Application of artificial neural networks to frost detection in central Chile using the next day minimum air temperature forecast

Abstract

Predicting future climatic events is one of the key issues in many fields, whether in scientific or industrial areas. An artificial neural network (ANN) model, based on a backpropagation type, was developed in this study to predict the minimum air temperature of the following day from meteorological data using air temperature, relative humidity, radiation, precipitation, and wind direction and speed to detect the occurrence of radiative frost events. The configuration of the next day ANN prediction system allows operating with low-power computing machines; it is able to generate early warnings that can lead to the development of effective strategies to reduce crop damage, lower quality, and losses in agricultural production. This paper presents a procedural approach to an ANN, which was trained, validated, and tested in 10 meteorological stations in central Chile for approximately 8 yr (2010)(2011)(2012)(2013)(2014)(2015)(2016)(2017). The overall mean results were classified by a confusion matrix and showed good performance in predicting minimum temperature with a mean square error (MSE) of 2.99 ºC for the network, 1.71 ºC for training, 1.77 ºC for validation, and 1.74 ºC for the testing processes. Frost detection results had an appropriate 98% overall mean accuracy (ACC), 86% sensitivity (TPR), and 2% error rate (ER). Differences and errors in frost detection can be attributed to several factors that are mainly associated with the accuracy of the sensors meteorological stations, local climatic and geographic conditions, and the number of parameters that enter in the ANN training processes.

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

“…The majority of recent frost prediction regression methods [8], [9], [10], [11], [12], [13] predict the minimum temperature of the next 12-24 hours. The prediction models include, linear regression [8], [9], random forest [10], and ANNs [11], [12], [13]. The ANNs have the highest accuracy among the other model types [3].…”

Chemical products for crop protection against freezing stress: A review

“…advective) that give rise to frost (Fuentes et al, 2018;Perry, 1998;Snyder & de Melo-Abreu, 2005) Plants cold acclimate when they are exposed to low, but nonfreezing temperatures (slightly above the water freezing temperature) for several days or weeks and the period of exposure to light decreases, whilst being growth retarded (Larcher, 2003;Ruelland et al, 2009;Fürtauer et al, 2019). In this process, plant metabolism changes as a result of hormonal changes (Fürtauer et al, 2019;Galiba & Tóth, 2017); moreover, membrane proteins and lipid compositions change, and the concentrations of metabolites (protective substances) increase (Fürtauer et al, 2019;Hoermiller et al, 2018;Larcher, 2003).…”

“…Spring frosts are most relevant for temperate crops and can trigger huge economic losses (Guillaume et al., 2018; Ma, Huang, et al., 2019). Orchard losses of 506,000 ton, equivalent to about US $354 million, were the result of spring frost in central Chile in September 2013 (ODEPA (Oficina de Estudios y Políticas Agrarias) 2013; Fuentes et al., 2018), resulting in serious economic and social problems for the government, growers, and rural families (ODEPA (Oficina de Estudios y Políticas Agrarias) 2013; Beyá‐Marshall et al., 2019). Similar losses occurred in central and eastern USA in 2007, when spring frost resulted in economic losses worth more than US $2.0 billion, due to reductions in wheat ( Triticum aestivum L.), peach ( Prunus persica (L.) Stokes), apple ( Malus domestica (Borkh.)…”

“…Notwithstanding the above discussion, damage provoked by frost continues to be a huge problem for crop production (Fuentes et al., 2018; Guillaume et al., 2018; Smith, 2019), and different mechanisms have been developed to protect crops against ice formation in the cells of plants (Smith, 2019). Frost protection methods for crops can be divided into passive and active methods (Hu et al., 2018; Smith, 2019; Snyder & de Melo‐Abreu, 2005).…”

Integration of Google Play Content and Frost Prediction Using CNN: Scalable IoT Framework for Big Data

“…Prediction of weather temperature in a crop field is a crucial issue, whether in the urban area or rural area. In [33], they have used the ANN model, but with another approach, their accuracy is good, but some conflictions also need to be resolved in terms of data. They have mainly sensors to get weather data from weather stations.…”