An Intelligent Serverless AI pipeline for infrastructure creation based on Agricultural sensory IoT data

Chavan, Vedant Rajendra (2025) An Intelligent Serverless AI pipeline for infrastructure creation based on Agricultural sensory IoT data. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (891kB) | Preview

Abstract

The rapid growth of efficiencies of cloud computing and Internet of Things(IOT) has given evolution to the agriculture sector, which leads to the use of precision farming system. This project presents a serverless IoT-based architecture system integrated with machine learning (ML) to enhance real-time agriculture monitoring, prediction, and resource optimization. The system utilizes AWS IoT Core, Lambda, DynamoDB, and ML model in order to create an entirely automated, scalable, and cost-efficient pipeline based on the analysis of heterogeneous sensor data pertaining to soil, crops, and environmental conditions.

The sensor network of the IoT has eight major parameters involved in agriculture, including soil moisture, temperature, pH, nutrients, crop health, soil health, plant stress, and growth that the system records and transmits via AWS IoT core to process the data. The implementation deploys the AWS serverless infrastructure, which results in automatic ingestion, feature engineering, feature training as well as inference, without having to maintain continuous server support, resulting in cost-effectiveness and scalability. The effectiveness of intelligent, cloud-native IoT pipelines as a sustainable means to improve the current state of agriculture is proven in the experiments showing a 30% improvement in the resource utilization and 15% accuracy in the prediction of crop yield. The project will make a contribution to a modular and scalable infrastructure of integrating real-time IoT sensing and machine learning in precision farming systems, which has been aligned with the global efforts on smart and sustainable agriculture.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Heeney, Sean UNSPECIFIED
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:	31 Aug 2026 12:30
Last Modified:	31 Aug 2026 12:30
URI:	https://norma.ncirl.ie/id/eprint/9693

Actions (login required)

View Item