RESEARCH FIELDMathematics › Applied mathematics
RESEARCHER PROFILEFirst Stage Researcher (R1)
APPLICATION DEADLINE26/02/2021 23:00 - Europe/Brussels
LOCATIONFrance › Sophia Antipolis
TYPE OF CONTRACTTemporary
HOURS PER WEEK35
OFFER STARTING DATE01/09/2021
EU RESEARCH FRAMEWORK PROGRAMMEH2020 / Marie Skłodowska-Curie Actions COFUND
MARIE CURIE GRANT AGREEMENT NUMBER945304
“Artificial intelligence for the Sciences” (AI4theSciences) is an innovative, interdisciplinary and intersectoral PhD programme, led by Université Paris Sciences et Lettres (PSL) and co-funded by the European Commission. Supported by the European innovation and research programme Horizon 2020-Marie Sklodowska-Curie Actions, AI4theSciences is uniquely shaped to train a new generation of researchers at the highest academic level in their main discipline (Physics, Engineering, Biology, Human and Social Sciences) and master the latest technologies in Artificial Intelligence and Machine Learning which apply in their own field.
26 doctoral students will join the PSL university's doctoral schools in 2 academic cohorts to carry out work on subjects suggested and defined by PSL's scientific community. The 2020 call will offer up to 15 PhD positions on 24 PhD research projects. The candidates will be recruited through HR processes of high standard, based on transparency, equal opportunities and excellence.
Description of the PhD subject: “Advanced methods for enhancing interpretability of AI tools with application to the energy sector”
Context - Motivation
Standard practice of decision-making in energy systems relies largely on complex modelling chains to address technical constraints and integrate numerous sources of uncertainty. In this context, artificial intelligence (AI) based solutions are increasingly developed (1) to simplify modelling chains (e.g. via “value-oriented” approaches formulating trading decisions for Renewable Energy Sources (RES) producers without additional predictive models [Carriere 2019]), and (2) to improve performances due to higher learning capabilities compared to state-of-the-art methods (e.g. reinforcement learning method to reduce energy consumption of large plants [Filipe 2019]). The activity on AI for the energy sector includes also the proposition of deep neural network architectures tailored to large-dimension problems such as electricity price forecasting [Toubeau 2019], determine dynamic states [Misyris 2019] or power flow optimization [Donon 2020]. Energy systems are exposed to increasing interactions at multiple scales (distributed generation, flexible prosumers, international exchanges, multi-energy transactions, etc.). Decision makers of the energy sector need to understand how decision-aid tools construct their outputs from the data representing such dynamic multi-scale systems. AI-based tools for different management functions of the energy system are often seen as black-box models and this penalizes their acceptability by the end-users (traders, power system operators a.o.). The lack of interpretability of AI tools is a major challenge for a wider adoption of AI in the energy sector and a fundamental requirement to better support humans in the decision-aid process.
Agents of energy systems expect high levels of reliability for the various services provided by these systems (energy, ancillary services, flexibility, etc.): this ensures proper sizing of security measures and quality of service for end-users. As energy systems are impacted by multiple uncertainty sources (e.g. available resource of distributed renewable plants, climate change, market conditions, agent behaviors), developed AI tools should not only be performant on average situations, but be able to guarantee robust solutions in the case of extreme events, which may be a joint realization of multiple extreme conditions (e.g. on available resources, market conditions and grid state) and humans make decisions under high stress levels. In general, state-of-the-art AI-based approaches require large amounts of data for training and show high dependability from the particular physical system or case-study. Another challenge is to explore symbolic reasoning to guarantee that the extracted knowledge, in addition to be interpretable to humans, can be transferred and generalized to different systems.
