Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the pojo-accessibility domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/doctoral/public_html/wp-includes/functions.php on line 6121
ICDSUPL4-T003 – University of Life Sciences in Lublin

ICDSUPL4-T003

Volume: 4, 2025
4th International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland:
ENVIRONMENT – PLANT – ANIMAL – PRODUCT

Abstract number: T003

DOI: https://doi.org/10.24326/ICDSUPL4.T003

Published online: 9 April 2025

ICDSUPL, 4, T003 (2025)


Machine learning in rice disease detection

Maria Kamińska1*

1 Department of Computer Science, Faculty of Electrical Engineering and Computer Science, Lublin University of Technology, Nadbystrzycka 38A, 20-618 Lublin, Poland

* Corresponding author: mkaminska26@gmail.com

Abstract

Rice is a staple food for billions of people worldwide. However, it is highly vulnerable to various diseases, which can significantly reduce its yield. These losses not only have economic consequences but also pose a serious threat to food security. The problem is particularly significant in regions where rice is the primary food source, and even small declines in production can lead to food shortages and price increases. Controlling diseases in large-scale cultivation is extremely difficult, especially once an infection has spread. Therefore, monitoring plantation health and early detection of disease symptoms play a crucial role. This not only helps limit losses but also reduces pesticide use, which has a positive impact on both the environment and crop quality. In recent years, artificial intelligence has been increasingly used in agriculture, as it allows for the automation of many processes that previously required significant labor and specialized knowledge. Algorithms that learn from large datasets can accurately recognize disease patterns, even under difficult lighting conditions. This allows farmers to make faster decisions regarding crop protection, leading to increased production efficiency and reduced losses. The dynamic development of artificial intelligence has prompted many researchers to develop models capable of recognizing the most common rice diseases. Advanced models can analyze plant images and detect the first signs of infection faster and more easily than a human could. The purpose of this overview was to compare selected research in the field, analyzing and summarizing the results in terms of classification performance, methods used, and recognized diseases. The review was created using scientific sources from the following databases: PubMed, Springer, EBSCOhost, and ScienceDirect. The analyzed studies show that modern machine learning-based systems can effectively support farmers in identifying threats and making decisions, which is an important step towards sustainable and more efficient agriculture.

Keywords: rice disease, image analysis, artificial intelligence, machine learning


How to cite

M. Kamińska, 2025. Machine learning in rice disease detection. In: 4th International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland: Environment – Plant – Animal – Product. https://doi.org/10.24326/ICDSUPL4.T003

Skip to content