openeo - small updates

.all-contributorsrc

@@ -50,7 +50,7 @@
       "login": "jdries",
       "name": "Jeroen Dries",
       "avatar_url": "https://avatars.githubusercontent.com/u/5937096?v=4",
-      "profile": "https://remotesensing.vito.be/",
+      "profile": "https://remotesensing.vito.be/team/jeroen-dries",
       "contributions": [
         "ideas",
         "design",

tutorial/part2/advanced_workflows.md

@@ -51,6 +51,7 @@ Operational products, like [Copernicus landcover 3.0](https://land.copernicus.eu
 also based on random forest.
 
 Key takeaways:
+- Merging Sentinel-1 and Sentinel-2 data cubes
 - Transform a timeseries datacube into features for learning
 - Use ML processes directly from openEO
 

tutorial/part3/advanced_udf.ipynb

@@ -3,7 +3,6 @@
   {
    "cell_type": "markdown",
    "source": [
-    "\n",
     "## UDF with machine learning\n",
     "\n",
     "Algorithm type: spatiotemporal data chunk\n",
@@ -25,7 +24,11 @@
     "\n",
     "The local openEO processing support allows to start from samples that are pretty much 'raw' data, so that you also have the ability to change your preprocessing pipeline.\n",
     "\n",
-    "https://open-eo.github.io/openeo-python-client/cookbook/sampling.html"
+    "https://open-eo.github.io/openeo-python-client/cookbook/sampling.html\n",
+    "\n",
+    "The image below shows how sampling points of the Lucas database are spatially grouped to be able to sample all of Europe:\n",
+    "\n",
+    "![Lucas Sampling](../figures/sampling_openeo.png)"
    ],
    "metadata": {
     "collapsed": false