Scientific Objectives, Methodology & Expected results
The scientific objectives of this thesis are:
- To develop advanced methods for enhancing interpretability of AI tools with application to the energy sector
- To cover important use cases of AI application to the energy sector such as decision-aid under extreme events or abnormal conditions and trading in the context of evolving energy markets
- And finally, to integrate in the methodology how humans understand complex systems and take decisions informed by AI tools
The thesis will start with a review of the definition of AI interpretability and its developments in different disciplines. A focus will be placed on understandable representations of data-driven decision-aid models for human operators in the energy sector. Explainability metrics for AI tools will be developed for applications to the energy sector. In order to increase the interpretability of the AI models, two different paradigms borrowed from the computer science domain will be explored and further developed. Genetic programming [Koza 1992] will be used to derive a symbolic representation for the data-driven model that can take the form of a single equation or decision-rules that evolve together according to a specific reward function. An alternative is inductive programming [Gulwani2015], where a template (or structured format) of algebraic equations is used to characterize the state-action relation and enables the integration of human expert knowledge. The main goal is to produce symbolic representations of the knowledge that requirement minimum changes when applied to different systems or case-studies. Real-world use-cases will be considered to demonstrate the added value of the proposed tools for decision making in different applications. An example of such use-case is that of trading of the production of a virtual power plant (aggregation of wind and photovoltaic plants) to the day-ahead and ancillary service markets. The typical model chain involves as much as 12 models for forecasting RES production and market quantities and a last step of stochastic optimisation to derive trading decisions. This complex chain may be replaced by a single AI-based model. The adoption though of such AI-based approach by the trader depends on the capacity to interpret its outputs.
The proposed topic is interdisciplinary as it combines research in artificial intelligence, data science and optimization and energy. The international dimension is strong as it gathers researchers from Mines ParisTech-PSL and INESC TEC, both leaders in their field.
The candidate will pass a period of at least a year at INESC TEC (Porto, Portugal). This will permit, among others, to apply for a European Doctorate Label. Additional stays are envisaged to laboratories with related activity to the topic.
George Kariniotakis and Ricardo Bessa
Created in 2012, Université PSL is aiming at developing interdisciplinary training programmes and science projects of excellence within its members. Its 140 laboratories and 2,900 researchers carry out high-level disciplinary research, both fundamental and applied, fostering a strong interdisciplinary approach. The scope of Université PSL covers all areas of knowledge and creation (Sciences, Humanities and Social Science, Engineering, the Arts). Its eleven component schools gather 17,000 students and have won more than 200 ERC. PSL has been ranked 36th in the 2020 Shanghai ranking (ARWU).
- Opportunity to conduct academic research in a top 100 university in the world.
- High-quality doctoral training rewarded by a PhD degree, prepared within Mines Paris - PSL and delivered by PSL.
- Access to cutting-edge infrastructures for research & innovation.
- Appointment for a period of 36 months (job contract delivered by the involved component school of PSL) based on a salary of 3100 € gross employer (including employer tax) per month or approximately a 2228 € gross salary per month.
- Job contract under the French labour legislation in force, respecting health and safety, and social security: 35 hours per week contract, 25 days of annual leave per year (“congés annuels”). Eventual complementary activities may be accepted or proposed by the co-supervisors (maximum of 64h/year for teaching, 32 day/year for specific missions).
- Short stay(s) or secondment in France or abroad are expected.
- An international environment supported by the adherence to the European Charter & Code.
- Access to AI training package, with a strong interdisciplinary focus, together with a Career development Plan.
- Applicants must have a Master’s degree (or be in the process of obtaining one) or have a University degree equivalent to a European Master’s (5-year duration) to be eligible at the time of the deadline of the relative call.
- There is no nationality or age criteria, but applicants must not have resided or carried out their main activity (work, studies, etc.) in France for more than 12 months in the 3 years immediately before the deadline of the call (MSCA Mobility rule).
- Applicants must declare to be available to start the programme on schedule.
For submitting your online application, go to: https://www.psl.eu/recherche/grands-projets-de-recherche/projets-europee...
