Sorry, this entry is only available in French.

What's Changed

• Fix user interface language not respecting system locale when available
• Work around an upstream Qt crash when a value relations editor combo box pick leads to its container to be hidden
• Fix cloud attachments not uploaded immediately when hitting the synchronize button
• Fix layer login popup getting into the top / bottom system margins
• Fix initiating a tracking session with a feature form containing relations
• Fix geometry digitizing step missing when adding a relationship parent via the relationship combo box
• To avoid interference with snapping results when creating features using a mouse/stylus, do not reset coordinate cursor when rubber band is frozen

Discover how Camptocamp, in collaboration with Zurich, used Mergin Maps and QGIS to map bird nesting sites, empowering volunteers to collect accurate survey data.

In the last month of October, 18 new plugins were published in the QGIS plugin repository.

Here follows the quick overview in reverse chronological order. If any of the names or short descriptions catches your attention, you can find the direct link to the plugin page in the table below:

It’s been a while since my post on geo and the AI hype in 2019. Back then, I didn’t use the term “GeoAI”, even though it has certainly been around for a while (including, e.g., with dedicated SIGSPATIAL workshops since 2017).

GeoAI isn’t one single thing. It’s an umbrella term, including: “AI for Geo” (using AI methods in Geo, e.g. deep learning for object recognition in remote sensing images) and “Geo for AI” (integrating geographic concepts into AI models, e.g. by building spatially explicit models). [Zhang 2020] [Li et al. 2024]

Today’s post is a collection of key GeoAI developments I’m aware of. If I missed anything you are excited about, please let me know here in the comments or over on Mastodon.

Background

A week ago, I had the pleasure to attend a “Specialist Meeting” on GeoAI here in Vienna, meeting over 40 researchers from around the world, from Master students to professor emeritus. Huge props to Jano (Prof. Krzysztof Janowicz) and his team at Uni Wien for bringing this awesome group of people together.

The elephant in the room: LLMs

Unsurprisingly, LLMs and the claims they make about geography are a mayor issue due to the mistakes they make and the biases behind them. An infamous example is AI’s issue with understanding topology:

Even if recent versions of ChatGPT (such as GTP 4o) do a better job with this specific example, this doesn’t make their answers reliable. So between the trustworthiness, reproducibility, explainability, and sustainability issues … LLMs have a long way to go. And it’s not clear whether they are going in the right direction right now.

Geospatial foundation models

Prithvi, a model developed by NASA, IBM, et al. in 2023, is one of the first geospatial foundation models. Like much of GeoAI, Prithvi deals with remote sensing data. Specifically, it is trained on Landsat and Sentinel-2 (HLS) imagery, with applications in flood mapping and wildfire prediction. And maybe best of all: the model is open-source and publicly available.

Spatiotemporal machine learning model specifications

In the general AI community, model cards have become a common way to share information about models. However, identifying the right model for spatiotemporal tasks is hard since there are no standardized descriptions in existing model catalogs (e.g. Hugging Face, DLHub or MLFlow). To address this issue, [Charette-Migneault et al. 2024] have proposed the Machine Learning Model (MLM) extension for the SpatioTemporal Asset Catalogs (STAC). But, yet again, this development is targeting models trained with remote sensing imagery.

Similarly, the OGC Training Data Markup Language for Artificial Intelligence (TrainingDML-AI) and its ISO equivalent are limited to EO as well …

Spatial knowledge graphs

For those among us working mostly with vector data, the KnowWhereGraph is an interesting development. It’s the first geo-enriched knowledge graph [Janowicz et al. 2022] that helps answer geospatial questions by integrating a variety of spatial datasets through hierarchical grids, standard region boundaries and appropriate ontology and knowledge graph schema development. However, so far, the KnowWhereGraph is mostly limited to the United States.

Explainable AI (XAI) and geo

While answers from knowledge graphs are intrinsically explainable, many other (Geo)AI solutions are built on AI approaches that result in black box models.

Graph neural networks (GNNs) have become very popular in GeoAI (including in urban analytics and mobility [Jalali et al. 2023] [Liu et al. 2024]) but their black box nature limits their practical usefulness in domains where transparency and trustworthiness are crucial. To offer insights into how model predictions are made, [Liu et al. 2024] propose a spatially explicit GeoAI-based method that combines a graph convolutional network and a graph-based XAI method, called GNNExplainer to explore the correlation between urban objects.

