DISASTER RISK MONITORING USING SATELLITE IMAGERY
Embark on transformative learning as you gain experience constructing and implementing a deep learning model to automate flood identification through satellite imagery. This innovative workflow has the potential to revolutionize natural disaster management by reducing costs, improving operational efficiency, and significantly increasing overall effectiveness.
- Construct a machine learning workflow tailored to address challenges in disaster management solutions.
- Use hardware-accelerated tools to process extensive satellite imagery datasets.
- Apply transfer learning strategies to economically develop advanced deep learning segmentation models.
- Deploy deep learning models to enable near real-time analysis.
- Leverage the skills of deep learning-based models to rapidly detect and respond to floods.
- Proficiency in the Python programming language 3.
- Basic understanding of machine learning and deep learning principles (with emphasis on different CNN variants) and their application in pipelines.
- Curiosity to explore advanced methods for manipulating satellite imagery.
- NVIDIA DALI
- NVIDIA TAO Toolkit
- NVIDIA TensorRT
- NVIDIA Triton Inference Server.
“Deploying an Inference Model at Production Scale”: a self-paced course that focuses on Triton for deploying deep learning models built in different frameworks.
For additional training through the NVIDIA Deep Learning Institute, visit www.nvidia.com/dli.
The course was developed in collaboration with UNOSAT, the United Nations Satellite Centre.
Digital skills for all
Digital skills for the workforce
Digital skills for ICT professionals
Format of the training
Duration of the training
Type of training
Language of the training
Country providing the training