I would be very interested by working on that as well !
1 Like
This would be a super interesting challenge to work on! One could use the approach @daveluo used for building detection on drone images with the extra challenge of doing DL for images with more than 3 channels!
There are 3 medium blogposts about the challenge describing the dataset, its unqiue challenges and there are also some pretrained models available -> 1 // 2 // 3
4 Likes
Is the link restricted for an access from arbitrary IP addresses? I am getting the error:
The IP address of ... has not been recognised to access this page.
Please contact support@tandfonline.com quoting the IP address of ... for further assistance.
@lesscomfortable @PierreO Great! I would suggest we all throw ideas here 
Here’s a good listicle with a couple of free-ish satellite imagery resources. In the end I ended up not using them in my previous project, because I’m used to read google API docs and went with the Google maps static API.
That said, the main constraint I can think of for all “relevant” projects is with the availability and temporality of the data at inference time. Training data should be plentiful 
1 Like
Nice! Some Geo-Folks around it seams…
Has anyone here worked with Sentinel data? I’m interested in leveraging Sentinel1+2 (radar+optical)…
Coming from Argentina I am focused in agriculture:
- Predicting commodity pricing from crop hectares in the world (crazy but we can filter out later)
- Predicting plantation yields/counting crops (as per Dave Luo)
- Identifying pests and harm to vegetation health to attack them quickly
4 Likes
Predicting weather, be it a particular event like drought as you suggested @henripal, or just global weather is very interesting to me.
It’s not very far from agriculture either. I’m curious of how deep learning could fare in such a chaotic system.
I would love a project around counting crop as well, as you suggested @lesscomfortable. I’m really interested by image segmentation right now so it would fit right in !
2 Likes
I have worked with Sentinel 1+2 data for my master thesis where I used Random Forests + Support Vector Machine to do Landcover Classification. Would be interesting to see, what one could do with DL
1 Like
Nice. Is your thesis available online somewhere? Would love to take a look…
The whole thesis is not available as I got a bit distracted finishing it, but I have a git repo where most of the code and a conference presentation are included:
3 Likes
I enjoyed taking part in a US midwest soy/corn segmentation problem earlier this year. https://www.crowdanalytix.com/contests/agricultural-crop-cover-classification-challenge
There is huge potential in using LANDSAT + annotations from https://nassgeodata.gmu.edu/CropScape/ to train other cnn’s for other crops/locations (US) or anywhere else that has both imagery and annotations. If anything, choosing problems that have readymade annotations is my recommendation.
2 Likes
i practiced binary image segm on INRIA dataset. with no modifications to u-net i obtained 0.96 accuracy, 0.77 iou and 0.87 dice.
i found the spacenet competition a few weeks ago. i am glad we are doing this here.
1 Like
Along those lines, I came across the Global Forest Watch website - especially given the situation in California, some automated forest watcher sound like it would be useful.
Re: @digitalspecialists’s point, it seems like GFW has a fair amount of labeled data. Not sure if enough.
Descartes labs made a splash a couple years back with their DL crop yield prediction - but it didn’t seem to stand the test of time.
Anyway, I propose to select a couple of these ideas, and split the responsibility of fleshing them out? (data availability, usefulness, feasability, previous attempts, etc…)
4 Likes
How about a small poll to see where’s everyone at ? I think that’s all the ideas we currently mentioned but if there’s others you want me to add no problem !
- Predicting commodity pricing
- Predicting plantation yields/counting crops
- Identifying pests and harm to vegetation
- Predicting weather
0 voters
2 Likes
Back online & catching up from Thanksgiving holiday travel, it’s great to see the excitement, resources, & project thoughts shared so far!
I’ve updated the original post to include all links/resources cited so far. The post has now been been wikified so please feel free to edit/add directly.
Re:
in addition to what’s been suggested so far, I’ll add a few complementary ideas under the big umbrella of Planetary Health (defined by the Lancet as the "health of human civilisation and the state of the natural systems on which it depends”):
-
Infectious disease forecasting (particularly mosquito-borne diseases like malaria & dengue) as it relates to the changing climate:
- A dataset & challenge has already been created by DrivenData for Dengue Fever: https://www.drivendata.org/competitions/44/dengai-predicting-disease-spread/
- a profile of Los Alamos National Lab & Descartes Lab’s work on dengue fever: https://www.fastcompany.com/40584406/how-satellite-imagery-could-combat-infectious-diseases-around-the-world
-
Wildfire detection & tracking:
- I bet we could make something like this but even better: https://venturebeat.com/2018/07/18/descartes-labs-wildfire-watchsystem-uses-satellite-imagery-to-track-active-fires-on-twitter/
- Wildfire boundaries in the US are carefully mapped and published openly for multi-agency use, on systems like this: https://www.geomac.gov/viewer/viewer.shtml
-
Monitoring air pollution at higher resolutions, identifying emission sources, estimating pollution levels:
- There’s a lot of air quality-related satellite data like Sentinel-5P’s TROPOMI data which just became publicly accessible a few months ago and from ground sources like OpenAQ.
- I’m looking for the exact link but I’ve seen public listings of where all industrial polluters are located (i.e. coal plants). Estimates of how much pollution is emitted from these sources are not very good.
In terms of resources, I’ve added a few new links to the wiki:
- Resource Watch: https://resourcewatch.org/data/explore
- Stanford’s Sustainability & AI Lab (projects on crop yield analysis & poverty prediction): http://sustain.stanford.edu/projects/
Also for accessing remote sensing data, a new version of this just came out (haven’t had a chance to try it out yet but looks promising): https://github.com/pytroll/satpy
8 Likes
Great topic! I’m also working with remote sensing data, focusing now on the wildfires problem. There are many datasets available on Google EarthEngine (like Sentinel 1, 2, 3, 5, Lansat, VIIRS, Modis, and even weather forecasts from GFS), updated regularly. It can be useful to preprocess large datasets and only download the final images.
4 Likes
Cool, what aspects of the wildfires problem are you focused on?
I came across this a few days ago from the NASA Jet Propulsion Lab about the California fires:
Using Sentinel-1 SAR before/during comparisons to estimate structural damage. More maps & explanations here: https://maps.disasters.nasa.gov/arcgis/apps/MapSeries/index.html?appid=8014e6c744a945baa8700797ccffccf6
Here’s some more work mostly with SAR by the ARIA group at NASA/JPL: https://aria.jpl.nasa.gov/case_studies
I’m very interested to see how we could combine Sentinel-1 and 2 data via DL approaches to create this kind of change analysis/damage proxy map at higher accuracy & resolution.
This is a great idea. I’ve spent about 16 months (part-time) of research efforts in Deep Learning enabled Urban Performance Assessment and Design. I’d be glad to brainstorm and discuss with people with similar interests!
Kind regards,
Theodore.
2 Likes
My goal is to combine multiple sensors at multiple resolutions to find burned scars and eventually to create products such fire damage rating. For now I’m focusing on moderate resolution (500m/1000m) before moving to higher resolutions with Sentinel-2 and Landsat. I think that combining all available sources of information will be very important in all problems mentioned in this topic.
4 Likes
i want to detect changes in time of some area for flood damage. multispectral would be perfect.
1 Like