Industries
Agriculture
Increase revenue by building intelligent AI-based solutions to track crops, carbon sequestration and trading trends
.jpg)
Challenges
Agriculture currently has a limited use of satellite imagery, but it’s one of the industries which can potentially get the most out of it. This is slowed down by several factors that remain to be solved in order to really maximize the benefit from satellite imagery:
Cloud coverage
Most of the large agricultural areas have between 45% and 80% cloud coverage, meaning that at least half of the time, there are clouds above it. This makes the use of low-revisit optical satellites quite unreliable to monitor crops.
Multiple sources of data
Between drones, weather reports, IoT sensors, tractors and satellite imagery, it is hard to get one unified insight. The different scales, formats are complex to merge and thus limit the information potential.
Limited machine learning models
Due to the factor above and the lack of extensive ground data, it remains today difficult to build machine learning models that are sufficiently robust to handle most scenarios in Agriculture.
Create advanced agricultural solutions quickly
SpaceSense enables you to quickly build actionable agricultural products based on satellite imagery and AI. Through our toolbox, we lift current limitations and empower your data science team to have more impact in a reduced time.
Access analysis ready sources
Use our always increasing library our data sources to build the perfect dataset.
Scale the analysis
Unlock continent-scale insights effortlessly with our scalability capabilities.
Fuse data sources
Built complex multi-sources datasets thanks to our data fusion module.
Get existing model architectures
Save time and effort by testing our specifically designed model architectures.
CASE STUDY
Monitoring more accurately using AI
Problematic
The carbon credit market is growing everywhere in the world and represents a tremendous opportunity for growers to generate more revenue while actively contributing to climate change mitigation. But that means making sure that the credit sold has really been stored in the ground. An Ag company approached us to help them create tools that would allow them to track some field information and have an independent assessment of their grower’s reports.
Solution
They used our data fusion module to create a dataset of hundreds of fields composed of Sentinel 1 & 2 data, crop type and significant event dates (like harvest and tilling). This dataset was then used to build several models, to be able to detect the main crop types present on fields, the rotation of these crops, and when a harvest or tilling happens.
Result
As a result, they were able to deploy a first full prototype of a carbon credit solution with their growers in a matter of weeks instead of months. It also allowed them to avoid outsourcing the project, since they didn’t have in-house skills to work with SAR data with, a problem that SpaceSense solves.
.jpg)
Save up to 70% development time and get access to complex data simply.
Additional agriculture use cases
.jpg)
Title use case 01
They used our data fusion module to create a dataset of hundreds of fields composed of Sentinel 1 & 2 data, crop type and significant event dates (like harvest and tilling).
Title use case 01
They used our data fusion module to create a dataset of hundreds of fields composed of Sentinel 1 & 2 data, crop type and significant event dates (like harvest and tilling).
