Frost Monitoring Cyber–Physical System: A Survey on Prediction and Active Protection Methods

Abstract

Frost damage in broadacre cropping and horticulture (including viticulture) results in substantial economic losses to producers and may also disrupt associated product value chains. Frost risk windows are changing in timing, frequency, and duration. Faced with the increasing cost of mitigation infrastructure and competition for resources (e.g. water and energy), multi-peril insurance, and the need for supply chain certainty, producers are under pressure to innovate in order to manage and mitigate risk. Frost protection systems are cyber-physical systems comprising of sensors (event detection), intelligence (prediction), and actuators (active protection methods). The Internet of Things communication protocols joining the cyber-physical system components are also evaluated. In this context, this paper introduces and reviews existing methods of frost management. This paper focuses on active protection methods because of their potential for real-time deployment during frost events. For integrated frost prediction and active protection systems, prediction method, sensor types, and integration architecture are assessed, research gaps are identified and future research directions proposed.

Intelligent Spatial Interpolation-based Frost Prediction Methodology using Artificial Neural Networks with Limited Local Data

“…Recent frost prediction methods can be divided into "classification methods" and "regression methods" [3]. The classification methods predict the probability of frost occurrence in the future.…”

“…Fortunately, frost events could be predicted and detected. Recent frost prediction methods are based on machine learning models [3]. These models require historical data from a specific site to predict future frost events.…”

“…These models require historical data from a specific site to predict future frost events. However, this requirement of on-site historical data poses a restriction for model construction in new sites without historical data [3]. Long periods of time are needed for data collection at these new sites to construct and deploy the machine learning models.…”

Food Supply Chains as Cyber-Physical Systems: a Path for More Sustainable Personalized Nutrition

“…Precision agriculture can rely on quite specific developments such as Wireless Underground Sensor Networks, when machinery is "communicated" with sensors under soil [96,112] or underground sensor networks controlling the quality of soils [13,50,81,112]. Further developments in agricultural stage include real-time monitoring of crops growth in field and greenhouses [47,64,94,105], weed control [119], and precise autonomous water or fertilizer management on the field [60,72,93] or frost monitoring [125]. Some authors proposed an overall method for information integration based on a service-oriented architecture (SOA) in agri-food supply chain networks, potentially enhanced with cloud systems, [25,45,116].…”

Towards the Optimal RF Sensing Strategy for IoT Applications: An Ice Sensing Case Study

“…R EMOTELY monitoring the accumulation of ice and frost is of great importance to smart cities [1], industrial [2], and environmental sensing [3] applications. For example, in renewable wind power farms, ice formation on wind turbines can reduce their power output by up to 30% over a year, in a region prone to icing events [4].…”