Reproducibility et al.

The AI hype in geo is still going strong. Journals are being flooded with paper submissions and good reviewers are hard to come by. In many geo-related venues, it is still acceptable to present an AI paper without making code or model available. (We recently discussed this issue for mobility AI specifically [Graser et al. 2024].)

I’m convinced we can and should do better: quality over quantity, moving steadily, building and fixing things.

References

• Charette-Migneault, F., Avery, R., Pondi, B., Omojola, J., Vaccari, S., Membari, P., … & Sundwall, J. (2024). Machine Learning Model Specification for Cataloging Spatio-Temporal Models. In Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Searching and Mining Large Collections of Geospatial Data (pp. 36-39).
• Graser, A., Jalali, A., Lampert, J., Weißenfeld, A., & Janowicz, K. (2024). MobilityDL: a review of deep learning from trajectory data. GeoInformatica, 1-33.
• Jakubik, J., Roy, S., Phillips, C., Fraccaro, P., Godwin, D., Zadrozny, B., … & Edwards, B. (2023) Foundation models for generalist geospatial artificial intelligence. arXiv preprint arXiv:2310.18660.
• Jalali, A., Graser, A., & Heistracher, C. (2023). Towards eXplainable AI for Mobility Data Science. arXiv preprint arXiv:2307.08461.
• Janowicz, K., Hitzler, P., Li, W., Rehberger, D., Schildhauer, M., Zhu, R., … & Currier, K. (2022). Know, Know Where, KnowWhereGraph: A densely connected, cross-domain knowledge graph and geo-enrichment service stack for applications in environmental intelligence. AI Magazine, 43(1), 30-39.
• Li, W., Arundel, S., Gao, S., Goodchild, M., Hu, Y., Wang, S., & Zipf, A. (2024). GeoAI for Science and the Science of GeoAI. Journal of Spatial Information Science, (29), 1-17.
• Liu, P., Zhang, Y., & Biljecki, F. (2024). Explainable spatially explicit geospatial artificial intelligence in urban analytics. Environment and Planning B: Urban Analytics and City Science, 51(5), 1104-1123.
• OGC Training Data Markup Language for Artificial Intelligence (TrainingDML-AI) Part 1: Conceptual Model Standard (2023)
• Zhang, L. (2020). Explainable Machine Learning for Activity Modeling in GeoAI. Doctoral dissertation, George Mason University.

We’ve added measurement tools to Mergin Maps, allowing you to measure both distance and area directly within the app. The new "Measure" action is accessible from the "more" menu, where you can easily add points to calculate lengths and areas in your projects. The process is similar to creating a line feature, with a live display of the measured distance and options to undo, add points, or complete the measurement. Measurements are following your QGIS distance and area project units.

Read more about the measurement tool in our documentation: https://merginmaps.com/docs/field/measure/

What's Changed

• Improve handling of captured photo's ratio and resolution
• Improve feature attribute pasting
• Optimize addition of child feature in a parent feature being edited
• Guard from potential crash when loading a project that requires authentication credentials
• Fix large files constantly being re-downloaded when synchronizing cloud projects

How to contribute to GRASS GIS development: Guidance for new developers in the GRASS GIS Project.

The post How to contribute to GRASS GIS development appeared first on Markus Neteler Consulting.

You can now preview your project data directly from the project details page—no need to open QGIS or the mobile app!

Maps in dashboard are currently in beta, and we’re more than happy to hear your feedback. Share your thoughts and help us improve it here: https://wishlist.merginmaps.com/p/let-s-get-maps-in-dashboard-out-of-beta.

Sorry, this entry is only available in French.

Oslandia is the main partner of OPENGIS.ch around QField. We are proud today to forward the announcement of the new QField release 3.4 “Ebo”.

Main highlights

A new geofencing framework has landed, enabling users to configure QField behaviors in relation to geofenced areas and user positioning. Geofenced areas are defined at the project-level and shaped by polygons from a chosen vector layer. The three available geofencing behaviours in this new release are:

• Alert user when inside an area polygon;
• Alert user when outside all defined area polygons and
• Inform the user when entering and leaving an area polygons.

