We want to make land cover data that is always up to date
- New releases
Last year we released an imperviousness map for Denmark in high resolution and with high accuracy. The map was created using machine learning which allows for nation-wide cost-effective mapping.
The map was well received and has been used extensively in city planning and surface water management across Denmark.
![](https://scalgo-web.imgix.net/images/copenhagen2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=312&q=80&w=750&s=cee9cc5c4eb488fca5a550c9513c91fd 750w, https://scalgo-web.imgix.net/images/copenhagen2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=416&q=80&w=1000&s=a51b4f2c847a61256edbc526b97f04f9 1000w, https://scalgo-web.imgix.net/images/copenhagen2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=521&q=80&w=1250&s=a7d5ebee661f7d9e0a2ef6c6d0a645a6 1250w, https://scalgo-web.imgix.net/images/copenhagen2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=523&q=80&w=1256&s=a048187ec8157cc1ebe6c2bc4e5e7a85 1256w)
Figure 1. Last year we released an imperviousness map for Denmark in high resolution and with high accuracy.
Since then, we have been working on improving the method further.
"In the first map we used orthophotos from 2015 and 2016 because those photos were most similar to the available Lidar point cloud data in our training areas" say Jonas, machine learning expert at SCALGO.
The fusion of different input features, orthophotos from 2015-2016 and Lidar data, enabled ground-breaking performance in automated imperviousness mapping. But this fusion also introduced some problems.
“In Denmark, Lidar data is collected with a 5-year cycle. This means that some of the Lidar data doesn’t match the chosen orthophotos simply because urban areas develop fast”, Jonas explains.
“This confuses the model and reduces performance in some areas. Also, a 5-year update in data is not good enough if we want to create up-to-date land cover maps”.
![](https://scalgo-web.imgix.net/images/Billede1.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=432&q=80&w=750&s=bbee4d874accce88620646ea4cf7d44d 750w, https://scalgo-web.imgix.net/images/Billede1.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=575&q=80&w=1000&s=ca4730060ef8890c9e4895cbd9b7b7d6 1000w, https://scalgo-web.imgix.net/images/Billede1.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=719&q=80&w=1250&s=7f55728ab02a059b6a22611e552b9fd3 1250w, https://scalgo-web.imgix.net/images/Billede1.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=863&q=80&w=1500&s=d6b796191bdd89992e95a6be93c13f1b 1500w, https://scalgo-web.imgix.net/images/Billede1.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=1007&q=80&w=1750&s=48106b8d29f1099b1e2c7ea67065c814 1750w)
Figure 2. Ørestaden, large development site in Copenhagen. In the map initial map (on the left), a mismatch between lidar data and photos resulted in a poor assessment. In the updated map (on the right) imperviousness is mapped with high accuracy.
Throughout the last year Jonas has worked on creating a new map, relying on only a single orthophoto source while improving performance compared to the previous model.
“Orthophotos are, in Denmark, updated every year. If we can become independent from lidar data we can make maps that are much more up to date”, says Jonas.
![](https://scalgo-web.imgix.net/images/Billede2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=321&q=80&w=750&s=d82876e08fe975edbfcb3f717078e84a 750w, https://scalgo-web.imgix.net/images/Billede2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=428&q=80&w=1000&s=effc2957f35fe50011540c196fa9d967 1000w, https://scalgo-web.imgix.net/images/Billede2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=535&q=80&w=1250&s=30878d271644c70b596302b64a698f24 1250w, https://scalgo-web.imgix.net/images/Billede2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=642&q=80&w=1500&s=3beddcc86af6067e9c8a2b13af658a67 1500w, https://scalgo-web.imgix.net/images/Billede2.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=749&q=80&w=1750&s=5e620e22fa1c4426461085b6512bbfe6 1750w)
Figure 3. Urban areas develop fast. Lidar data collection cannot keep up with this development.
The new machine learning model is trained using orthophotos from varying years, which allows for training the model to understand different kinds of shadows, brightness in the pictures, colours, and other details in the photos. By doing this, Jonas has developed a model that is much more robust.
The new model has improved the performance in many locations, despite using less input data. An example is suburban areas where the new model maps driveways better than before.
![](https://scalgo-web.imgix.net/images/Billede3.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=251&q=80&w=750&s=5a38e0932e9c589c6c6ab9bd65952bd3 750w, https://scalgo-web.imgix.net/images/Billede3.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=335&q=80&w=1000&s=9f87fd1feb0520eb9249090041974faa 1000w, https://scalgo-web.imgix.net/images/Billede3.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=419&q=80&w=1250&s=056a55841b5ac468f4026b4740a2c91e 1250w, https://scalgo-web.imgix.net/images/Billede3.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=503&q=80&w=1500&s=690944533913c1b2a35a042301a492aa 1500w, https://scalgo-web.imgix.net/images/Billede3.png?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=586&q=80&w=1750&s=d9d3ad7a213627a5708a953e9cc5bef7 1750w)
Figure 4. Example to the left is from the old model while example to the right is from the new model. Despite using less input data, performance has improved in many areas of the new model.
An updated imperviousness map that uses orthophotos from 2020 has now been released and is available for all SCALGO Live users in Denmark. Our goal is to continue developing our model and release imperviousness maps to users in other countries too.
![](https://scalgo-web.imgix.net/images/Sara.jpg?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=120&q=80&w=120&s=71aaf346cec858e4b7bf7aa5fee07a4c 120w, https://scalgo-web.imgix.net/images/Sara.jpg?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=180&q=80&w=180&s=3c98cccd1bfe160394dbeaf0314d6132 180w, https://scalgo-web.imgix.net/images/Sara.jpg?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=240&q=80&w=240&s=e0a34e7ee03ca23ca2bb71db64472612 240w, https://scalgo-web.imgix.net/images/Sara.jpg?auto=compress%2Cformat&crop=focalpoint&cs=srgb&fit=crop&fp-x=0.5&fp-y=0.5&h=360&q=80&w=360&s=206d93074274c266152d48c033efa554 360w)