- This event has passed.
COMPUTING ALGORITHM FOR GEOSPATIAL DATA SESSION 2
March 16 @ 2:00 pm - 3:30 pm
HANDS-ON DEEP LEARNING ALGORITHMS FOR LAND COVER MAPPING FROM SATELLITE IMAGES
Deep learning (DL), a branch of machine learning (ML) and artificial intelligence (AI) is nowadays considered as a core technology of today’s Fourth and Fifth Industrial Revolution (Industry 4.0 and Industry 5.0). Due to its learning capabilities from raw data, DL technology originated from artificial neural network (ANN), has become a hot topic in the context of computing, and is widely applied in various application research areas like healthcare, remote sensing, semiconductor manufacturing industry, visual recognition, natural language processing, text analytics, cybersecurity, 5G Networks and many more. However, building an appropriate DL model is a challenging task, due to the dynamic nature and variations in real-world problems and data. Moreover, the lack of core understanding turns DL methods into black-box machines that hamper development at the standard level for societal applications. This session presents DL algorithms for Land Cover Mapping using Python Programming and deep Learning TensorFlow Library. This session also summarizes real-world application areas where deep learning techniques can be used. Finally, Practical demonstration of UNet and DPPNet model for Land Cover Mapping using Satellite Images and Python Deep Learning TensorFlow Library.
Learning Objectives:
The primary objective of the expert talk is to enlighten the audience on the potential and challenges of using Deep Learning Algorithms for Land Cover Mapping from Satellite Images both theoretical and practical. At the end of the session, the participants should be able to understand:
- Understand fundamental concepts of 2D U-Net and DPPNet CNN Models
- The challenges of working with Land Cover Mapping from Satellite Image
- Understand the advance deep learning algorithms
- How to practically implement DL techniques using TensorFlow
Target Audience: Students, researchers, academic and industry professionals who have foundational theoretical knowledge of Probability, Linear Algebra, Computer Vision, Image Processing and Fundamental of Artificial Neural Networks.