From 889c2979fc59930ea0740748a85bb7d1d47d22e0 Mon Sep 17 00:00:00 2001 From: sdesabbata Date: Tue, 12 Sep 2023 01:43:37 +0100 Subject: [PATCH] Added link to slides --- docs/README.md | 4 ++++ .../learning-urban-form-gnn.html | 22 ++++++++++++++++++- .../learning-urban-form-gnn.qmd | 15 ++++++++----- 3 files changed, 35 insertions(+), 6 deletions(-) diff --git a/docs/README.md b/docs/README.md index 4eb93f2..87e3320 100644 --- a/docs/README.md +++ b/docs/README.md @@ -5,6 +5,10 @@ Graph theory has long provided the basis for the computational modelling of urba Our preliminary results (see [results and supplementary materials](#results-supplementary) below) illustrate how a model trained on a 1% random sample of street junctions in the UK can be used to explore the urban form of the city of Leicester, generating embeddings which are similar but distinct from classic metrics and able to capture key aspects such as the shift from urban to suburban structures. +## Slides + +The slides for our presentation at the [2nd International Workshop on Geospatial Knowledge Graphs and GeoAI: Methods, Models, and Resources](https://geokg-geoai2023.github.io/) (12th September, 2023, Leeds, UK) can be found [here](https://sdesabbata.github.io/gnn-urban-form/slides/geokg-geoai2023/learning-urban-form-gnn.html). + ## Data diff --git a/docs/slides/geokg-geoai2023/learning-urban-form-gnn.html b/docs/slides/geokg-geoai2023/learning-urban-form-gnn.html index 5ca4a84..3ceb54d 100644 --- a/docs/slides/geokg-geoai2023/learning-urban-form-gnn.html +++ b/docs/slides/geokg-geoai2023/learning-urban-form-gnn.html @@ -1316,7 +1316,12 @@

Results

+
+

+

Street network data by OpenStreetMap, under ODbL, and by Boeing (2020), under CC0 1.0

+
+

 

@@ -1332,7 +1337,12 @@

Results (embedding clustering)

+
+

+

Street network data by OpenStreetMap, under ODbL, and by Boeing (2020), under CC0 1.0

+
+

 

@@ -1348,7 +1358,12 @@

Results (ego-graph pooled)

+
+

+

Street network data by OpenStreetMap, under ODbL, and by Boeing (2020), under CC0 1.0

+
+

 

@@ -1550,7 +1565,12 @@

Thank you for your attention

Check out our GitHub repo

sdesabbata.github.io/gnn-urban-form

-

+
+
+

+

Street network data by OpenStreetMap, under ODbL, and by Boeing (2020), under CC0 1.0

+
+
diff --git a/docs/slides/geokg-geoai2023/learning-urban-form-gnn.qmd b/docs/slides/geokg-geoai2023/learning-urban-form-gnn.qmd index 5cff2c2..82cf740 100644 --- a/docs/slides/geokg-geoai2023/learning-urban-form-gnn.qmd +++ b/docs/slides/geokg-geoai2023/learning-urban-form-gnn.qmd @@ -22,6 +22,8 @@ bibliography: biblography-geokg-geoai2023.bib citations-hover: true --- + + ## Urban form (and function) @ARRIBASBEL2022102641 define urban form as *what a space "looks like"* compared to urban function, which focuses on *"what it is used for"*. @@ -97,7 +99,6 @@ Unsupervised learning of *nodes representations* - ## Graph AutoEncoder (some details) {.smaller} @@ -159,19 +160,23 @@ Leicester (UK) ::: :::: + + ## Results ::: {layout="[16,-1,16]" layout-valign="center"} -![](images/gnnuf_ea_v0-5-emb_Leicester_scatter-bivar.png) +![Street network data by OpenStreetMap, under ODbL, and by @DVN/KA5HJ3_2020, under CC0 1.0](images/gnnuf_ea_v0-5-emb_Leicester_scatter-bivar.png) ![](images/gnnuf_ea_v0-5-emb_Leicester_streetmap-bivar.png) + ::: + ## Results (embedding clustering) ::: {layout="[16,-1,16]" layout-valign="center"} -![](images/gnnuf_ea_v0-5-emb_Leicester_scatter-clust.png) +![Street network data by OpenStreetMap, under ODbL, and by @DVN/KA5HJ3_2020, under CC0 1.0](images/gnnuf_ea_v0-5-emb_Leicester_scatter-clust.png) ![](images/gnnuf_ea_v0-5-emb_Leicester_streetmap-clust.png) ::: @@ -181,7 +186,7 @@ Leicester (UK) ## Results (ego-graph pooled) ::: {layout="[16,-1,16]" layout-valign="center"} -![](images/gnnuf_ea_v0-5-emb-pooled_Leicester_scatter-bivar.png) +![Street network data by OpenStreetMap, under ODbL, and by @DVN/KA5HJ3_2020, under CC0 1.0](images/gnnuf_ea_v0-5-emb-pooled_Leicester_scatter-bivar.png) ![](images/gnnuf_ea_v0-5-emb-pooled_Leicester_streetmap-bivar.png) ::: @@ -255,7 +260,7 @@ GNNs can be used as an unsupervised framework to explore urban form [sdesabbata.github.io/gnn-urban-form](https://sdesabbata.github.io/gnn-urban-form/) -![](images/gnnuf_ea_v0-5-emb_Leicester_streetmap-bivar.png) +![Street network data by OpenStreetMap, under ODbL, and by @DVN/KA5HJ3_2020, under CC0 1.0](images/gnnuf_ea_v0-5-emb_Leicester_streetmap-bivar.png){width=80%} ::: ::: {.column width="5%"}