam.R’s Knowledge Strategy department, which he manages. He identifies, organises and distributes the practical knowledge required for nam.R project implementation and algorithm optimisation. He also handles nam.R's public and regulatory affairs.

  • Gaël Grasset

    Chief Technical Officer

    Gaël is a trained data scientist and sociologist who holds a degree in statistics engineering from ENSAE and master's in sociology from Sciences Po Paris. He is a multitalented data scientist, manager and product manager whose efforts — bolstered by the technical expertise in Artificial Intelligence he gained at Oscaro — have driven nam.R's continued evolution since it began its operations. Gaël is in charge of nam.R's technical teams.

  • Servane Khaouli

    HR Business Partner

    Servane has a degree in history and is a trained project manager with extensive experience in culture, communications and SME management. She has been at the heart of nam.R's operations since the start-up was founded. Servane oversees office management and human resources to support development across every department at nam.R.

  • Alexandre Bacchus

    Operations Manager Data Science

    With a PhD in electrical engineering, Alexandre is a recognized expert in Artificial Intelligence and the energy sector. He has worked on innovation and data projects at EDF and Enedis. A trained agile project manager, Alexandre joined nam.R's data science group to help build its Digital Twin and organise team management.

  • Stéphane Gaïffas

    Scientific Committee Member – Machine Learning

    Professor of machine learning at Paris Diderot University and associate researcher at the École Polytechnique, Stéphane is a brilliant scientist. He is the author of some forty research papers on machine learning, statistics, optimisation and probability theory published in top machine learning, statistics and probabilities journals and conference proceedings, including NIPS and ICML. Stéphane is a founding member of nam.R's Scientific Committee.

  • Duccio Piovani

    Research Lead Data Science

    After completing his PhD in complex systems at the prestigious Complexity Centre, Imperial College London, Duccio worked as a data scientist and then researcher at Imperial College's Centre for Advanced Spatial Analysis. Duccio joined nam.R to design its proprietary algorithms.

  • Charles Hutin-Persillon

    Data Strategist

    A graduate of IEP Grenoble, Charles is a researcher in the domains of social science, political science and international relations. His passion for environmental issues and the strategic use of statistics led him to enter the world of data in September 2017, when he became a Data Strategist at nam.R. At the same time, he joined the Sorbonne/UPMC Data Strategy degree program.

  • Aymeric Flegeo

    Data Engineer

    After receiving his degree in data science from Télécom Paris, Aymeric worked in data engineering at Renault before joining nam.R. in 2017 as a Data Engineer. He contributes to construction of the Digital Twin and implementation of best practices in data workflow design.

  • Guillaume Larcher

    Developer Product

    After obtaining his MVA master's at ENS Paris-Saclay and the École Centrale de Lille, Guillaume joined nam.R in April 2017 for his end of studies internship. He is very much hands-on — a polymath and practical specialist in computer vision and development. After working for several months to set up nam.R's image recognition algorithms, he joined the product team to help develop nam.R's unique solutions.

  • Vincent De Chillaz

    Data Quality Analyst

    Vincent is a graduate of the École Centrale de Lyon in engineering and an energy and climate specialist. He worked at renowned firm Carbone 4 for several years after holding posts at Schlumberger, Vinci and Citeo. A lecturer at ESTP who is passionate about data projects, Vincent joined nam.R as Product Owner for the Digital Twin.

  • And also...

    Discover the other great people at nam.R !

Alexander Usoltsev

Data Scientist – Computer Vision

After obtaining his master's in biometrics, Alexander first worked as a research engineer before joining nam.R in early 2018. As part of the Computer Vision team, Alexander works on satellite images that he segments to identify different objects of interest, especially those pertinent to the domain of solar energy.

Clément Perny

Data Scientist

Clément recently obtained his master's of data science from Grenoble ENSIMAG school of engineering. He initially joined nam.R as a Natural Language Processing intern. As part of the Data Science team, Clément contributes to toolbox improvement, attribute massification and information extraction from nam.R’s unstructured text data.

