Postdoctoral researcher in Geospatial Machine Learning for Predicting Land Use Dynamics

This position requires expertise in geospatial machine learning with a focus on predicting land use dynamics. The ideal candidate should have advanced knowledge and experience in applying machine learning algorithms to spatial data, including proficiency in handling geospatial datasets and integrating remote sensing, GIS, and environmental data sources. Strong skills in programming languages commonly used in geospatial analysis and machine learning, such as Python or R, are essential, along with familiarity with relevant libraries and frameworks like TensorFlow, PyTorch, scikit-learn, or geospatial libraries such as GDAL, GeoPandas, or Rasterio. Experience in spatial statistics, temporal data analysis, and modeling land use change processes is important. The role likely requires a strong academic background, typically a PhD or equivalent research experience in fields such as geography, environmental science, computer science, or related disciplines with a focus on spatial data science or machine learning. Competencies in data preprocessing, feature engineering for spatial datasets, model validation, and interpretation of predictive models in ecological or land management contexts are critical. Additionally, the candidate should be capable of conducting independent research, publishing scientific results, and collaborating within interdisciplinary teams. Familiarity with high-performance computing environments and cloud platforms for scalable geospatial data processing may be advantageous. Overall, the role demands a combination of advanced technical skills in geospatial machine learning, strong analytical capabilities, and domain knowledge in land use and environmental systems.