A Review of the Historical and Prospective Applications of Predictive Analytics in Precision Agriculture

Abstract

Precision agriculture (PA) has gained popularity because it can solve the agricultural industry's problems while reducing its environmental impact. This paper examines precision agriculture's predictive analytics history and possible applications. The report underlines the rising global demand for food and the need for sustainable agriculture. The restrictions and environmental concerns of conventional agriculture have driven precision agriculture adoption. This study analyses the development of precision agricultural technologies from wireless sensor networks (WSN) to the Internet of Things. This article covers the numerous IoT challenges in agriculture. Internet security, power constraints, and storage limits are covered in detail. This study shows that precision agriculture relies on the Internet of Things (IoT). Sensors, communication devices, and embedded systems collect and evaluate crucial agricultural data. This article evaluates LoRa, Bluetooth, and Zigbee in agricultural settings. This research also examines data analytics in agriculture, explaining the concept and emphasising the importance of big data. This article discusses big data in agriculture, covering large data sets, quick data collection, different data kinds, data correctness and dependability, and data value extraction. Machine learning (ML), deep learning (DL), and data mining are essential for predictive analytics, which predicts future outcomes based on previous data. This research shows that precision agriculture can meet global food demand and environmental concerns. In order to exploit precision agriculture, IoT and big data issues must be addressed