Abstract
Grapes are indeed a vital crop for both the fruit and wine industries globally. They are cultivated in numerous regions around the world and contribute significantly to the economy and culinary culture of many countries. By prioritizing disease detection and implementing proactive management strategies, growers can effectively safeguard their grape crops, optimize yields, and sustain the productivity and profitability of the global fruit and wine industry. We present the "Grape Disease Dataset" consisting of 10,000 records of classified environmental parameters sensed by sensors classified into three categories, temperature, humidity, and leaf wetness. The dataset covers diseases such as powdery mildew, downy mildew, and bacterial leaf spot. Designed to meet the needs of researchers and practitioners who wish to develop machine learning algorithms for disease detection. Some of the most common diseases affecting grapes include fungal infections such as powdery mildew, downy mildew, bacterial leaf spot and bunch rot. These diseases can affect different parts of the grapevine, including leaves, shoots, and clusters, ultimately leading to reduced photosynthesis, defoliation, and loss of fruit quality. Additionally, bacterial diseases like Pierce's disease and viral diseases like grapevine leaf roll disease pose serious threats to grape cultivation. Managing these diseases requires a combination of preventive measures, cultural practices, and, in some cases, the use of fungicides, bactericides, or other chemical treatments. Additionally, advancements in disease-resistant grape varieties and sustainable farming practices are being explored to mitigate the impact of diseases on grape production. Overall, effective disease management strategies are crucial for maintaining the health and productivity of grapevines, ensuring a stable supply of grapes for both fresh consumption and wine making, and sustaining the global fruit and wine industry. In order to improve the accuracy and efficiency of automated grape disease identification systems, various machine learning techniques can be applied to the dataset, including feature extraction and pattern recognition.