ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Automated Crop Nutrient Deficiency Detection Using Computer Vision and Multi-Sensor Data Analytics

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2026 ASABE Annual International Meeting  2601051.(doi:10.13031/aim.202601051)
Authors:   Karishma Kumari, Ali Mirzakhani Nafchi
Keywords:   Crop nutrition status, Resource optimization, Nutrient deficiencies, Plant morphology, Fertilizer application, Deep Learning and Artificial Intelligence

Abstract. Nutrient deficiencies have a substantial impact on crop yield, making the agricultural industry critical to food security and sustainability. Traditional nutrient evaluation methods are frequently labor-intensive, damaging, and ineffective for large-scale real-time monitoring. Recent improvements in sensing technologies, computer vision, and artificial intelligence have enabled non-destructive, high-throughput nutrient monitoring using RGB, multispectral, hyperspectral, UAV, and IoT-based systems. Machine Learning (ML) and Deep Learning (DL) models, such as CNNs and transformer-based techniques, are increasingly being utilized to evaluate picture and spectral data to diagnose nutrient deficiencies. This paper examines recent breakthroughs in machine learning and deep learning, analyzes their performance in greenhouse and field settings, and explores difficulties and future solutions for sustainable agricultural nutrient management, including multi-sensor fusion, temporal analysis, and explainable AI.

(Download PDF)    (Export to EndNotes)