Dina Khattab

Data Engineer

Dina holds a master's 2 in data science from the Sorbonne. She originally joined nam.R as a data scientist intern. In nam. R, and its use of open data to drive the ecological transition, Dina found an opportunity to dedicate her knowledge of data science tools and technologies to truly useful, practical projects

Hermes Martinez

Data Scientist - NLP

Hermès holds a master’s in English linguistics and language sciences with a specialisation in computer science linguistics. He is an expert in NLP Artificial Intelligence methods. Hermès worked on automated message classification at SparkUp, opinion mining and sentiment analysis at Webedia (Allociné, AuFeminin) and language modelling at CEPED. He joined the nam.R Data Science team to introduce NLP methods into the construction of its Digital Twin.

François Andrieux

Data Scientist

François completed his computer and electronic engineering studies in 2018. He joined nam.R in August 2018 as an alternate data scientist generalist. He uses machine learning algorithms to extract entities and attributes that are then inserted into the Digital Twin.

Pascal Barneville

Video Manager

As Video Manager, Pascal produces the presentation and promotional films for nam.R. Since its inception, Pascal has filmed every stage of or growth and development. He filmed interviews during nam.R's first data summer school at École Polytechnique and has created documentaries on tech, the founding principles of nam.R and its participation at various events in addition to producing educational films in 3D. In March of 2018, he produced a series of commercials explaining the nature of nam.R's Digital Twin in tandem with communications agency BETC.

Paul-Louis Barbier

Lead Developer Data Library

A degree-holding expert in computer science and information systems, Paul-Louis was a back-end developer and lead dev at a start-up before joining nam.R in May 2018. He is in charge of developing the data library for the Data Strategy team.

Sébastien Ohleyer

Computer Vision Scientist

After receiving his bachelor’s in data analysis from the École Centrale de Lille and his master's in mathematics research from University Lille 1, Sébastien began his MVA master's degree at the École Normale Supérieure Paris-Saclay. As part of his studies, he has joined nam.R as a Computer Vision Scientist.

Bastien Hell

Data Scientist – Computer Vision

After completing his degree in engineering, Bastien joined the National Institute of Geographic and Forest Information (IGN) where he performed image processing and deep learning applied to geographic information. In early 2018, he joined nam.R as a Computer Vision Scientist.

Frédéric Maison

Office Manager

Before joining nam.R, Frédéric worked at Geo PLC as Office Manager. He has been an integral part of nam.R’s operations since the beginning. Frédéric is a veritable Swiss army knife who uses his considerable experience in office management to fortify nam.R’s ties to external providers and support the growth and sustainability of nam.R operations across every department.

Florentin Fromont

HR Assistant

Florentin holds a master's in HR management and sustainable performance. He became nam.R’s HR assistant in February 2018, where he is responsible for HR administration, ongoing personnel file upkeep and upstream intervention in the recruitment process.

Jules Robial

Art Director

Jules holds a degree in applied arts from the Estienne art school, Paris, and has a solid background in graphic design and typography. Since joining nam.R in late 2017, Jules has been responsible for developing and enhancing every aspect of nam.R's visual identity across all media.

Claire Kaluska

Communication & Marketing Manager

Holder of a master’s in operational marketing, Claire has worked for B2B structures of various sizes. Her extensive experience developing communications and operational marketing services for start-ups grants her a 360° perspective on the projects she handles. She joined nam.R in September 2018 as Marketing and Communications Manager.

Hassen El Golli

System Administrator, Consultant

Hassen is an EPITECH graduate and expert in computer systems and networks with a passion for hacking and cybersecurity. He joined nam.R in 2018 to address the technical challenges that big data raises today. A committed proponent of open software and net neutrality, Hassen values the ethical use of open data and AI. He uses his DevOps and technical expertise to support the cloud infrastructure within which the Digital Twin is developed.

Pierre Serafini

Front-end Developer, Consultant

After obtaining successive degrees in modern literature and web development from UTBM, Pierre rapidly became an expert in culture and media digital technologies. His versatile profile — encompassing content, dev and systems — as well as his 10+ years' experience working with the web led to his appointment as CTO first for Trax, then for Open Minded. The work he does as a web and front-end developer at nam.R is in line with his ecological convictions and his need to honour them.

Tristan De Malleray

Community Manager

After obtaining his bachelor of laws from FACO, Tristan attended ISCG where he received a DEES (State Diploma of Specialist Educator) in digital communications and media. His career as a student culminated with a master's 2 in digital and e-business communications strategy. He became nam.R’s Community Manager in 2018 to optimize company visibility on the web and across multiple social networks.

