Skip to content

amogh-sood/Croptimizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

UTA2024

TEAM: Lalith V., Ajay A., Amogh S., and Rohith T.

Inspiration

The inspiration for Croptimizer came from watching Clarkson’s Farm where a TV host, Jeremy Clarkson, decides to dip his toes in farming. Clarkson's Farm highlights the great challenges and complexities of modern farming, showing how unpredictable weather, rising costs, and the constant demands of society make it a tough and often underestimated profession. This is where I saw firsthand how challenging farming can be. With fewer farmers left and increasing pressures on their livelihoods, I realized that AI could play a role in making farming more efficient and less stressful.

What it does

Croptimizer is a web app that predicts crop yields by analyzing key agricultural data, such as rainfall, soil moisture, temperature, etc. By leveraging a neural network, it processes these inputs to give farmers accurate yield forecasts. The app helps optimize farming decisions, allowing farmers to adjust irrigation, fertilizer, and resource management based on real-time and historical data, improving efficiency and crop productivity.

How we built it

We developed Croptimizer by training a machine learning model based on a Neural Network, capable of processing a wide range of environmental and agricultural data to deliver accurate crop yield predictions. This provides farmers with valuable insights and foresight into their expected harvest. For the front end, we built a user-friendly web interface using HTML, CSS, and JavaScript, allowing farmers to easily input their data and receive real-time predictions in a seamless way.

Challenges we ran into

One of our biggest challenges was achieving high accuracy with the machine learning model. Initially, we experimented with a Random Forest algorithm, but it didn’t perform well due to the limited dataset we had for our original concept. Another hurdle was developing an intuitive user interface. Our primary focus was on delivering accurate predictions to farmers, so we prioritized functionality over design, ensuring they could access the data quickly without spending too much time navigating the website.

Accomplishments that we're proud of

We’re proud of successfully implementing a Neural Network to solve a real-world problem in agriculture. Despite the limitations of the data, we built a model that provides meaningful predictions and shows the potential of AI to support farmers in their work.

What we learned

Neural Networks are one of the best algorithms.

What's next for Croptimizer

Weather and Climate is the biggest risk of agriculture. We believe the next step for Croptimizer is to incorporate live and predicted weather patterns to suggest an optimal time for harvesting. This would expand the idea of helping make farmer's work efficient by saving significant time and decision-making to guarantee an optimal yield.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published