Satellite image deep learning

In this episode Robin catches up with Roberto Del Prete to learn about PyRaws. PyRaws is a powerful open source Python package that provides a comprehensive set of tools for working with Sentinel 2 raw imagery. It provides tools for band coregistration, geo-referencing, data visualisation, and image processing. What is particularly exciting is that this software could be deployed onto future satellites, enabling on-board processing using python. Note you can also view the video of this recording on YouTube here* https://github.com/ESA-PhiLab/PyRawS * https://www.linkedin.com/in/roberto-del-prete-8175a7147/ Bio: Roberto Del Prete is a PhD candidate focused on expanding the uptake of Deep Learning for enhancing the applications of onboard edge computing. His aim is to improve decision-making in time-critical scenarios by reducing the time lag required to process and deliver useful information to the ground. He is also working on developing autonomous spacecraft navigation systems using onboard instruments like cameras. Through his research he wants to contribute to the advancement of AI technology and its real-world applications, pushing the boundaries of what is possible to accomplish onboard. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this episode Robin catches up with Nathan Kundtz to learn about the creation, and use of synthetic image data in training machine machine models. Nathan has a PhD in physics, and over 40 peer reviewed papers and 15 patents to his name. As a serial entrepreneur, he has successfully founded multiple companies and raised over $250 million in venture capital funding. Note you can also view the video of this recording on YouTube here* Nathan LinkedIn* rendered.ai* DIRSIG This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In the episode I caught up with the co-founder of the company developing Orbuculum, Derek Ding, to learn more about this innovative new platform. What makes Derek's story even more intriguing is that he doesn't have a traditional background in remote sensing. However, fuelled by ambition and a desire to introduce new technologies, he is determined to transform the landscape of the Earth observation data market. My conversation with Derek was thought-provoking, and offered valuable insights into the innovative possibilities within our field. I hope you enjoy this episode. Please note the video is also available on YouTube* 🖥️ Orbuculum website* 📺 Demo video of Orbuculum platform* 🗣️ Orbuculum Discord* 💻 Orbuculum Github* 🐦 Orbuculum Twitter This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this episode, Robin catches up with Ryan Avery to learn about the machine learning workflow at Development Seed. The making of this episode was inspired by a three part blog series Ryan has authored on the ML tooling stack used at Development Seed. Please note the video is also available on YouTube- https://developmentseed.org/blog/2023-04-13-ml-tooling-3 - https://www.linkedin.com/in/ryan-avery-75b165a8/ Bio: Ryan is an expert in developing machine learning-powered services for processing satellite and camera trap imagery, and he is deeply passionate about leveraging machine learning to enhance environmental outcomes and improve livelihoods. In addition to his work at Development Seed, Ryan has made significant contributions to open-source. These include a comprehensive two-day geospatial python curriculum, an image segmentation model service, and a torchserve deployment of Megadetector for wildlife monitoring. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this video, Robin catches up with Michael Bewley to hear about the use of AI at Nearmap. Nearmap captures very high resolution aerial imagery and Michael and his team have trained a single segmentation model to identify 78 different target layers in the imagery. These layers can then be displayed on a map or accessed via an API. Please note the video is also available on YouTube* Michael on LinkedIn* Nearmap* Nearmap AI docsBio: Michael is the Vice President of AI and Computer Vision at Nearmap. He's worked as a data scientist in a range of areas including medical devices, underwater robotics and banking. For the last six years, he's been building machine learning based products on top of Nearmap's technology stack of Australian designed aerial imaging cameras, and one of the biggest aerial capture, photogrammetry and 3D reconstruction programs in the world. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

Join Robin in a career chat with Martha Morrisey, a senior machine learning engineer at Pachama, a company elevating remote sensing data and machine learning to fight climate change by monitoring carbon capture and storage projects in forests. In this episode, Martha shares her career journey and provides further insight into the role of a machine learning engineer.* Martha on LinkedIn* Pachama website* Video on YouTubeBio: Martha is a senior Machine Learning Engineer at Pachama. Prior to Pachama Martha worked at Development Seed, and Maxar. Martha has an undergraduate degree from UC Berkeley in Geography, and a master's degree in Geography from the University of Colorado, Boulder. Outside of work Martha loves spending time outside cycling, running, and attempting to take her cat on walks! This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this episode, Robin catches up with Gilberto Camara to talk about SITS. SITS is an open-source R package for land use and land cover classification of big Earth observation data using satellite image time series. Gilberto is a Senior Researcher in GIScience, Geoinformatics, Spatial Data Science and Land Use Change at Brazil’s National Institute for Space Research.* https://github.com/e-sensing/sits * https://gilbertocamara.org/* Video on YouTubeBio: Prof. Dr. Gilberto Câmara is a Brazilian researcher in Geoinformatics, GIScience, Spatial Analysis, and Land Use Modelling, who works at Brazil's National Institute for Space Research (INPE). He is internationally recognized for promoting free access for geospatial data and for setting up an efficient satellite monitoring of the Brazilian Amazon rainforest. After retiring from INPE in June 2016 after 35 years of work, he continues to conduct R&D activities at INPE as a Senior Research Fellow. Logo animation and thumbnail credits: Mikolaj Czerkawski @mikonvergence This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this career chat, Robin catches up with Nishant Yadav to hear about his path from PhD to Applied Scientist (II) at Microsoft Azure AI working on computer vision. Nishant graduated from Northeastern University in Boston, US, with a Ph.D. in machine learning with applications in environmental and climate science. His research focused on developing deep transfer learning methods for extracting information from remotely-sensed data (e.g., satellite imagery). Nishant is an AI optimist, and his current favourite hobby is learning more about generative AI. * https://www.linkedin.com/in/nisyad/* 📺 Video of this chat on YouTube This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this episode, Robin catches up with Michail Tarasiou to discuss the new paper, ViTs for SITS: Vision Transformers for Satellite Image Time Series. This paper introduces the temporo-spatial vision transformer (TSViT) architecture. The TSViT incorporates novel design choices that make it suitable for time series tasks such as crop classification. In this work, TSViT crop classification and segmentation models are trained and evaluated on Sentinel 2 datasets and achieve state of the art (SOTA) results on these tasks by a significant margin. This is an exciting step towards high accuracy and low cost & automated crop mapping using remote sensing imagery.Paper authors: Michail Tarasiou, Erik Chavez, Stefanos Zafeiriou* 📖 Paper* 💻 Code on Github* 📘 Transformers in remote sensing blog post* 👤 Michail on LinkedIn This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com

In this episode of the career chat series, Robin catches up with Zhuang-Fang NaNa Yi to hear about her career path into the role of senior machine learning engineer at Regrow Ag* https://www.linkedin.com/in/zhuang-fang-yi-phd-01178a34/* https://www.regrow.ag/Bio: Zhuang-Fang NaNa Yi is a senior machine learning engineer at Regrow Ag. Her day-to-day work involves building R&D and machine learning models to scale and generate accurate machine learning-derived data layers for sustainable and regenerative agriculture at Regrow. Formerly, she was a machine learning engineer & GeoAI team lead at Development Seed and a research scientist at World Agroforestry Centre. She had a Ph.D. in Ecology from the Chinese Academy of Sciences and a B.S. in Geography from Sun Yat-Sen University. Outside of work, she is an artist, and you can often find her work at local art galleries, art shows, and art centres in the DC area. This is a public episode. If you would like to discuss this with other subscribers or get access to bonus episodes, visit www.satellite-image-deep-learning.com