Automated Extraction of Satellite BAthymetric data by Artificial Intelligence strategies
Project reference: 2204
The aim of the project is to start the development of methodologies to analyse COPERNICUS satellite data to extract low-resolution bathymetric data in shallow coastal areas where multibeam echosounder data is lacking. These satellite bathymetric extrapolations will provide new information useful for identifying the most critical areas where to plan new high-resolution data acquisitions from Autonomous Underwater Vehicle (AUV) and LiDAR from aircraft.
The challenge will be to develop a method able to extract bathymetry data using Machine Learning from multi-temporal satellite images. Particular emphasis will be placed on the use of HPC resources and the application of Image recognition algorithms related to artificial intelligence such as the Mask Recursive Convolutional Neural Network (Mask R-CNN). The preferred development environment in this case will be Python and the pandas, numpy, keras and tensorflow software packages. For the satellite derived bathymetry, Sentinel-2 or Landsat images along with a large datasets of existing high-resolution bathymetric data will be used.
Project Mentor: Silvia Ceramicola
Project Co-mentor: Veerle Huvenne, Gianluca Volpe
Site Co-ordinator: Massimiliano Guarrasi
The selected student will learn to manage oceanographic and satellite data to integrate different resolution data.
Increase student’s skills about:
– AI libs (e.g. PyTorch, Keras, TensorFlow, …)
Student Prerequisites (compulsory):
The student will need to have the following compulsory skills:
- Python main scientific libraries (at least basic knowledge):
- At least one of the following packages:
- Tensorflow, Keras
Student Prerequisites (desirable):
Experience in image recognition methods, GIS
Week 1: Training week with the other SoHPC students
Week 2: Training by CINECA (HPC facility, slurm batch scheduler, VNC, Blender, …) and OGS staff (How to read the data, how to visualize and explore them)
Week 3: Setup the workplan and start the work according with the student abilities and interest
Week 3 (end): Workplan ready.
Week 4-6: Continue the work on structures recognition
Week 7-8: Prepare the final video and report
Week 8 (end): The final video and report will be submitted
Final Product Description:
Our final result will be an automated tool to recognize seabed structures form oceanographic and satellite data. These satellite bathymetric extrapolations will provide new information useful for identifying the most critical areas where to plan new high-resolution data acquisitions from AUV and LiDAR from aircraft. The selected student will also prepare a short video and a final report illustrating his/her work.
Adapting the Project: Increasing the Difficulty:
Depending on the student skills he/she can try to recognize many different type of structures.
Adapting the Project: Decreasing the Difficulty:
In the case the student will not be able to complete the desired tool, he/she will work on the visualization of the data using some visualization tools
The oceanographic data and the standard software to inspect them will be given by OGS. Satellite data were taken from Copernicus website (https://www.copernicus.eu/en/copernicus-satellite-data-access). All the needed HPC software (mainly Python, Pytorch, Keras, Fensorflow, Pandas, numpy) is released open source and already available on the CINECA clusters that will be used by the students with their own provided accounts.
CINECA – Consorzio Interuniversitario