![](https://i.imgur.com/evE3GlG.png) # Machine Learning with spatial data seminar **27.02.24** :::danger :bell: **Notes:** An event to share and discuss technical details about your Machine Learning with spatial data work ::: ## Table of contents [toc] --- ## :link: Links :::info - This document: **siili.rahtiapp.fi/geoml_seminar** - Zoom link for online participants: https://cscfi.zoom.us/j/63054298580 - Materials: linked in schedule ::: --- :::warning ### :bell: Ad: Introduction to geospatial Python course **online 4.-6.3.24** Last chance to register (until tomorrow): https://ssl.eventilla.com/geospatial_python ::: --- :::warning ### Are you working in Finland? -> Please fill in this survey: https://link.webropolsurveys.com/S/2990BB63955084B4 ::: --- ## Code of Conduct We strive to follow the [Code of Conduct developed by The Carpentries organisation](https://docs.carpentries.org/topic_folders/policies/code-of-conduct.html) to foster a welcoming environment for everyone. In short: - Use welcoming and inclusive language - Be respectful of different viewpoints and experiences - Gracefully accept constructive criticism - Focus on what is best for the community - Show courtesy and respect towards other community members For code of conduct related issues at this seminar, please send an email to giscoord@csc.fi. ## :calendar: Schedule | time | speaker | topic | | ------ | ------ | ------ | |12.00 – 12.25| CSC, Samantha Wittke | [Intro & Welcome, What is CSC, How does this seminar work, Thanks to sponsors](https://gis-seminars.a3s.fi/2024-02-27/GeoML_seminar_intro.pdf) | || CSC, Mats Sjöberg | [Intro to ML at CSC](https://a3s.fi/mats/ml-tools-csc.pdf ) | |12.25 – 13.05| Leon-Friedrich Thomas | Deep Learning based Semantic Segmentation Workflow for the QGIS Plugin EnMAP-Box (slides not public) | || Janne Mäyrä | [geo2ml: python package for converting geospatial data to ML formats](https://gis-seminars.a3s.fi/2024-02-27/JanneMayra_SYKE.html) | || Mohammad Imangholiloo (online) | A New Approach for Feeding Multispectral Imagery into Convolutional Neural Networks Improved Classification of Seedlings | ||| + Buffer time | |13.05 – 13.45| Jorma Laaksonen | [Hyperspectral superresolution and multi-image fusion for remote sensing forest studies](https://gis-seminars.a3s.fi/2024-02-27/JormaLaaksonen_Aalto.pdf) | || Maria Yli-Heikkilä | Agricultural monitoring with satellite remote sensing (slides not public) | || Parvez Rana | [3-D modeling of biodiversity and ecosystem services](https://gis-seminars.a3s.fi/2024-02-27/RanaParvez_LUKE.pdf) | ||| + Buffer time | |13.45 – 14.20|| **Break** | |14.20 – 15.00| Pyry Kettunen | [Vector ML - case Gaze-Aware Interactive Map System](https://gis-seminars.a3s.fi/2024-02-27/PyryKettunen_FGI.pdf) | || Emma Turkulainen | [Monitoring Bark Beetle Damage: Technical Insights into UAS Image Classification with Deep Neural Networks](https://gis-seminars.a3s.fi/2024-02-27/EmmaTurkulainen_FGI.pdf) | || Andras Balazs | [Predicting tree species specific growing stock using ALS point clouds and a 3D-Convolutional Neural Network](https://gis-seminars.a3s.fi/2024-02-27/AndrasBalazs_LUKE.pdf) | ||| +Buffer time | |15.00 –15.30 | Ilja Vuorinne| Mapping invasive plant species using airborne hyperspectral data and weakly supervised deep learning (slides not public) | || Jere Raninen | [Building detection from Lidar data using 3DUNet](https://gis-seminars.a3s.fi/2024-02-27/JereRaninen_NLS.pdf) | || Emilia Hattula| [How the diversity of training data improves the 2D UNet building detection](https://gis-seminars.a3s.fi/2024-02-27/EmiliaHattula_NLS.pdf) | |15.30 -16.00| CSC | Discussion, Q&A | Note: The talk by Jani Kuurasuo | Deep learning for estimating 3D vegetation traits from multispectral UAVs was cancelled. ## Questions - **I have difficulty pasting my questions into HackMD/HedgeDoc (here). Do you have some instructions on how to write here?** - A: HackMD/HedgeDoc can look a bit differend depending on the view you are in. Can you see the three icons on top left corner, next to HackMD/HedgeDoc text? There’s pencil, this side-by-side symbol, and an eye (see below for a screenshot). In eye view, you can’t edit, you are just viewing. The other two reveal the markdown (MD) version of the page, which you can edit. I find it easiest to edit with the side-by-side view, but it can be a bit slow sometimes. First time opening the page, the small Edit (pencil) button might be on right next to the table of contents. Please note that it might make things faster if you **switch to view only mode when not editing**! :::info The small pencil icon for entering edit mode for the first time. You might need to scroll all the way up to see it. ![The icon corresponding to the edit link with title "Edit this note"](https://siili.rahtiapp.fi/uploads/f24239cd-3c6b-46f6-a61f-4f08c4d96415.png) ::: :::info The bigger HedgeDoc/HackMD toolbar for switching between modes later on. ![The toolbar from which the different modes can be accessed. You can also switch between edit and view mode using hotkeys ctrl-alt-v and ctrl-alt-e respectively](https://hackmd.io/_uploads/HJyCrkgj6.png) ::: - Your question here - answer will appear here - Your question here - answer will appear here - Your question here - answer will appear here - Your question here - answer will appear here - Your question here - answer will appear here - Your question here - answer will appear here - Your question here - answer will appear here ## Collaboration corner :::info Looking for collaborators on a new project? - Leave a project/idea description and your email address here for interested people to contact you! ::: - idea - email - idea - email - idea - email ## Discussion - What are your usual bottlenecks in Geospatial ML? What part of the process do you spent most time with? - .. - .. - .. - .. - What kind of training is missing in order to efficiently work with geospatial data for ML? - .. - .. - .. - ..