Key points are not available for this paper at this time.
Crop disease and soil health are critical factors influencing agricultural productivity and food security worldwide. Traditional methods for disease detection and soil analysis often involve time-consuming and labourintensive processes, leading to delays in response and management. Given the current trajectory of population growth, it is anticipated that by 2050, global crop productivity will need to double from its current levels. Pests and diseases are a major obstacle to achieving this productivity outcome. Hence, it's imperative to devise efficient methodologies for automatically detecting, identifying, and predicting pests and diseases in agricultural crops. Employing Machine Learning (ML) techniques can facilitate extracting insights and correlations from the data under analysis. This paper conducts an extensive review of the literature on machine learning techniques utilized in agricultural contexts, particularly emphasizing their application in tasks related to the classification, detection, and prediction of diseases and pests. The survey endeavours to advance smart farming and precision agriculture by advocating for the creation of methodologies that enable farmers to reduce reliance on pesticides and chemicals while simultaneously enhancing crop quality and productivity. AI models can accurately detect symptoms of diseases such as leaf discoloration, damaged area, and other visual different. the integration of IoT (Internet of Things) devices and wireless sensor networks facilitates real-time monitoring of environmental variables such as temperature, humidity, and soil moisture, providing valuable data for disease prediction and prevention.
Kothari et al. (Tue,) studied this question.