R&D Engineer – AI Modelling for Real‑Time Prediction of Degradation in New PV Technologies F/H

🌟 Job offer : R&D Engineer – AI Modelling for Real‑Time Prediction of Degradation in New PV Technologies F/H 🌟

📅 Contract type : CDD

⏳Duration : 24 months

📍 Location : Palaiseau (91120)

📚 Formation : M2 or engineer school in data science, physics modelling

Context

The Île-de-France Photovoltaic Institute (IPVF), is an institute for the energy transition created in 2013. It is a scientific and technical center dedicated to the research and development of solar technologies. Located on Paris-Saclay campus, it brings together its own staff, employees of its partners, and those of external companies. The IPVF aims to become one of the world's leading centers for research, innovation, and training in the field of energy transition.

The IPVF's primary objective is to improve the performance and competitiveness of photovoltaic cells and to develop breakthrough technologies by leveraging four key drivers:

• An ambitious research program;
• Hosting 150 researchers and their laboratories on Paris-Saclay campus
• A cutting-edge technological platform (8,000 m²) open to stakeholders in the photovoltaic industry, and housing more than 100 state-of-the-art equipment units housed in clean rooms.
• A training program mainly based on a master's degree, supervision of doctoral students, and continuing education

Data modelling at IPVF

Perovskite solar cells (PSCs) and associated tandems have gained significant attention due to their high-power conversion efficiency (PCE) and potential for low-cost production. However, their stability under various environmental conditions remains a major challenge. PSCs are susceptible to degradation from factors such as light, heat, humidity, and reverse bias. Addressing these stability issues is crucial for their commercial viability.

Machine learning (ML) techniques have been increasingly applied to predict and enhance the stability of PSCs. These methods can analyze large datasets to identify patterns, predict and optimize perovskite degradation.

Perovskite‑based photovoltaic technologies and tandem architectures are rapidly reaching maturity and are expected to be deployed industrially in the near term. However, real‑time degradation prediction in industrial‑scale PV fields remains under active investigation and represents a highly promising industrial challenge. The integration of AI‑based models represents a strategic lever to better understand degradation, to predict degradation in real time in PV fields using industrial methods, and to accelerate the validation of these emerging technologies.

Main missions

AI Modeling and Degradation Prediction, Develop AI‑based models to:

• Estimate in real time the power output and degradation of a PV field equipped with new technologies (perovskite/ tandem), for integration into MPPT strategies. Develop AI models capable of predicting degradation under real operating conditions in PV fields, with future integration into MPPT strategies for perovskite and tandem technologies.
• Use large available perovskite degradation datasets for AI and big‑data analysis.
• Embed these models into a decision‑support and field‑deployment tool to facilitate the industrial rollout of perovskite and tandem modules.
• Identify and quantify the dominant meteorological stress factors driving degradation. And contribute to recommend the most representative indoor testing protocols, aligned with real outdoor stressors. Analyze datasets, exploiting real PV‑field data to identify the main meteorological stress factors (irradiance dose, thermal gradients, day/night cycling, humidity, etc.).
• Apply the developed AI models to the prediction of physical phenomena (regression, time‑series forecasting, and hybrid models combining physics and data).

Profile

• Knowledge or proficiency in AI/ML approaches applied to time‑series analysis and the prediction of physical phenomena (regression, time‑series models, hybrid physics‑informed + data‑driven models).
• Strong skills in data analysis, modelling, and processing large datasets.
• Experience in AI‑based modelling.
• Critical thinking, scientific rigor, and autonomy.
• Ability to work in a collaborative environment (R&D teams, industry partners, laboratories).
• Excellent communication and synthesis skills.
• PVSyst knowledge is a plus