Valentine Lambolez

Data Engineer

Valentine holds a master's degree in statistics and socio-economic informatics from the University Lumière Lyon II, where she specialized in data engineering. After obtaining her degree, she joined Deepki to oversee the development and optimal implementation of customer specific statistics models. She joined nam.R in 2018 as a Data Engineer.

Frédéric Kingué Makongué

Data Strategist

A graduate of the CNAM and the University of Bordeaux, specialised in digital archiving, Frédéric strengthens the Data Strategy team thanks to his expertise in ontology construction, document set structuring and massive data corpus analysis.

Juliette Cocault

Business Analyst

After obtaining a bachelor’s in commerce from McGill University in Canada, Juliette is pursuing her studies at EDHEC here in France. As part of her master's study, Juliette joined nam.R for a 6-month internship in Strategy. She contributes to nam.R's strategic foresight, the implementation of an automated strategic intelligence/monitoring tool and the development of energy renovation performance indicators.

Nicolas Esse

Software engineer

Freshly returned from a year in Shanghai, Nicolas is now in his fifth year at Epitech where he is training to be a developer. He joined nam.R at the end of October 2018, part-time, to work on API development and the company's portfolio of platforms.

Corentin Louison

Business Analyst

Corentin is currently pursuing his master's in science, international strategy and influence at SKEMA BS. He joined nam.R’s Solutions Team in July of 2018 for a 6-month gap-year internship. He participates in monitoring (technological survey) and ecosystem projects.

Mélisande Teng

Data Scientist intern – Computer Vision

Mélisande has nearly completed her degree in applied mathematics at CentraleSupelec Paris and her master's in MVA at ENS Paris-Saclay. Prior to this, she pursued an MSc in social entrepreneurship management at ESSEC. After participating in a Data Science for Social Good Europe project predicting the risk level associated with a child not receiving both doses of the MMR vaccine (Croatia) she joined nam.R as a Computer Vision intern working on Google Street View image analysis.

Francis Valla

Web Integrator & Developer

After two years in England, Francis returned to France where he graduated as a steward and worked at EDF's head office as a receptionist for two years. In 2017, his lifelong fascination with development led him to train online and then at IFOCOP, where he began formal study in 2018. As part of his final year internship, he joined nam.R's product team where he contributes to web demo interface and services development.

partners

For the development of our artificial intelligence tools and the definition of business rules applicable to various sectors, we rely on private and public structures such as research laboratories and business experts.

news

A Data Library to strengthen external data value

Private and public open data, social network data, private data platforms... The web is an infinite source of external data. It comes in a variety of formats: data tables, geolocated data, APIs, images and text. How can organisations take advantage of all the value to be gained from big data processing?

+

Merging Geo-Spatial Data on Twin Polygons.

One of the most important aspects of our work at nam.R is to find, clean, aggregate and organise large datasets of geo-localised data found in Open Data portals. Very often the same geographical area or object is described in many different datasets, each containing a different piece of information.

+

Developing a Complex Computer Vision System, a Case Study : Solar Panels Equipped Roofs.

At nam.R we are working hard to build the Digital Twin of France. To this end, we use a lot of sources of information such as aerial images.Extracting useful information from the unstructured data that are images? Sounds like a job for the computer vision team !

+

Advanced Aerial Imagery Analysis with Deep Neural Networks Explained in 5 Minutes.



+

nam.R on Twitter

pictures

Data Job 2018

  

nam.R recrute ! Nous serons au @CdLouvre à l’occasion du salon #DataJob le 22 novembre 2018.

WEB SUMMIT 2018

Lisbon, Portugal - 11/2018

  

We are already halfway through #WebSummit2018 ! If you are interested in #EnergyEfficiency, #Renewables, #RealEstate and #SustainableDevelopment, be sure to stop by booth (E341, hall 3) for a demo of our tailor-made #Data platform ! #smartcities #solarization #AIForGood

WEB SUMMIT 2018

Lisbon, Portugal - 11/2018

  

What better way to demonstrate our #digitaltwin than with real, miniaturized buildings ? The results are more than satisfactory — come and see for yourself at booth E341, hall 3 ! @XXII_GROUP #WebSummit2018 #AugmentedReality #AIForGood

WEB SUMMIT 2018

Lisbon, Portugal - 11/2018

  

#WebSummit2018 : what an inspiring event ! We’re here at booth E341, hall 3. Come and discover nam.R’s #Data solutions for #sustainabledevelopment ! @WebSummit #aiforgood #DataScience #dataforgood

WEB SUMMIT 2018

Lisbon, Portugal - 11/2018

  

Ready for #WebSummit2018 ! We’re working hard to make our booth welcoming, and looking forward to meeting you for some constructive dialogue on #Data & #DataScience !

