For human livelihood, agriculture is an extremely important sector in Indian Agronomy. Environmental toxic farm impact affects all fields, making it difficult to manage numerous challenging situations. In order to get benefited of a crop for farmers and end user’s point of view, agriculture must adapt different technologies according to the day to day life environmental changes. Early identification of crop diseases will help farmers instead of entering into dangerous life threatening situations. For finding crop diseases along with close observation of a farmer, computer technologies will help a lot to maintain sustainable and healthy crop. Among several computing technologies, Deep Learning techniques create a major impact. In this paper we review various existing methods including machine learning, deep learning and AI for precision agriculture. The research insights provide understanding of state-of-the-art techniques, their limitations and the research gaps for further investigation towards precision agriculture.

Agriculture is an important sector of Indian agronomy for human livelihood. All areas are affected by the effects of environmental toxic farms, which makes managing various difficult situations more challenging. Agriculture must adopt new technology in accordance with daily environmental changes if it is going to benefit from a crop from the perspectives of farmers and end users. Farmers will benefit from early detection of agricultural diseases rather than risking their lives in dangerous circumstances. Computer technology will be very helpful in maintaining sustainable and healthy crops for the objective of identifying crop diseases in addition to the farmer's close observation. Deep learning (DL) techniques are very influential among various computing technologies. In this work, we explore several current approaches to precision agriculture, such as artificial intelligence (AI), DL, and machine learning (ML). The findings of the study make clear modern methods, their drawbacks, and the knowledge lacking that needs to be addressed to explore precision agriculture fully.