Approach to long-term forecasting of frosts and droughts in smart agriculture

Abstract

Due to the trend of a global increase in average daily temperatures and the occurrence of extreme weather events, the task of long-term forecasting of agrometeorological risks is becoming increasingly actual. The work considers frost and drought as the main meteorological risks. The problem comes down to analyzing time series, in the simple case one-dimensional. In each individual case, based on a preliminary analysis of the initial information, researchers select the most effective method; there is no comprehensive comparison of probabilistic and statistical approaches to long-term forecasting of time series. In this regard, the goal of the work was to formulate the concept of a unified intelligent system for long-term forecasting of drought and frost. The proposed approach involves generating traditional, well-studied models for each source dataset in real time and selecting the most accurate result. The need to develop an intelligent system for long-term forecasting of droughts and frosts is also confirmed by the results of computational experiments carried out in this work on three different datasets. To conduct computational experiments, we used the open programming language R (RStudio), which is widely used and has proven itself in scientific research. The results of the analysis of datasets showed that different methods turn out to be the most accurate for different source data. Moreover, datasets 1 and 2 were prepared from the same weather station for the same period; only the observation factors differ.