AI-Powered Diagnosis of Pomegranate Diseases in Maharashtra: A Comprehensive Review of Machine and Deep Learning Techniques

View at publisher Summarise with VIRAT
Authors: Seema Murkar, Dr Manoj Varshney
Cited by: 0
References: 56

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Agriculture plays a vital role in India’s economy, with Maharashtra being a key contributor to the cultivation of pomegranates, a high-value crop. However, pomegranate yields are frequently impacted by diseases such as bacterial blight and fungal infections, which threaten farmers’ livelihoods and the state’s agricultural output. In this study, we examine the applications of deep learning techniques to predict pomegranate diseases accurately, enabling timely interventions. Leveraging insights from existing literature on crop disease prediction and artificial intelligence (AI) applications in agriculture, this study highlights the implementation of convolutional neural networks (CNNs) and transfer learning techniques for precise disease detection. A The global analysis of analogous Artificial Intelligence applications reveals how these methods can boost agricultural output levels. Our methodology uses Maharashtra’s specific data sources while optimizing predictive models according to the distinct environmental characteristics throughout the state. The system aims to detect diseases before manual inspection thresholds by minimizing farmers’ dependence on hands-on evaluation to reduce product waste while maximizing resource potential. The findings of this study advocate for deploying AI-driven solutions as part of sustainable farming practices.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Water Quality Monitoring Technologies

Publication details

Journal / source
Biennial International Conference on Nascent Technologies in Engineering (ICNTE)
Pages
1–6
Publication date
16 January 2026
Language
EN