Abstract
Soybean is an important oilseed crop, rich in protein and oil, often referred to as a ``cash crop'' or ``gold bean'' by Indian farmers. In Maharashtra, soybean cultivation spans over approximately 3.8 million hectares, producing 3.07 million tons, placing the state second in India for overall soybean production. However, despite of its significance, several issues such as weeds, diseases, and pests hamper the overall productivity of soybean. Addressing these challenges faced by soybean growers it is essential to enhance yield and improve the crop's overall potential Currently, the farming sector is transitioning towards Agriculture 5.0, also known as digital farming. This approach utilizes data-driven technologies, such as artificial intelligence and computer vision, to transform the agriculture sector. These technologies enable the automation of several farming tasks. To develop accurate and robust machine learning/deep learning models high quality datasets are needed. With this aim, we have created a comprehensive dataset of soybean crop images affected by diseases and pest attacks from original fields of Maharashtra region located in India. Data acquisition was conducted across two seasons through aerial as well as ground-based approaches. The dataset is enriched with 4 types of diseases and 1 pest attack. The proposed dataset will serve as a valuable resource for training and testing machine learning and deep learning models ,enabling accurate detection and classification of diseases and pests attack damage.