Detecting newly emerging Apple Blotch Leaf Miner (ABLM) using a deep learning approach

Apple Blotch Leaf Miner (ABLM) has just recently surfaced and is posing serious risk to apple orchards worldwide. It is crucial to find the disease early in its infection cycle to properly regulate and prevent more damage. Unfortunately, some learned behaviors are never forgotten when it comes to traditional diseases. In this situation, corruption of the methods of diagnosing the illness and the use of ABLM as the primary agent are always present, especially in the early stages of the infection when the virus manifests as eggs or larvae. Therefore, it is imperative to evaluate contemporary trends and develop robust and precise artificial intelligence (AI) detection algorithms. The goal of these systems is to gather enough high-quality field data to build these kinds of systems. However, the attempts to develop AI models have been thwarted by the lack of these kinds of datasets. However, there are issues with the similarity of ABLM to other leaf-mining insects, as well as the effects of various variables on the leaf that cause the edible portions of the leaf to decay. This indicates that the only way to fix the issue is to use highly developed AI systems that can distinguish ABLM from other killers while also avoiding the effects of outside influences. This review investigates and highlights the clear deficiency in the availability of reliable data sets and AI models required for the timely diagnosis of ABLM. By addressing these critical gaps, we can significantly improve the management of this emerging disease and make timely interventions.