In addition to being alerted or informed, users can also prevent digitizing of features when being alerted by the first or second behaviour. The configuration of this functionality is done in QGIS using QFieldSync.

Pro tip: geofencing settings are embedded within projects, which means it is easy to deploy these constraints to a team of field workers through QFieldCloud. Thanks Terrex Seismic for sponsoring this functionality.

QField now offers users access to a brand new processing toolbox containing over a dozen algorithms for manipulating digitized geometries directly in the field. As with many parts of QField, this feature relies on QGIS’ core library, namely its processing framework and the numerous, well-maintained algorithms it comes with.

The algorithms exposed in QField unlock many useful functionalities for refining geometries, including orthogonalization, smoothing, buffering, rotation, affine transformation, etc. As users configure algorithms’ parameters, a grey preview of the output will be visible as an overlay on top of the map canvas.

To reach the processing toolbox in QField, select one or more features by long-pressing on them in the features list, open the 3-dot menu and click on the process selected feature(s) action. Are you excited about this one? Send your thanks to the National Land Survey of Finland, who’s support made this a reality.

QField’s camera has gained support for customized ratio and resolution of photos, as well as the ability to stamp details – date and time as well as location details – onto captured photos. In fact, QField’s own camera has received so much attention in the last few releases that it was decided to make it the default one. On supported platforms, users can switch to their OS camera by disabling the native camera option found at the bottom of the QField settings’ general tab.

Wait, there’s more

There are plenty more improvements packed into this release from project variables editing using a revamped variables editor through to integration of QField documentation help in the search bar and the ability to search cloud project lists. Read the full 3.4 changelog to know more, and enjoy the release!

Contact us !

A question concerning QField ? Interested in QField deployment ? Do not hesitate to contact Oslandia to discuss your project !

In September a total of 20 new plugins were published in the QGIS plugin repository.

Highlight

In the last month some AI-related plugins became available for users, namely IntelliGeo and TreeEyed, which in addition to the increasing number of tools, greatly contribute for the adaptation of QGIS to current and future needs, showcasing it as one of the best options for beginners and experts alike to conduct a number of geospatial analyses.

As stated by their authors, with IntelliGeo there’s a chat interface where users can detail their requests, and the output is either a PyQGIS code or a graphical processing model, which can in turn be executed directly in QGIS.

As for the TreeEyed plugin, its main objective is the monitoring of trees by generating vector and raster datasets from high resolution RGB imagery.

Overview

Here follows the quick overview in reverse chronological order. If any of the names or short descriptions catches your attention, you can find the direct link to the plugin page in the table below:

After the initial ChatGPT hype in 2023 (when we saw the first LLM-backed QGIS plugins, e.g. QChatGPT and QGPT Agent), there has been a notable slump in new development. As far as I can tell, none of the early plugins are actively maintained anymore. They were nice tech demos but with limited utility.

However, in the last month, I saw two new approaches for combining LLMs with QGIS that I want to share in this post:

IntelliGeo plugin: generating PyQGIS scripts or graphical models

At the QGIS User Conference in Bratislava, I had the pleasure to attend the “Large Language Models and GIS” workshop presented by Gustavo Garcia and Zehao Lu from the the University of Twente. There, they presented the IntelliGeo Plugin which enables the automatic generation of PyQGIS scripts and graphical models.

The workshop was packed. After we installed all dependencies and the plugin, it was exciting to test the graphical model generation capabilities. During the workshop, we used OpenAI’s API but the readme also mentions support for Cohere.

I was surprised to learn that even simple graphical models are actually pretty large files. This makes it very challenging to generate and/or modify models because they take up a big part of the LLM’s context window. Therefore, I expect that the PyQGIS script generation will be easier to achieve. But, of course, model generation would be even more impressive and useful since models are easier to edit for most users than code.

ChatGeoAI: chat with PyQGIS

ChatGeoAI is an approach presented in Mansourian, A.; Oucheikh, R. (2024). ChatGeoAI: Enabling Geospatial Analysis for Public through Natural Language, with Large Language Models. ISPRS Int. J. Geo-Inf., 13, 348.

