Machine learning techniques on agro meteorological parameters to predict the crop yield in support of building decision support system to farmer's community

Over the years, farmer grievances have been rapidly increasing due the barrage of issues that they face on a regular basis. This includes not getting good harvests, shortage of resources, etc. Decision making is an important aspect of farming, as it can improve results tremendously, hence helping fa...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2020-12, Vol.1706 (1), p.12143
Main Authors: Sowmya, B J, Seema, S, Monteiro, Daniel, Hossain, Zaid, Paymaster, Zubin, Tomar, Aditya
Format: Article
Language:English
Subjects:
Agro meteorological
Algorithms
Classification
Crop yield
Decision making
Decision Support
Decision support systems
Decision tree
Farmers
Humidity
Machine learning
Manhattan distance
Mathematical models
Meteorological parameters
Physics
Rainfall
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Over the years, farmer grievances have been rapidly increasing due the barrage of issues that they face on a regular basis. This includes not getting good harvests, shortage of resources, etc. Decision making is an important aspect of farming, as it can improve results tremendously, hence helping farmers. With the rise in technology, and great research in the realm of Data Science, there is an increasing demand for technical solutions for farmers. To solve this, we built a Decision Support System that predicts a crop to be grown based on agrometeorological factors such as rainfall, temperature, and humidity. The system was built using various machine learning algorithms. We compared multiple models, change algorithmic parameters, and decide the best model to be used. This system aims to aid the decision-making process of a farmer, and hence help them gain maximum yield with the knowledge and resources available.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1706/1/012143