A Novel Application for Identification of Nutrient Deficiencies in Oil Palm Using the Internet of Things

Abstract

This paper presents a novel approach to identify and geolocate nutrient deficiencies in oil-palm plantations using a mobile application. The process starts when the user captures an image of an oil-palm leaf with the integrated camera of an Android smart device. Then, the application processes and classifies the image into four categories corresponding to: a healthy palm, or a specimen with a deficit of Potassium (K), Magnesium (Mg), or Nitrogen (N). Finally, the application shows the corresponding predictions on the screen and it includes the current timestamp and GPS coordinate. However, if the smart device has an internet connection, the application also sends the processed data to Microsoft Azure for long-term storage and it enables the visualization of historic predictions through a web report built with Microsoft Power BI. The developed application allows producers to obtain in situ diagnosis of plant deficiencies in their crops, helping nutrient management plans and crop management policies. The proposed solution can be easily scaled to hundreds of devices for field deployments because each mobile application is configured as an Internet-of-Things device in the Azure Cloud.