The online application should contain the following documents:
- English translated transcripts from the Master’s degree (or equivalent 5-year degree). A copy of the Master’s degree or a certificate of achievement will be required later on for the final registration.
- International curriculum vitae and a cover letter explaining the reasons that lead him/her to prepare a PhD, why he/she applies to this offer and his/her professional project (guidelines will be given to the applicants in order to help him/her in the writing of his/her letter).
- Two academic reference letters.
- A statement duly signed on the mobility rules, availability, and conflicts of interest.
The applicants can only apply to one PhD project among the available ones. Multiple applications of one candidate will automatically make all his/her applications ineligible.
The applications will be analysed by the Management Team for eligibility and completeness. Afterwards, the applications will be reviewed by the Selection Committee. In the pre-selection round (March-April 2021), applicants will be rated using a scoring system based on 3 criteria (academic excellence, experience, motivation, and qualities). A shortlist of qualified applicants will be interviewed during the selection round (June 2021) to further assess their qualifications and skills according to the predefined selection criteria.
All information regarding the applications (criteria, composition of the Selection Committee, requirements) can be found on the website of the programme, in greater detail.
The selection and recruitment processes of the PhD student will be in accordance with the European Charter for Researchers and Code of Conduct of the Recruitment of Researchers. The recruitment process will be open, transparent, impartial, equitable, and merit based. There will be no discrimination based on race, gender, sexual orientation, religion of belief, disability, or age.
The Centre for Processes, Renewable Energies and Energy Systems (PERSEE) is one of the 18 R&D centers of Mines Paris - PSL. It has a long experience since the early 90’s on problems related to renewables integration and management and planning of Energy Systems. The PhD director has published as early as in 1996 the first journal paper ever with an application of AI in the renewable energies field. Today the research in PERSEE in the area focuses on problems that involve large/big amounts of data and develops solutions based on AI for the management and planning of power systems. Research in PERSEE spans the whole range of TRLs, from the development of concepts up to their demonstration to real world environments.
Mines Paris - PSL is a graduate school (Grande Ecole) in Science, Engineering and Economics under the tutelage of the Ministry of Industry. It provides multidisciplinary education (relying upon around 230 academics) to train high level engineers (150/year in “Master’s degree in science and executive education” track and 200 Advanced Master’s degrees/year) expected to fulfil high responsibilities in government bodies and in the industry in France and abroad. This mission is connected to a very strong research activity closely linked to the industry, that has proved its ability to innovate, anticipate and contribute to the evolutions of the socio-economic world in the fields of risk management, public policies, economics et sustainable development among others.
This long-standing link with the industry has lead Mines Paris - PSL to set up several major collaborations (Research and Education Chairs, Framework agreements…) with leading industrial partners such as SAFRAN, EDF, ArcelorMittal or Total to name a few.
On the academic side, it is a full member of Université PSL and as such participates to a wide number of structuring education and research (both applied and more fundamental) projects, especially with two other Grandes Ecoles (Chimie Paris - PSL and ESPCI - PSL). Mines Paris - PSL is also leader or acting member of several major international academic research programs and projects on its own.
Web site for additional job details
Required Research Experiences
YEARS OF RESEARCH EXPERIENCE1 - 4
REQUIRED EDUCATION LEVELMathematics: Master Degree or equivalent
REQUIRED LANGUAGESENGLISH: Excellent
- Typical profile: Engineer and/or Master of Science.
- Good level of general and scientific culture.
- Good level of knowledge of English and eventually French.
- Good analytical, synthesis, innovation and communication skills.
- Qualities of adaptability, creativity and motivation to work in a team.
- Coherent professional project.
- Specific skills for this thesis: strong background in Applied Mathematics (i.e. optimization) and/or AI.
- Skills in computer programming (i.e.PYTHON, R) are required.
EURAXESS offer ID: 578936
The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.
Please contact firstname.lastname@example.org if you wish to download all jobs in XML.