EGG Conference 2018

Paris, France - 11/2018

  

Our CTO @GrassetGael will be talking about #Artificial Intelligence, #GeolocalisedData and satellite data at #EGGConference, the first @Dataiku event dedicated to #DataScience and # IA. All are welcome!

ComplexCity 2018

Turin, Italy - 10/2018

  

Our Research Lead Data Scientist, Duccio Piovani is on stage right now at @SICC_IT presenting nam.R’s #DigitalTwin and the platforms we are building to make #OpenData accessible and exploit its value to navigate the cities’ ecological #SmartTransition #DataForGood

Web Summit 2018

Paris, France - 10/2018

  

The @WebSummit 2018 countdown has begun! We’re really looking forward to meeting you and talking about what #IA has to offer the world—and especially to #SustainableDevelopment ! #WebSummit2018 #FrenchTech #GreenTech #IAForGood #DataForGood

HSBC : Smart Cities

Paris, France - 10/2018

  

Thanks to @vpecresse and #HSBCSmartcities for these exciting exchanges on #Data, # IA and #SmartCities @namr_france #ParisInfraWeek #DataForGood

HSBC: Smart Cities

Paris, France - 10/2018

  

#namr_france is glad to be part of the #HSBCSmartCities: @g_labrousse presented new opportunities offered by #Data in #NewTransactions #SmartCities #DataForGood #ParisInfraWeek

ODPP: Observatoire Open Data

Paris, France - 10/2018

  

Open Data By Default Days (Semaine Open Data Par Principe, #ODPP), @namr_france attends a presentation by the Observatoire Open Data des Territoires #opendata @datagouv #collterr

ODPP: Atelier ETALAB

Paris, France - 10/2018

  

How can we expand open #data public services? Which areas should we prioritise? Very exciting workshop led by @Etalab as part of France’s #ODPP week.

Séminaire nam.R

Paris, France - 10/2018

  

A few highlights from the @namr_france one year anniversary seminar on board the@lesmaquereaux barge in Paris—hard work, festive atmosphere! #teamnamr #OpenData #IntelligenceArtificielle #TransitionEcologique

IEEE – DSAA 2018

Turin, Italy - 10/2018

  

Glad to be at the IEEE #DSAA2018 #Torino #DataScience #environment #dataforgood

Dreamforce 2018

San Francisco, USA - 09/2018

  

About to attend the Community Cloud Keynote at #Dreamforce2018. Looking forward to new features for the @namr_franceproduct @salesforce!!

Séminaire à l’Institut Français de Norvège

Paris, France - 09/2018

  

We attended the “Observations, #AI, #SustainableDevelopment” seminar at @ifnorvege: #EarthObservation is imperative if we are to find #innovativesolutions to the climate crisis @DSMeu @sup_recherche #H2020. #EUDigital #copernicus #sdg #dataforgood

France Digitale Day 2018

Paris, France - 09/2018

  

Thank you @VillaniCedric for the chat on #FDDay at @Elysee about using #IA and #opendata to power the #TransitionÉcologique ! @FRdigitale @namr_france @mounir @nautoui @MissionVillani #frenchtech #aiforgood

Présentation Ministère de la Transition Ecologique

Paris, France - 09/2018

  

Amazing exchange of ideas with @ar_leroy and @caromarek from @ademe at the #FAIRE presentation day, where we had the chance to present our #IA platforms supporting the #TransitionEcologique @namr_france @FdeRugy @Min_Ecologie @PlanBatiment #FrenchTech

Inspire Conference 2018

Anvers, Belgique - 09/2018

  

@namr_france at the #InspireConference 2018, insisting on the importance of data quality

Collège de France

Paris, France - 09/2018

  

@namr_france was pleased to take part in the Green & Sustainable Finance Transversal Program workshop organised by @LouisBachelier and chaired by @pierrelouislions at the @collegedefrance! Many thanks to @jmbeacco @petertankov @jeanmichellasry @voisin_steph @pierreducret @patriciacrifo @CarolineLeMeaux

Vivatech 2018

Paris, France - 05/2018

  

Emmanuel Macron était à #vivatech2018. Grégory Labrousse a pu lui présenter nam.R qui incarne parfaitement les valeurs d’une startup d’intérêt général.

