Maximize Agriculture Yield
Predictive Model to recommend most suitable crops to grow and then determine the outcome of the harvest season.
Created on February 27|Last edited on January 29
Comment
Motivation
Agriculture is a core piece of our lives. Farmers today face a huge challenge — feeding a growing global population with less available land. The world’s population is expected to grow to nearly 10 billion by 2050, increasing the global food demand by 50%. As this demand for food grows, land, water, and other resources will come under even more pressure. The variability inherent in farming, like changing weather conditions, and threats like weeds and pests also have consequential effects on a farmer’s ability to produce food. The only way to produce more food while using less resources is using Machine Learning to optimize the yield by forecasting the most suitable crop to grow and then predicting the outcome of the harvest season as well as applying CV to determine the crop health.
Use-Case
You are creating genetically engineered seeds to support farmers demand. You also have large farms across the country where you grow different fruits to supply across the country.
- Producing genetically engineered seeds is a very long supply chain cycle, so it's quite crucial to plan for the seed demand for different fruits across different geographical regions. So you have ML practitioners build models to recommend the best fruit to grow based to changing weather and soil condition.
- One of the biggest challenge is to manage crops with the changing conditions. It's quite crucial to make sure the right pesticide is used and administered regularly to avoid crops getting damaged. So you have another team of ML practitioners building models to predict if the crop would be healthy, damaged by pesticides or damaged by other reasons.
For ML practitioners, training models on parameters that are constantly changing can be highly iterative and experimental — it's useful to have interactive tools to visualize, track, and explore datasets and models.
For business leaders, the results impact customers/farmers personally — these same tools help ensure the end users are getting the best crop yield possible.
In this report, we'll show you how to make your models — and your customers — fit better with Weights & Biases.
Scope
Given the different components and the scale of the challenge, this is divided across different teams for each use-case and also for different steps
There is a separate team for Data Engineering that is responsible for data pre-processing and modeling for these use-cases.
Potential Customers:
- Monsanto
- Caterpillar
- Iron Ox
- Carbon Robotics
- AgroScout
- Fieldwork Robotics
& many more
Overview
Detailed View
References:
Add a comment