Preserving Solanaceae Crops: Strategies for Detecting and Controlling Diseases

Abstract

Solanaceae vegetables, a vital group of crops including tomatoes, potatoes, peppers, and eggplants, play a significant role in global agriculture and culinary traditions. These crops are essential for our diets and contribute substantially to the economy. However, these plants are prone to numerous ailments, specifically leaf-related diseases, which have the potential to significantly impact the overall well-being and yield of the crops. Detecting and managing these diseases are crucial for ensuring food security and economic stability. In recent years, advanced techniques have been developed to tackle the issue. Machine learning (ML), a subset of artificial intelligence, has revolutionized the field of disease detection. It involves training algorithms to identify disease patterns in images of plant leaves, enabling rapid and accurate diagnosis. Various studies have demonstrated the effectiveness of ML in classifying tomato leaf diseases with high accuracy. Deep learning (DL), a subset of ML, utilizes neural networks to analyze large datasets, thereby improving the precision and efficiency of disease detection. Several DL models have been applied to detect tomato leaf diseases, offering precise and efficient solutions. Hybrid models, which combine traditional ML with DL techniques, have shown promise in improving disease identification and classification. In this study, we delve into a comprehensive exploration of time-honored methods employed for the identification of plant diseases, with a particular focus on leaves, as they serve as critical indicators of a plant's well-being. An in-depth analysis of various conventional techniques is conducted, shedding light on their inherent limitations. These advanced techniques in disease detection offer valuable tools for farmers and researchers, contributing to agricultural sustainability, crop protection, and food security.

Abstract from the paper’s OpenAlex record, shown for indexing and research. Copyright remains with the authors or the publisher. Read at the source ↗

The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.