Vivatech 2018

Paris, France - 05/2018

  

Un stand aux couleurs de nam.R pour servir de scène aux pitch des 3 jours de #vivatech2018. #DIY

AI for Good 2018 – ITU

Geneva, Switzerland - 05/2018

  

Conférence #AIforgood2018

Data Science Summer School

Paris, France - 07/2018

  

Duccio et Sacha sont toute la semaine de la Data Science Summer School pour présenter les projets de nam.R. #DS3

GeoDataDays 2018

Le Havre, France - 07/2018

  

@namr_france était présent aux #GeoDataDays2018 organisés par @afigeo_asso_fr et @DecryptaGeo. Grand rendez-vous des producteurs et utilisateurs des données géographiques. #opendata #geodata

Web Summit 2017

Lisboa, Portugal

  

Président Hollande talks with Gregory Labrousse about the Open Data revolution. François Hollande was one of Open Data’s pioneers alongside President Barack Obama.

Web Summit 2017

Lisboa, Portugal

  

Meeting with Professor Mohan Munasinghe, Nobel Prize for Peace dedicated to his contribution to define the Sustainable Development Goals. nam.R is a key actor in the SDG working groups.

Data Science Summer School

Paris, France - 07/2018

  

Grégory rencontre ann LeCun à la Data Science Summer School. L’occasion de présenter le travail de nam.R pour mettre la #datascience au service de la transition écologique. #iaforgood

Hackathon DataEnergie 2017

Paris, France - 06/2017

  

nam.R est lauréat du Hackathon DataEnergie 2017 organisé par @rte_france @GRTgaz @enedis @GRDF @Etalab et @LIBERTE_LL. #hackathon #victory

Websummit 2017

Lisbon, Portugal - 11/2017

  

L’équipe nam.R au complet (ou presque !) s’était rassemblée à Lisbonne à l’occasion du #websummit2017.

Websummit 2017

Lisbon, Portugal - 11/2017

  

Le stand de nam.R au #websummit2017, un lieu pour découvrir le projet ambitieux de nam.R et son #digitaltwin.

Websummit 2017

Lisbon, Portugal - 11/2017

  

A la rencontre d’@enigma_data, société majeure de l’#opendata aux Etats-Unis. Une curiosité toute particulière pour l’immense dépôt de données qu’ils ont constitué : Enigma Public. #opendata

Websummit 2017

Lisbon, Portugal - 11/2017

  

Le stand en construction de nam.R, le projet prend vie au #websummit2017.

Dreamforce 2017

San Francisco, U.S.A - 11/2017

  

nam.R était à #dreamforce2017, la grand messe de Salesforce. Au programme, toutes les déclinaisons du préfixe my : #myEinstein, #mySalesforce, #myTrailhead !

World Efficiency Solutions 2017

Paris, France - 12/2017

  

@GrassetGael présente nam.R au #WorldEfficiencySolutions2017.

World Efficiency Solutions 2017

Paris, France - 12/2017

  

Le stand de nam.R au #WorldEfficiencySolutions2017, événement complémentaire au #OnePlanetSummit !

World Efficiency Solutions 2017

Paris, France - 12/2017

  

@LouisPetros est présent sur le stand pour présenter le projet de nam.R pour la #transitionécologique. #WorldEfficiencySolutions2017

World Efficiency Solutions 2017

Paris, France - 12/2017

  

@g_labrousse et @LouisPetros présentent à la ministre @brunepoirson le projet de nam.R pour la #transitionécologique. #WorldEfficiencySolutions2017

Big Data Paris 2018

Paris, France - 03/2018

  

@GrassetGael représente @namr_france pour les finales du Trophées Big Data à @BigDataParis

Big Data Paris 2018

Paris, France - 03/2018

  

@Nicolas_data présente la #DataLibrary et son usage à #BigDataParis2018. #opendata #satellite #aerialimagerey

Big Data Paris 2018

Paris, France - 03/2018

  

@g_labrousse présente le projet nam.R à une audience nombreuse rassemblée à #BigDataParis2018

Big Data Paris 2018

Paris, France - 03/2018

  

Lila Tretikov, CEO de Terrawatt Initiative & co-fondatrice de nam.R à Big Data Paris

Observatoire de l’Open Data

Paris, France - 04/2018

  

nam.R est fier d’avoir participé à la création de l’Observatoire de l’Open Data en partenariat avec @OpenDataFrance, @Etalab, @caissedesdepots, @sciencespo. #opendata

Vivatech 2018

Paris, France - 05/2018

  

La Team nam.R est présente en force à #vivatech2018. Les curieux de #DigitalTwin, d’#ODD et d’ #AIforgood sont venus nombreux pour discuter des projets de @namr_france.