It uses a fine-tuned Llama 2 model in combination with spaCy for entity recognition and WorldKG ontology to write PyQGIS code that can perform a variety of different geospatial analysis tasks on OpenStreetMap data.

The paper is very interesting, describing the LLM fine-tuning, integration with QGIS, and evaluation of the generated code using different metrics. However, as far as I can tell, the tool is not publicly available and, therefore, cannot be tested.

Are you aware of more examples that integrate QGIS with LLMs? Please share them in the comments below. I’d love to hear about them.

QField 3.4 is out, and it won’t disappoint. It has tons of new features that continue to push the limits of what users can do in the field.

Main highlights

A new geofencing framework has landed, enabling users to configure QField behaviors in relation to geofenced areas and user positioning. Geofenced areas are defined at the project-level and shaped by polygons from a chosen vector layer. The three available geofencing behaviours in this new release are:

• Alert user when inside an area polygon;
• Alert user when outside all defined area polygons and
• Inform the user when entering and leaving an area polygons.

In addition to being alerted or informed, users can also prevent digitizing of features when being alerted by the first or second behaviour. The configuration of this functionality is done in QGIS using QFieldSync.

Pro tip: geofencing settings are embedded within projects, which means it is easy to deploy these constraints to a team of field workers through QFieldCloud. Thanks Terrex Seismic for sponsoring this functionality.

QField now offers users access to a brand new processing toolbox containing over a dozen algorithms for manipulating digitized geometries directly in the field. As with many parts of QField, this feature relies on QGIS’ core library, namely its processing framework and the numerous, well-maintained algorithms it comes with.

The algorithms exposed in QField unlock many useful functionalities for refining geometries, including orthogonalization, smoothing, buffering, rotation, affine transformation, etc. As users configure algorithms’ parameters, a grey preview of the output will be visible as an overlay on top of the map canvas.

To reach the processing toolbox in QField, select one or more features by long-pressing on them in the features list, open the 3-dot menu and click on the process selected feature(s) action. Are you excited about this one? Send your thanks to the National Land Survey of Finland, who’s support made this a reality.

QField’s camera has gained support for customized ratio and resolution of photos, as well as the ability to stamp details – date and time as well as location details – onto captured photos. In fact, QField’s own camera has received so much attention in the last few releases that we have decided to make it the default one. On supported platforms, users can switch to their OS camera by disabling the native camera option found at the bottom of the QField settings’ general tab.

Wait, there’s more

There are plenty more improvements packed into this release from project variables editing using a revamped variables editor through to integration of QField documentation help in the search bar and the ability to search cloud project lists. Read the full 3.4 changelog to know more, and enjoy the release!

The post Migration of grass-dev mailing list to OSGeo Discourse appeared first on Markus Neteler Consulting.

What's Changed

• Prevent feature form crash with blob attributes
• Fix regression with cloud project's synchronize and push buttons sometimes not responsive to clicks
• Fix multi-line handling of expressions within QML / HTML editor widgets
• Fix regression with value relation editor widget search bar not reacting to keystrokes with a number of virtual keyboards
• Update translations (thanks to our growing group of contributors!)

The app now respects QGIS sorting rules when listing features from a specific layer. Navigate to “Layers -> select a layer”, and the feature list will follow the sorting set in QGIS. Sorting can be set in QGIS by clicking a column to toggle between ascending or descending order, or set a custom sort expression through the popup menu. The sorting order is saved in the QGIS project file and will be automatically applied in the app.

We’ve added support for ordering entries by value in value relation widgets. To enable this feature, simply check the option in the QGIS layer’s attribute form configuration. Once selected, the list will automatically be sorted by value. See the screenshot below for details.

Today, we celebrate a true geospatial legend: GRASS GIS!

The post Happy 41st birthday, GRASS GIS! appeared first on Markus Neteler Consulting.

The GRASS GIS 8.4.0RC1 release provides more than 515 improvements and fixes with respect to the release 8.3.2. Please support us in testing this release candidate.

The post GRASS GIS 8.4.0RC1 released appeared first on Markus Neteler Consulting.