Post-doc on remote sensing and machine learning

The CMCC Foundation, a cross-cutting scientific research center on climate change and its interactions with the environment, society, the world of business, and policymakers is looking for a highly organized and motivated post-doc, specialist on remote sensing and machine learning applications for climate risk assessment, in particular related to wildfire prediction, and to growth, status and productivity of forests and their vulnerability to fires, to join our Impact on Agriculture, Forests and Ecosystem Services (IAFES) division, based in Sassari. The candidate should have a proven track record on international research and publication at the intersection of climate science, data analytics, and risk modeling.    

ROLE

The Post-Doctoral Researcher in this role will focus on advancing the use of remote sensing and machine learning to address critical challenges in climate risk assessment. Specifically, the role will center on wildfire prediction and the monitoring of forest growth, status, productivity, and vulnerability to fires. This interdisciplinary position combines expertise in geospatial data analysis, climate science, and artificial intelligence to deliver innovative solutions for understanding and mitigating the impacts of climate change on forest ecosystems.
The research conducted in this role will enhance the understanding of wildfire dynamics and forest vulnerability, providing critical insights for climate adaptation and mitigation strategies. Outputs will support the development of tools for early warning systems, sustainable forest management, and policy decision-making to build climate-resilient landscapes. This position is ideal for a researcher passionate about leveraging advanced technology to address urgent environmental challenges and contribute to the sustainable management of forests under a changing climate.

RESPONSIBILITIES

The post-doc will support the IAFES division, with:

• Wildfire Prediction:
  • Develop and implement machine learning models to predict wildfire occurrences and their potential impacts using remote sensing and environmental data.
  • Integrate climatic, meteorological, and vegetation datasets to identify risk factors and patterns associated with wildfires.
• Forest Monitoring:
  • Use remote sensing data to monitor forest growth, health, and productivity across different ecosystems.
  • Develop algorithms to assess forest vulnerability to fire and other climate-related stressors.
• Data Processing and Analysis:
  • Analyze large-scale geospatial datasets, including satellite imagery (e.g., Sentinel, Landsat, MODIS), LiDAR.
  • Employ advanced machine learning techniques (e.g., deep learning, random forests, ensemble models) to extract insights from diverse datasets.
• Research Integration:
  • Collaborate with interdisciplinary teams to integrate findings into broader climate risk assessments and forest management strategies.
  • Communicate research outcomes through high-impact publications and presentations at conferences.

REQUIREMENTS

• PhD in Environmental Sciences, Remote sensing, Agricultural and/or Forest engineering or equivalent subjects.
• Proficiency in remote sensing data processing tools (e.g., Google Earth Engine, ENVI, QGIS).
• Expertise in machine learning frameworks (e.g., TensorFlow, PyTorch, Scikit-learn).
• Strong programming skills in Python, R, or similar languages.
• Experience with geospatial analysis and visualization tools.
• Very good knowledge of the English language, with strong communication skills for collaboration within a multidisciplinary team.
• Availability to travel for limited periods

DURATION, COMPENSATION & BENEFITS

• The appointment period will be initially of 18 months, renewable for n°12 months additional months pending a positive evaluation.
• The gross annual salary range is from 28 to 35K Euros, depending on qualification and working experience.
• Welfare package, for minimum 12 months contract.
• Flexible working time as per internal policies
• Support during the immigration process, if needed.