AI for Good 2018 – ITU

Geneva, Switzerland - 05/2018

  

Gaël à la conférence de l’International Telecommunications Union pour l’#IAforGood

Meet-up Green Tech Verte

Paris, France - 05/2018

  

@g_labrousse présente nam.R au Meet-up de la GreenTechVerte

Conférence Comité21

Paris, France - 06/2018

  

Conférence #anthropocene & #ia du @Comite21, avec @Bettina_Laville & @LouisPetros de @namr_france

Toulouse Space Show 2018

Toulouse, France - 06/2018

  

@Charles_data et @GuillaumeLarch sont présents au #ToulouseSpaceShow2018. Ils peuvent y échanger sur notre usage de la donnée satellite aux experts du secteurs, producteurs comme utilisateurs. #satellite #newspace #opendata

Data Science Summer School

Paris, France - 07/2018

  

Présentation de Duccio et Sacha de l’utilisation de leur algorithme de shape matching à la Data Science Summer School. #DS3 #datascience #geomatics

contact

Contact Us
First Name
Last Name

4 rue Foucault, 75116 Paris
+33 (0) 1 85 800 801
contact@namr.com

A Data Library to strengthen external data value

Private and public open data, social network data, private data platforms… The web is an infinite source of external data. It comes in a variety of formats: data tables, geolocated data, APIs, images and text. How can organisations take advantage of all the value to be gained from big data processing?

Before you hear about nam.R’s solutions, it’s important to understand a bit about what they do. nam.R is a data producer that uses only external data in its data science processes. This unique founding principle has one important advantage — no reliance on data from partners who enforce data exclusivity/protections preventing data use. nam.R has extensive expertise with data in every sector of the ecological transition: renewable energy development, energy efficiency operations, smart grids, short circuits . . . Its data science teams exploit not only geolocalised data, but also images and textual corpora to build an incredibly fine mesh of actionable information for a wide variety of actors.

Given that external data is nam.R’s only source of data, they focus on exploitation to the fullest extent. This is why the start-up has tasked itself with building the widest possible structured knowledge base.

The first requirement of this database was that it be comprehensive, drawing from every structured data source in France. Exhaustive research into open and closed data sources was crucial, and monitoring efforts are ongoing. nam.R developed scrapers that browse the pages of these sources on a daily basis. The scrapers download available datasets and retrieve the metadata in a structured way.

The second requirement was to harmonize the information available on each of the databases so that queries would be evenly distributed. This meant developing data mining tools that complete the work of the scrapers by browsing the downloaded files. The scrapers extract a vast array of information from each of the files: number of records, number of variables, column headers and types, and very soon they will reveal single or multiple themes thanks to an algorithm of Natural Language Processing.

Finally, the third requirement was to set up a fluid pipeline integrating external data into machine learning processes. The robustness of the pipeline is based on its ability to adapt to source data updates. Upon receiving an alert form the scrapers, the data scientist can update the databases upstream of the flow. In the short term, the Data Library will be able to score evolutions resulting from dataset updates. If the schema remains consistent and the number of records is not increased tenfold, the dataset will be automatically updated.

The open data movement and the multiplication of data marketplaces both present opportunities that can only be seized with new tools. The nam.R Data Library is equal to the challenge. Although the library is still in development, it already fulfils several internal functions. Its first public trial run will be in February as part of the open data observatory co-developed by nam.R, OpenData France, Etalab and the Cour des Comptes.

Merging Geo-Spatial Data on Twin Polygons.

One of the most important aspects of our work at nam.R is to find, clean, aggregate and organise large datasets of geo-localised data found in Open Data portals. Very often the same geographical area or object is described in many different datasets, each containing a different piece of information. To build a rich description of the object the real challenge is to join these pieces together. But in absence of a clear and coherent name or index, this process can become quite difficult and noisy.

