Year: 2024
Type: article
Abstract: Small-scale farmers face challenges such as plant diseases, pest infestations, soil fertility issues, water mismanagement, and unpredictable weather, which reduce crop yields and profitability, especially in remote areas with limited access to expertise. To address this, we propose an online platform connecting farmers with agricultural experts like agronomists and entomologists, fostering knowledge exchange to tackle these issues and promote sustainable farming. Leveraging deep learning, our study classifies soil textures using Convolutional Neural Networks (CNNs) to analyze soil images, employing techniques like image augmentation to improve datasets and exploring models such as Baseline, Augment, Dropout, and Padding. This AI-powered approach, integrated into our platform alongside a farmer discussion forum, empowers farmers with actionable insights, enhancing crop yields, conserving resources, and advancing food security and economic growth. AgroSense AI merges traditional agricultural wisdom with cutting-edge technology, offering tools and a collaborative community to drive a sustainable future in farming. Keywords : AI powered , Convolutional Neural Networks, Deep Learning , Padding, Plant disease prediction, Soil texture classification
DOI: 10.55041/ijsrem40112
Language: English
Topic: Smart Agriculture and AI
Subfield: Plant Science
Domain: Life Sciences
SDGs: Zero hunger, Life on land
Open Access status: bronze
OpenAlex ID: W4405740035