Back to search

CSUniversity San Bernardino

CLASSIFICATION MODEL FOR DISCOVERING THE TYPE OF CROP TO PLANT USING ENSEMBLE TECHNIQUES

Abstract

dc:description.abstract

Farming plays a role in ensuring survival, especially with the growing need for increased agricultural output. It is vital for farmers to efficiently choose the crops to cultivate. By using crop recommendation systems farmers can make decisions on what crops to plant leading to yields and improved resource management. The success of crop production depends on maintaining the balance of soil nutrients and favorable weather conditions. In this research project, we created a crop recommendation system utilizing learning methods to predict the appropriate crops based on essential soil nutrients and weather patterns. We worked with a dataset sourced from Kaggle, which included 2,200 entries featuring elements like Nitrogen, Phosphorus, Potassium, Temperature, Humidity, pH levels, and Rainfall data in CSV format. We compared two techniques: bagging and boosting. For bagging, we utilized base estimators such as Decision Tree, Random Forest, and Support Vector Classifier (SVC). Our analysis revealed that the Random Forest classifier attained an accuracy rate of 99% after optimizing parameters, emerging as the effective model for our dataset. Additionally, the boosting approach using the Gradient Boosting classifier also performed well, with an accuracy rate of 98%. These findings underscore how ensemble methods can significantly improve accuracy in crop recommendation systems. The bagging model based on Random Forest showed effectiveness in this scenario, providing insights for making decisions in agriculture.

Degree

thesis:*
Name thesis:degree_name
Master of Science in Computer Science
Level thesis:degree_level
Project
Discipline thesis:degree_discipline
School of Computer Science and Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Addanki, Uma Mahesh
Contributors dc:contributor
  • Dr BILAL KHAN

Subjects

dc:subject × 7

Identifiers

dc:identifier.*
Repository record dc:identifier
https://scholarworks.lib.csusb.edu/etd/2012

Chain of custody

source
Harvested from
CSUniversity San Bernardino
Base URL
scholarworks.lib.csusb.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Addanki, Uma Mahesh. CLASSIFICATION MODEL FOR DISCOVERING THE TYPE OF CROP TO PLANT USING ENSEMBLE TECHNIQUES. Project thesis, https://scholarworks.lib.csusb.edu/etd/2012