Agriculture is a vital sector that supports human survival, yet it is increasingly challenged by factors such as climate variability, water scarcity, soil degradation, and crop diseases. In many situations, farmers rely on conventional practices and personal experience for decision-making, which may not always produce accurate outcomes. Therefore, there is a growing need for a more advanced and dependable system to assist farmers in monitoring crops and improving productivity. This paper presents a smart agricultural system that utilizes Machine Learning and Deep Learning techniques. The proposed system focuses on collecting real-time data from agricultural fields, including soil moisture, temperature, humidity, and weather conditions using sensor devices. The collected data is analyze to assess crop health and field conditions effectively. Machine Learning algorithms are applied to generate recommendations for irrigation management, crop selection, and yield prediction. Furthermore, Deep Learning models are employed for plant disease detection through image analysis of crop leaves. This approach enables early identification of diseases, helping to reduce crop damage and improve overall yield. The system also supports automated irrigation by supplying water only when required, thereby conserving resources and enhancing efficiency. Experimental evaluation indicates that integrating Machine Learning and Deep Learning improves prediction accuracy and system performance compared to traditional farming methods. This work demonstrates the importance of intelligent agricultural systems in enabling efficient, precise, and sustainable farming practices.
kumar et al. (Sun,) studied this question.