Machine Learning Techniques for Detection and Classification of Crop (Solanum lycopersicum) Plant Diseases Due to Pests: A Review

Agriculture supplies all people with food, even in situations of high population growth. Early detection of plant diseases is encouraged as it is essential to make sure entire population has a supply of food. However, it can be difficult to predict diseases when crops are still developing. The main aim of this paper is to discuss various used machine learning techniques to identify different types of pests in crop (Solanum lycopersicum) plant. Artificial intelligence is a subset of machine learning and has gained attention recently due to autonomous learning benefits and data pre-processing. Additionally, it has evolved into a centre for research on agricultural plant protection, including identifying plant diseases and assessing pest ranges. ML in tomato (Solanum lycopersicum) leaf disease recognition can lessen negative effects of artificially choosing disease spot attributes, improves the features extraction, and fasten development of new technologies. This paper describes recent advances in the field of ML-based pest classification. Using ML and imaging technologies, we describe current developments and difficulties in pest identification. Then, the research gaps and proposed methodology has been discussed which help scientists to investigate who are trying to recognise plant illnesses and insect pests. Additionally, we stated some of the current issues and challenges that require simultaneous resolution.