Enhanced CNN Model for Lettuce Disease Identification in Indoor Aeroponic Vertical Farming Systems

India, like many other nations, heavily relies on agricultural exports to fund its national budget. Economic losses may occur when crop and plant diseases reduce production quality and quantity. Hence, it is crucial to detect infections early on in crop farming. Commercial crops grown using aeroponic vertical farming techniques include lettuce in particular. To increase the crop yield, the crop should be free from disease-causing agents like viral, bacterial, or fungal. As a response, scientists have utilized deep learning algorithms for the automatic identification of abnormalities in both indoor and outdoor farming crops by capturing leaf images. In this work, fine-tuned convolutional neural networks (CNN) were utilized to identify diseases in the aeroponic lettuce crops in an effective manner. Further, the Convolutional Neural Networks (CNN) were fine-tuned by training them on lettuce images. While testing, a higher accuracy of 95.6258% was achieved. Hence, this research work signifies that the proposed model would be appropriate for lettuce disease classification in controlled environment agriculture.