Page 27 - Emerging Trends and Innovations in Web-Based Applications and Technologies

International Journal of Trend in Scientific Research and Development (IJTSRD)
Special Issue on Emerging Trends and Innovations in Web-Based Applications and Technologies
Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470

Machine Learning-Based Crop Recommendation System
Using K-Means Clustering for Precision Agriculture

2
3
Yash Kushwaha , Damini Thakare , Prof. Anupam Chaube
1
1,2 BCA, Department of Science and Technology,
3 Department of Science and Technology,
1, 2, 3 G H Raisoni College of Engineering and Management, Nagpur, Maharashtra, India

ABSTRACT pH, and soil type to offer real-time recommendations to
Utilizing Machine Learning and Clustering Techniques for farmers. The goal of implementing this model is to improve
Crop Recommendation Food security worldwide heavily agricultural decision-making, boost crop yields, and
depends on agriculture; however, farmers often face encourage sustainable farming practices. While this study
challenges in selecting the most appropriate crops for their primarily focuses on the Indian agricultural sector, it has the
fields due to diverse soil characteristics, weather potential for application in other regions with similar
conditions, and precipitation levels. This research environmental conditions. The system is designed to be user-
introduces a Crop Recommendation System based on friendly, enabling individuals to input their regional
Machine Learning, employing K-Means Clustering, an characteristics and receive dynamic crop recommendations,
unsupervised learning method, to categorize areas thereby making farming more efficient and data-driven.
according to temperature, rainfall, soil pH, and soil type.
The system analyzed historical farming data to group Literature Review
similar regions and propose ideal crops for cultivation. The Paper 1:- Summary of Notable Research Crop
Recommendation System (Ruchirawya et al., 2020) Employs
model was developed using a dataset comprising soil and
machine learning techniques to suggest suitable crops by
climate information from various geographic locations.
considering environmental conditions such as temperature,
Users can access a web-based interface to input their local
humidity, pH, and rainfall, to provide user-friendly decision
parameters and receive dynamic predictions for optimal
support.
crops. The findings demonstrated that clustering offers a
robust solution for precision farming, enabling data-driven Paper 2:- Risk-Averse Stochastic Optimization
crop selection. This system is designed to assist farmers in (Akhavizadegan et al., 2022) Creates optimization
making well-informed decisions, potentially leading to frameworks that account for uncertainty, combining crop
enhanced agricultural output and long-term sustainability. models with Bayesian algorithms to improve farm

management strategies.
KEYWORDS: Machine Learning, Crop Recommendation, K-
Means Clustering, Precision Agriculture, Soil Analysis Paper 3:- Nutrient Application Timeline (Ikhlaq & Kechadi,
2023) Introduces a predictive model for scheduling fertilizer
applications using extensive datasets, focusing on the
INTRODUCTION importance of timely nutrient management.
Agriculture is crucial for global food security and economic
stability, but farmers struggle to select the best crops based Paper 4:- Pre-Clustering Point Clouds (Nelson &
on environmental and soil conditions. Traditional methods of Papanikolopoulos) Presents algorithms for dividing crop
crop selection often rely on personal experience or expert fields into segments, enhancing the scalability of agricultural
advice, which may not always yield optimal results. Factors robotics and machine learning applications.
such as soil composition, pH levels, temperature, and rainfall
significantly affect crop productivity. Selecting an Paper 5:- E-commerce Analysis (Hua Tian) Examines
inappropriate crop can lead to reduced yields, financial consumer behaviour in rural e-commerce settings, which is
setbacks, and inefficient use of resources. Machine learning relevant for comprehending market dynamics in agricultural
has recently emerged as a powerful tool for tackling complex product sales.
agricultural challenges by analyzing large datasets, Paper 6:- OCA for E-Commerce Recommendations (Gulzar et
identifying patterns, and providing data-driven al.) Offers a clustering approach to tackle cold-start
recommendations. Unlike conventional farming approaches, problems, applicable to addressing data scarcity issues in
machine learning techniques can process vast amounts of crop recommendations.
information and generate accurate predictions, thus
minimizing uncertainties in crop selection. By leveraging Paper 7:- Machine Learning-Based Crop Recommendation
(Kaur et al.) Investigates various ML algorithms (SVM,
these capabilities, farmers can make more informed
decisions that increase productivity and promote sustainable decision trees) for precise crop recommendations,
practices. This research aims to develop a machine learning- underscoring the potential of ML in agriculture.
based crop recommendation system using K-Means Findings:- Multiple algorithms are utilized to examine
Clustering, an unsupervised learning algorithm, to classify environmental conditions for crop recommendations. Data
regions based on their environmental conditions and suggest Utilization: Focus on extensive datasets encompassing soil
the most suitable crops. The system will consider key and climate information; integration of real-time data is
agricultural parameters such as temperature, rainfall, soil essential. Optimization Under Uncertainty: Acknowledges

IJTSRD | Special Issue on Emerging Trends and Innovations in Web-Based Applications and Technologies Page 17