For example when trying to aggregate information on a building we may find its price per square meter in a file, while another file may contain information on its heating system or material. Of course though buildings usually don’t have names, and are often indexed differently according to the source, or institution, behind the creation of the dataset. This means that to correctly merge the various sources one has to be creative.

Luckily more often than not the geographical objects come with the coordinates that describe their geometry, and this indeed can be used to merge the data on twin polygons. By twin polygons we mean polygons describing the same object in the different datasets.

That said one can be surprised to see how many small differences are found in the coordinates of one same object coming from different sources: the angles, the number of vertexes, the length of the edges and of course the geolocalization are often slightly different. Moreover a single building in a dataset can be easily represented as several buildings in another one. In the figure above we can see two tricky examples. All this implies that a unique definition of twin polygonsdoes not exist and therefore we leave this task to an algorithm.

Machine Learning Approach: A Shape Matching Algorithm.

The Machine Learning approach we chose consists of training a Random Forest algorithm to give a similarity score of two polygons. To do this we started by describing polygons through a number of geometrical features: compactness, PCA orientation, eccentricity, convexity and more. A polygon is therefore interpreted as a vector of numbers like in the figure above. This allowed us to quantify the difference of any given couple as the difference of these vectors .

To train our Random Forest algorithm we labeled by hand more than 20 000 couples of polygons, coming from spatial intersections of real datasets, as same or different.

The algorithm then learnt to give a similarity score based on the geometrical features of two polygons. This can be interpreted as the probability of the two polygons being the same one. By setting a threshold at t = 0.7 on the similarity score we obtained the following performances on our training set.

We considered these values good enough, and therefore started using this algorithm to put some order in the wildness of the geospatial data universe. May the merging begin !

Developing a Complex Computer Vision System, a Case Study : Solar Panels Equipped Roofs.

At nam.R we are working hard to build the Digital Twin of France. To this end, we use a lot of sources of information such as aerial images.Extracting useful information from the unstructured data that are images? Sounds like a job for the computer vision team !

To detect all solar panels on the roofs of french buildings, we used aerial imagery and the known outlines of the buildings, through a pipeline consisting of a solar panel outline detector and a filtering algorithm.

We took inspiration from the projects revolving around the state-of-the-art object segmentation deep learning algorithm known as Mask-RCNN. This algorithm is the newborn of a family of algorithms developed by Ross Girshick & al., in direct continuation of RCNN, Fast-RCNN and Faster-RCNN.

The chosen pipeline consists in two complementary parts :

– an object detector, more specifically an instance segmentation algorithm, meant to detect solar panels and extract their contours ;

– a filtering algorithm that takes all detections and filters out those that don’t match our business rules.

While the filtering algorithm can easily be developed using the expert rules we chose to consider (size of the detected solar panels, their position regarding to the considered roof), the deep learning model depends directly of the data we will feed it with.

The first part of the project was, accordingly, to generate a dataset of roofs equipped with solar panels, and the matching labels. There are multiple existing tools for image annotations (VGG VIA, MIT LabelMe,…) that can be used as is. We chose the VGG Image Annotator. After a few (hundreds of) clicks, we ended up with a dataset we’re quite proud of.

Only then, we were able to train the Mask-RCNN model to detect solar panels. The first version of our model wasn’t performing all that well and if was necessary to add more data to the training stage. We realized semi-supervised learning with automatic labelling.

This technique consists in using the model as a way to compute more labels that are then controlled by human operators and used as training data for a new, more robust version of the model. Controlling whether the proposed labels were right and correcting the wrong ones was way simpler than labelling by hand hundreds of images. Basically, we used our first model as a replacement for crowdsourcing ! After a few loops we fetched more data and matching labels and were able to train a model that had acceptable performances.

We transformed the raw output of the model into polygons in the same format and projection as our building polygons using geometric algorithms (Marching Squares, Douglas-Peucker) and geographic transformations. This enables us to directly filter out the potential false positives. We found out that roof windows, glass roofs and blue awning fabric were likely to be mistaken for solar panels due to their similar visual textures.

Fortunately, most false positives can be filtered out using the information of the building shape and position, but also expert rules concerning the minimal surfaces for solar panels.

The first conclusion we draw is that the combination of machine learning and expert rules can become a reliable framework, harnessing the power of machine learning algorithms and the robustness of business rules.

