Event-Driven Smart Agriculture Monitoring using AWS Cloud Services

Kanukula, Vivekananda (2025) Event-Driven Smart Agriculture Monitoring using AWS Cloud Services. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Ineffective irrigation methods typically reduce agricultural productivity, leading to water waste and crop stress. According to this study, an event-based smart agricultural monitoring platform that uses machine learning and the cloud platform of Amazon Web Services (AWS) to predict irrigation needs in real time should be developed. The simulated data from IoT sensors—temperature, humidity, soil moisture, and rainfall—is ingested by an AWS IoT core and processed by AWS Lambda. An accurate Random Forest Classifier that predicts when irrigation should be turned on is trained and deployed using Amazon SageMaker. The system uses SNS to detect users, DynamoDB to store the records, and S3 to archive the data. A Streamlit dashboard running on EC2 displays sensor readings and prediction results in real time. Despite the model’s high accuracy on a test dataset, more testing using real-world data is suggested to be required. This cloud, IoT, and AI-based technology will enhance agricultural decision-making, increase the sustainability of farming methods, and optimize irrigation. The Random Forest Classifier was successful with 94.6 accuracy, 93.8 precision, 95.2 recall, and 94.5 F1-score on the test dataset and made it possible to predict irrigation in time.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Cortes Mendoza, Jorge Mario UNSPECIFIED
Uncontrolled Keywords:	Smart Agriculture; IoT; AWS; Machine Learning; Irrigation Prediction; Cloud Computing
Subjects:	H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > T Technology (General) > Information Technology > Cloud computing T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 14:23
Last Modified:	26 Mar 2026 14:23
URI:	https://norma.ncirl.ie/id/eprint/9226

Actions (login required)

View Item