About the Client
Cloud-Based Precision Agriculture Platform Service aided by satellite data which provides you with intelligent analytical decision-support tools to easily monitor, understand and optimize field yield and crop performance.
Our client wants to help individual farmers and agriculture organizations those interested in measuring the performance of the agricultural growth at the field level.
In modern agriculture, there is a growing demand for increased land productivity while lowering input costs.
Farmers need to continuously obtain, reliable and cost-effective information in order to maximize crop yields.
Our client wants to use satellite and drones data to get different indexes like NDVI to analyze field status.
Quantum developed a cloud-based platform that provides farmers the ability to analyze different indexes about their fields and increase productivity.
The platform solves everyday problems for the agriculture area.
It analyzes satellite data in a smart way.
The solution gets satellite information suitable for a broad variety of crops, which also provides with comprehensive coverage of the agricultural areas.
For example, it could process anomaly situations like nebulosity and overcast.
Information on crops and field performance is updated every 3-5 days on average, depending on their location.
Quantum has created a service hosted at Amazon EC2, that automatically finds newest datasets captured by Landsat Sentinel satellite, cuts out areas of interest to us, calculates the vegetative index (NDVI) and creates raster from this data.
We created a web application that displays the statistics we have already collected. So our client gets all needed information on top of Google Maps, with analytics platform and geospatial measurement tools.
Also, we added the ability to connect statistical data from Google Earth Engine, in addition to our service for more statistical data.
Development of a standalone windows application with Python, GDAL, and PyQt was challenging, because of the complexity of connection all needed libraries altogether.
As a result, this desktop application cuts tiles from datasets by coordinates of the customer fields borders, then color these tiles by the NDVI color mapping and then uploads them to the Amazon S3.
The back-end part was developed using Python.
As the database, we have chosen PostgreSQL.
For data computing, we used AWS Lambda and deploy our service with AWS.
The system works using GDAL, a translator library for raster and vector geospatial data formats, and is deployed on the AWS infrastructure.