A deep learning algorithm for detection of potassium deficiency in a red grapevine and spraying actuation using a raspberry pi3

The fourth industrial revolution (4IR) has ushered in technological advancement, which is currently reshaping all sectors of the economy, including the agricultural domain. This paper describes the application of artificial intelligence technique on an embedded device. It involves the smart detection of potassium deficiency in red grape vines using the deep learning algorithm. This was deployed on a raspberry pi-3 for real-time actuation and effective prediction. The light-emitting diode (LED) was lit when a potassium deficient red grapevine leaf was brought close to the pi-camera. Image data obtained was fed as input into the model. Training, validation, and testing accuracies of 89%, 81%, and 80% were obtained respectively for the CNN model which surpassed the performance of the Support Vector Machines (SVM) classifier. This research has demonstrated a paradigm shift from the conventional agricultural method of detecting nutrient deficiency to a more effective real-time deep learning algorithm which prompt a corresponding actuation to effectively spray of fertilizers. This technique in no doubt would lead to tremendous increase in food production.