Agriculture Digitalization is moving fast and there are more and more companies and developers providing solutions for crops monitoring, asset management, developing fertilizer optimization tools and doing other amazing digital stuff to make agriculture business more effective.
Whenever it comes to agriculture management — the fundamental entity is the land parcel and the field that has its certain coordinates and borders and all remote sensing data is referred to the field.
That’s why many agriculture applications start from the map of crop fields and many of them have such a map implemented as a core feature of the product.
The only question is how to place all fields on the map?
Let’s do some napkin math here given the pilot area in Belgorod region (Russia). (We took it as an example as Russia has quite large cropland parcels that are clearly visible in Sentinel imagery)
This area of 2 422 sq. km has:
- approximately 4,500 polygons of crop fields;
- the average polygon has about 100 vertices;
Handmade mapping from scratch would take by our estimates: 4,500 (features) 100 (vertexes) / 350 (vertexes/hour) = 1,285 work hours or 160 working days of the human cartographer
But today we can delegate some part of the routine mapping work to artificial intelligence (AI) — to be more focused on the implementation phase and the application of the product to the end user needs.
Let’s use the same pilot area:
- AI-mapping pipeline processes a single image of this area in ~ 30 min;
- usually several images are required to cover all fields in the area (to avoid clouds, shadows, etc…). We used six images which took three hours of processing time for the whole region.
While AI overcomes human cartographers many times by speed performance, it makes errors due to instability in some cases, like cloudy areas, shadows from clouds, different seasons and fields patterns , etc.
So what if we could combine the speed of AI and a human accuracy?
To be more specific, let’s discuss two potential use cases, where the automatization of the mapping of crop fields will be greatly helpful, and propose a cartographer’s workflow for iterative processing and merging of the resulting field masks.
Case 1: Count the number and the area size of all cultivated fields in the territory
If you are a bit experienced in free and popular QGIS (qgis.org) — here you get started with Sentinel-2 and field masks using our plugin Mapflow-QGIS. The plugin is powered by Mapflow API and all you need to start working is to create an account and get a token to login.
If you get lucky to find the cloudless images that cover your area — it will take about 5 minutes to process the area of 350 sq. km (as you see on the picture above) using a single Sentinel-2 image.
Voila! You’ve got the mask and the image in your QGIS layers.
Case 2: Inventory of all fields in the territory
To get a precise map of all the crop fields cultivated in the territory within a specific period of time (let’s say the vegetation season that requires updated images and masks) you have to do some preliminary work of the analysis of the Sentinel-2 images available.
Preliminary analysis should be done for two reasons:
- not to miss objects, that were cultivated at different times (see Fig. 4(a, b))
- to ensure a full coverage of the territory (in case of clouds, haze, snow etc. , see Fig. 4(c))
For this purpose we designed the special iterative AI-mapping workflow based on the composition of field masks extractions from several satellite images.
How it works given our sample territory in Russia:
- Six images to process,
- One cartographer*,
- iterative AI-mapping guideline for the cartographer
*Important — the cartographer was not familiar with this mapping workflow before.
In summary it took roughly three hours for the algorithm and two days for one cartographer to finalize the results (instead of 165 days)!
A sneak peek at the iterative AI-mapping workflow
The iterative mapping workflow is based on the following principles:
- Selection of the successful polygons produced by AI from multiple satellite images
- Minimizing the number of clicks for cartographer
This workflow could be picked up in hours by any cartographer and we are already developing a series of tutorials explaining how it works.
Watch this tutorial for a brief visual explanation: Iterative mapping workflow tutorial powered by AI
You are welcome to watch a replay of our webinar where we spoke about AI-mapping of cropland areas: Map with Mapflow. Agriculture maps using free Sentinel imagery.
There is also one important thing to be taken into account when we speak about the effectiveness of the mapping of objects in satellite imagery — you need a handy tool for searching and processing images in one bottle.
And that’s why we are pleased to announce our special purpose tool that can be used by every cartographer for free.
- The new model of Sentinel-2 fields-mapping is successfully implemented into Mapflow and available for all users of the Mapflow-QGIS plugin. You can try it along with the high resolution model that we released before
- Mapflow-QGIS 1.6 is been released 🎉🎉🎉 — the main new feature is implementation of Catalog & Processing of Sentinel imagery.
(Sentinel search is powered by SkyWatch API 🙏— cool service and imagery provider, which we will tell much more about next time)
- We’ve described the benchmark of an experimental agriculture territory showing that AI-mapping can speed up the whole process 80 times
- We are looking for brave cartographers and developers who are ready to try iterative AI-mapping workflow — look at the guide and if you want to get more materials or suggest some edits, don’t hesitate to contact us
- Don’t forget that apart from this service Mapflow provides Hi-res imagery model for field and road masks extraction that can be useful for your overall agriculture mapping project — check related materials
More from GeoAlert
- Run AI-Mapping in QGIS over high-resolution satellite imagery
- Mapflow.ai — New Buildings Model and Kepler.gl Implementation