During the past decade, the RL has envisioned and built the ARIES (ARtificial Intelligence for Environment and Sustainability) platform, a technology that integrates network-available data and model components through semantics and machine reasoning.
Its underlying open-source software (k.LAB ) handles the full end-to-end process of integrating data and with multiple model integration types to predict complex change. It also supports selection of the most appropriate data and models using cloud technology and following an open data paradigm: the resulting insight remains open and available to society at large, and becomes a base for further computations, contributing to an ever-increasing knowledge base. For the first time, it is possible to consistently characterize and publish data and models for their integration in predictive models, building and field-testing technologies that have eluded researchers to date.
We are looking for an individual who can support strategic activities related to integrated data science and collaborative, integrated modelling on the semantic web (semantic meta-modelling).
Job description: Contribute to the ARIES (ARtificial Intelligence for Environment and Sustainability) platform, a semantic web infrastructure that uses artificial intelligence (AI) to build computational solutions to environmental, policy and sustainability problems. This technology, based on machine reasoning, machine learning, distributed computing and high-performance, multi-disciplinary and multi-paradigm system modelling, is the flagship product of the Integrated Modelling Partnership (IMP) which is expected to serve a growing number of worldwide users (from academia, governments, NGOs and industry) in the years to come.
ARIES’ current model resources largely focus on ecosystem services, using diverse modeling paradigms including machine learning and deductive models. The modeler will work as part of a team to develop and test new models that expand the breadth of ARIES’ model library, including ecosystem services and other environmental models at scales from local to global. Data-driven models built with a variety of machine learning classifiers have been applied so far to land cover change modelling, biodiversity modelling (https://www.sciencedirect.com/science/article/pii/S2212041617306423), water quality modelling and pollination modelling. The candidate will work to expand the use of ML libraries (e.g., Weka) and applications beyond the state of the art.
The position may require international travel on an as-needed basis.
Desired machine learning skills:
- Familiarity with machine learning fundamentals.
- Aware of optimization techniques and experience with different problems and domains, ideally in spatial applications.
- Familiarity with traditional ML models (k-means, KNN, decision trees, SVM, Bayesian/graphical models, Gaussian process, etc.).
- Able to work in different coding environments (local, notebooks, containers) and familiar with software engineering workflows (testing, code management/Git) – candidates with experience using multiple toolkits or platforms are preferred.
- Handling of large data sets and models on distributed file systems.
Additional experience/skills required:
- A PhD in Computer Science, Statistics, Ecology, Economics, Engineering, Geography or other fields relevant to the position.
- Strong analytical skills and an ability to learn quickly and to think outside the box. Our work is very innovative and you should expect your job to be both as intellectually challenging and as rewarding. A strong motivation and a desire to learn and explore new technologies are a must.
- Experience with environmental/ecosystem services modeling.
- Working knowledge of geomatics and, in particular, open-source GIS. Knowledge of OGC services, Geotools, GeoServer is considered a plus.
- Programming ability in any language, particularly Java, is considered an asset.
- Excellent interpersonal and communication skills.
- Excellent written and oral command of English.
- Ability to work independently, with a diverse, multi-location and multi-lingual team.
