Solar irradiance nowcasting using artificial intelligence – image processing, deep learning, solar irradiance nowcasting, time series evaluation
Would you like to write your PhD thesis in our Institute of Solar Research at CIEMAT’s Plataforma Solar de Almeria (PSA) developing a solar irradiance forecasting tool based on AI and cameras?
Solar irradiance forecasts for the next minutes ahead can help to operate solar power plants and electricity grids during variable cloud conditions. Such shortest-term forecasts are also called nowcasts. Your objective is to improve the performance of solar irradiance nowcasts derived from local camera observations by means of artificial intelligence. The used ground-based cameras provide images of the sky or the ground. Positions and motion vectors of clouds in the sky or cloud shadows on the ground can be determined from these images. Furthermore, the radiative effect of the clouds is analyzed. Local measurements of radiometers are available for this purpose. Finally, solar irradiance nowcast of the immediate future are determined. Deep learning methods are especially suited for the image processing tasks at hand. Further artificial intelligence methods are of great interest for the evaluation of additional time series data related to the nowcasts.
Your tasks will be:
- Evaluate uncertainty of state of the art nowcasting approaches and identify key uncertainty sources
- Investigate potential of different artificial intelligence approaches
- Implement most promising artificial-intelligence-based models, e.g. RNN for cloud segmentation and tracking
- Benchmark new approaches with state-of-the-art approaches
- Documentation and publication of scientific results
We offer the opportunity for continuous education and advanced training possibilities by participation in several courses of DLR’s Graduate Program.
You will be part of a young, diverse and motivated team aiming to build a sustainable future. You will have the possibility to work every day knowing you’re doing your best to fix the planet and to fight climate change. The PhD thesis is planned to be finalized in three years.
We are always keen to improve our recruiting process:
Please refer in your application letter through which platform we caught your attention!
- Master’s degree (or equivalent) in computer science, meteorology, physics, engineering, natural science or similar
- programming skills (Python and/or Matlab) in particular related to artificial Intelligence and interest in extending already existing skills
- passion for innovative research, scientific and systematic way of working
- ability to work individually and together as part of an international team, on both experiments and simulations
- good communication skills
- good oral and written expression in English language. Interest to learn Spanish
Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development. Our unique infrastructure offers you a working environment in which you have unparalleled scope to develop your creative ideas and accomplish your professional objectives. Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (f/m/x). Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.