Using Machine Learning and RGB Images to Assess Nitrogen and Potassium Status in Sorghum (Sorghum bicolor L.) Under Field Conditions
Authors:
- Guilherme Augusto MartinsGMGuilherme Augusto Martins
- Murilo Mesquita BaessoMBMurilo Mesquita Baesso
- Fernanda de Fátima da Silva DevechioFDFernanda de Fátima da Silva Devechio
- Adriano Rogério Bruno TechATAdriano Rogério Bruno Tech
- Jamile Raquel RegazzoJRJamile Raquel Regazzo
- Carlos Eduardo Nunes RicciCRCarlos Eduardo Nunes Ricci
- Murilo de Lima LeãoMLMurilo de Lima Leão
Open Access
- 3 November 2025
- journal article
- research article
- Published by MDPI AG in Agriengineering
- Vol. 7 (11) , 367
Abstract
Sorghum (Sorghum bicolor L.) is a resilient crop with high relevance in tropical and semi-arid regions, where nutritional deficiencies, particularly of nitrogen (N) and potassium (K), limit yield. This study evaluated the potential of RGB imagery combined with machine learning to detect N and K deficiencies in sorghum at different phenological stages. The traditional models showed significant limitations in distinguishing nutritional status, especially at the early V4 stage, where accuracies remained below 40%. At the flowering stage, their performance improved for nitrogen detection, reaching up to 58% accuracy, but remained insufficient for potassium (below 30%). In stark contrast, the CNN demonstrated substantially superior performance, effectively identifying even subtle visual symptoms. For nitrogen deficiency, the CNN achieved high accuracies of 76% at the V4 stage and 87% at flowering. While potassium classification proved more challenging overall, the CNN still outperformed traditional models, reaching 55% accuracy at flowering. These results indicate that deep learning is a powerful and viable low-cost tool for the early and accurate diagnosis of nutrient deficiencies in sorghum, overcoming the limitations of conventional machine learning approaches.Keywords
Funding Information
- Luiz de Queiroz Agricultural Studies Foundation
This publication has 14 references indexed in Scilit:
- Enhanced Neural Network for Rapid Identification of Crop Water and Nitrogen Content Using Multispectral ImagingAgronomy, 2023
- Improving Nitrogen Status Diagnosis and Recommendation of Maize Using UAV Remote Sensing DataAgronomy, 2023
- Machine learning and handcrafted image processing methods for classifying common weeds in corn fieldSmart Agricultural Technology, 2023
- Prediction of Strawberry Leaf Color Using RGB Mean Values Based on Soil Physicochemical Parameters Using Machine Learning ModelsAgronomy, 2022
- Support Vector Machine in Precision Agriculture: A reviewComputers and Electronics in Agriculture, 2021
- Molecular and phenotypic characterization of a collection of white grain sorghum [Sorghum bicolor (L.) Moench] for temperate climatesGenetic Resources and Crop Evolution, 2021
- Detection of nutrition deficiencies in plants using proximal images and machine learning: A reviewComputers and Electronics in Agriculture, 2019
- Classification of images of wheat, ryegrass and brome grass species at early growth stages using principal component analysisPlant Methods, 2011
- A systematic analysis of performance measures for classification tasksInformation Processing & Management, 2009
- A HYPOTHESIS RELATING CRITICAL POTASSIUM CONCENTRATIONS FOR GROWTH TO THE DISTRIBUTION AND FUNCTIONS OF THIS ION IN THE PLANT CELLNew Phytologist, 1984