Data Analytics and Data-driven Tools for Smart Agriculture
Abstract
Digital agriculture is quickly embracing the capabilities of Big Data that has been successfully developed in other sectors of industry, such as banking and cybersecurity. Digitalization of agriculture has enabled sensors and sensor networks to collect high-resolution data on different farm parameters, which are then processed and analyzed by models to make predictions about growth and productivity. The nature of data pipeline, data collection strategies, data analysis models, and predictive tools need to be carefully assessed by technology developers in collaboration with farmers to generate sufficient value for investment. This is one of the limitations of today’s technologies geared towards smart agriculture where the technology does not appropriately serve the specific farm needs or does not generate sufficient value to the farm. This paper reviews the data analytics pipeline for smart agriculture with a focus on types of data being generated, models being developed, and predictions made about farm events. We address the current challenges in data analytics including data privacy and security that need further attention as the size and volume of the generated data grows with time. This paper serves as an introductory review of different themes of data analytics that hold potential within smart agriculture.