The second one was the use of our first imperfect model to help us label more data. Real data but synthetic labels, a great example of human-machine cooperation, isn’t it?

Finally, there are many different ways for computing the performances of this kind of pipelines. The deep learning model itself can be evaluated using metrics such as its mean average precision but we were mainly interested in the performances of the whole flow. Thus, we chose metrics that are less image-centric and oriented more towards information retrieval : precision, recall and overall accuracy. We added a geometric metric that indicates how well our predicted panels matched with the actual ones, the Intersection over Union (IoU).

We achieved the performances of 96% overall algorithm accuracy and 84% IoU on our test set, values we’re quite proud of.

The predictions of solar panels were integrated in nam.R’s Digital Twin and the information is already put to good use !

Advanced Aerial Imagery Analysis with Deep Neural Networks Explained in 5 Minutes.

There is no secret that when dealing with aerial images the best state-of-the-art results are achieved with deep learning models which come at the cost of their complexity. At the same time thanks to the Open Data, we can explore in a creative way even the most sophisticated techniques.

At nam.R we are working hard to build a Digital Twin of France, and to achieve that we use a lot of sources of information. One of the richest of them being aerial images. For us, humans, “reading” images is easy, but to teach computers how to deal with it is sometimes a real challenge (and fun!). In this post, we will show how we extract a rich description of buildings’ roofs from aerial images, particularly detecting their slopes. In Computer Vision jargon this task is called “object segmentation”, and to do that we chose to use a deep learning approach.

One of the current state-of-the-art segmentation models is the Mask R-CNN model published by researchers from Facebook. And we used this architecture implemented with a Keras framework.

To sum up, our deep learning model should be able to analyze the aerial images and detect roof slopes. This can help us understand the solar energy potential of the roof, and ultimately lead to a progress in nam.R’s vision: accelerating the ecological transition.

What Data Do We Need?

First of all, we need to define what kind of data is suitable for this task. We have a choice between satellite and aerial images. The main difference between them, in the context of our work, is the image resolution. Openly accessible satellite images have a resolution of several meters per pixel, while one can find aerial images with resolutions around 15-20 cm per pixel.

Because we would like to find some fine details on the images, roof slopes and ridges, we have gone with aerial images.

Training a deep learning model to detect roof slopes is a “supervised learning” task, so we need not only the images but also the labels of the slopes. So we created some labels ourselves. This is not a very exciting task, but it is a necessary steps to train a decent model.

This way we obtained two types of data to train the machine learning model: images of roofs and the labels for roof slopes.

A train data “image-label” pair looks like this:

To train a good model we need as much data as possible. Of course, we can label more roofs by hand, but it also possible to generate new samples just with the use of some simple transformations of original images and labels (“data augmentation”). This could be a rotation, a vertical or a horizontal flip and so on.

This way we can obtain a big enough dataset to train our deep learning model.

Deep Learning Model Which Fits Our Goal

Last few years, many high-performance deep neural networks were developed, and achieved impressive results on tasks of object detection. We chose Mask RCNN, a high-performance object segmentation network that was released in 2017. We adapted Matterport’s implementation to be compatible with our aerial images and labels data source.

During the training, the model takes images and corresponding labels and learns its internal parameters to detect roof slopes on any new image. Because our dataset is quite small, a couple of hours of training already produce decent results.

One of the indicators that our model learned is the value of its loss function. The loss function is the criterion which the model tries to minimize, and it is usually an average of error between the real label and the predicted one.

Below are the loss function values for our model, which are constantly decreasing. The figures mean that the model learns well how to detect roof slopes:

Detect Roof Slopes on New Image

During the prediction phase, the model reads only aerial image and predicts the contours of the roof slopes in the image. Because the prediction step does not require complex calculations, it is possible, for example, to copy trained model to the production server and use it to analyze images in a real time.

We can see, that predicted labels for roof slopes are quite accurate, but, as always, there is some space for improvement. From the image above we can see how the roof slope detection doesn’t work well on roofs uncommon material such as metal.

One can imagine several ways to improve this model. For example, we can try to add more training samples for this type of roof material or do more data transformations to generate new samples.

But for the goal of our exploration of deep learning in advanced aerial image analysis, it is already a great result.

This post was just one example of a deep learning model used by nam.R to make France’s Digital Twin richer and closer to the reality. We will share our other techniques in future posts.

Stay tuned!