Sustainable Plant Pathogen Detection: Balancing Accuracy and Energy Efficiency in Deep Learning Models

Bediskar, Aishwarya Satish (2024) Sustainable Plant Pathogen Detection: Balancing Accuracy and Energy Efficiency in Deep Learning Models. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (4MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

In the realm of sustainable agriculture, accurate and energy-efficient plant pathogen detection is crucial for crop health, environmental sustainability, and economic viability. This study investigates sophisticated machine learning methods for the identification of plant pathogens from images, with a particular emphasis on deep learning models such as DenseNet121, VGG19, and Convolutional Neural Networks (CNN). In order to maintain environmental sustainability, I built and assessed these models to determine their accuracy in diagnosing plant illnesses as well as their carbon footprint. A dataset consisting of 2,025 photos that were classified as bacteria, viruses, fungus, healthy, and pests was used in the study. According to the results, DenseNet121 performs better than CNN and VGG19, obtaining the maximum accuracy of 98% with the least amount of loss (0.068). DenseNet121 is the most ecologically friendly model as it also shows the lowest carbon emissions. DenseNet121 has a rather low carbon emission of 0.0003 kg CO2 per epoch, proving the efficiency of the model for large-scale applications in precision agriculture. The results depicted DenseNet121 as the most reliable and greenest among the models studied.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Jain, Mayank UNSPECIFIED
Uncontrolled Keywords:	Plant Pathogen Detection; Deep Learning; Energy Efficiency; Carbon Footprint; Sustainability
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Agriculture Industry G Geography. Anthropology. Recreation > GE Environmental Sciences > Environment Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Artificial Intelligence
Depositing User:	Ciara O'Brien
Date Deposited:	17 Jun 2025 18:38
Last Modified:	17 Jun 2025 18:38
URI:	https://norma.ncirl.ie/id/eprint/7899

Actions (login required)

View Item