Drone Data and Environmental Sensor Read-out to Automate Plant Health Prediction and Drought Control

In this high-impact 8-week challenge, join a global team of 50 AI engineers to build an automated plant health prediction model, based on drone-derived multispectral and thermal data.

Brain Pool Tech is a technology integration company developing expert and machine learning solutions in the areas of resilience and sustainability. They believe that smart solutions plus smart users result in improved and faster decision-making.

The Problem

With emerging concepts in remote sensing and machine learning, Brain Pool Tech provides software-as-a-service that integrates drone (and satellite) derived high-resolution geographical information, environmental sensor data (e.g. weather information), as well as inputs from users through mobile applications. A proof of concept project is currently executed in Australia generating unique data related to drought control and plant health and is set out to create a minimum viable product. 

Multispectral drone data, as well as weather and irrigation information in an agronomic setting, are used to create predictive models to save and optimize water consumption as well as to reduce the use of herbicides/pesticides. This will have wide implications in the fields of agronomics, agriculture, and forestry. 

The Project Goals

• Build an automated plant health prediction model, using drone-derived multispectral and thermal data combined with weather and irrigation data. With these sources nitrogen, chlorophyll, moisture, and evapotranspiration levels can be approximated. These data sets can then be used to train a model to detect water stress, pest infestation, and man-made plant stress.  These algorithms will be built on approximately 10-20 data sets that Brain Pool Tech has acquired in the area of interest. 
• The model should allow user inputs, e.g. labels for new areas to retrain the algorithm. 
• Integration of the model via API into the Brain Pool Tech software ecosystem. 

Why join? The uniqueness of Omdena AI Challenges

A collaborative experience you never had in your working life! For the next eight weeks, you will not only build AI solutions to make a real-world impact but also go through an entire data science project lifecycle. This covers problem scoping, data collection, and preparation, as well as modeling for deployment.

And the best part is that you will join a global and collaborative team of changemakers. Omdena AI Challenges are not a competition or hackathon but a real-world project that will take your experience of what is possible through collaboration to a new level.

Find more information on how an Omdena project works