Skip to content

A machine learning solution to predict the crop yield per acre of rice or wheat crops in India. The goal is to empower these farmers and break the cycle of poverty and malnutrition.

Notifications You must be signed in to change notification settings

rapsoj/crop-yield-estimate

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Digital Green Crop Yield Estimate Challenge

title card

Challenge Link

Variable Description Link

Smallholder farmers are crucial contributors to global food production, and in India often suffer most from poverty and malnutrition. These farmers face challenges such as limited access to modern agriculture, unpredictable weather, and resource constraints. To tackle this issue, Digital Green collected data via surveys, offering insights into farming practices, environmental conditions, and crop yields.

The objective of this challenge is to create a machine learning solution to predict the crop yield per acre of rice or wheat crops in India. Our goal is to empower these farmers and break the cycle of poverty and malnutrition.

A crop yield model could revolutionise Indian agriculture, and serve as a global model for smallholder farmers. Accurate yield predictions empower smallholder farmers to make informed planting and resource allocation decisions, reducing poverty and malnutrition and improving food security. As climate change intensifies, adaptive farming practices become crucial, making precise yield predictions even more valuable. Solutions developed here can drive sustainable agriculture and ensure a stable food supply for the world's growing population. This challenge offers data scientists and machine learning enthusiasts a unique chance to make a real difference in vulnerable populations' lives while advancing global food security in a concise, impactful way.

The data was collected through a survey conducted across multiple districts in India. It consists of a variety of factors that could potentially impact the yield of rice crops. These factors include things like the type and amount of fertilizers used, the quantity of seedlings planted, methods of preparing the land, different irrigation techniques employed, among other features. The dataset comprises more than 5000 data points, each having more than 40 features.

Organisations

  • Digital Green (a global development organization that empowers smallholder farmers to lift themselves out of poverty by harnessing the collective power of technology and grassroots-level partnerships)

  • Fair Forward AI (promotes a more open, inclusive, and sustainable approach to AI on an international level. FAIR Forward seeks to improve the foundations for AI innovation and policy in seven partner countries: Rwanda, Uganda, Ghana, South Africa, Kenya, Indonesia, and India. Together with their partners, they focus on three areas of action: (1) strengthen local technical know-how on AI, (2) increase access to open AI training data, (3) develop policy frameworks ready for AI)

Efficacy analysis of precision agriculture for development

  • Analysis
  • TLDR; program is estimated to cost $3.41 per farmer/year with a benefit-cost ratio (BCR) of 32:1

Team

  • Jessica Rapson (lead, geospatial analysis)
  • Shaw Brandon Chifamba (agricultural data)
  • Alice Ardis (model optimisation)
  • Juliette Zaccour (feature engineering)

About

A machine learning solution to predict the crop yield per acre of rice or wheat crops in India. The goal is to empower these farmers and break the cycle of poverty and malnutrition.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 3

  •  
  •  
  •