Forecasting frost risk in forest plantations by the combination of spatial data and machine learning algorithms

Abstract

Brazil is one of the leading timber producers in the world. However, in South Brazil, frost events frequently cause damage and reduce yield in forest plantations, a situation predicted to become more common under global change scenarios. This raises the need for low cost and efficient tools, such as machine learning algorithms to improve forecasting of frost risk. This study used machine learning algorithms to create zoning classifications forecasting frost risk for forest plantations located in the south-central region of Rio Grande do Sul State, Brazil. For this, we gathered and processed data from a local geodatabase (i.e. high-spatial-resolution contour lines, hydrography, and forest stands limits) comprising 30 management units with consistent historical data of frost occurrence. Then, we generated possible local-scale predictors of frost occurrence, which included longitude, latitude, elevation, relative altitude, relief orientation, and Euclidean distance from hydrography. We carried out tests of three machine learning classifiers (Random Forest – RF; Support Vector Machine-SVM and Multi-layer Perceptron-MLP) in order to determine which would most accurately predict frost occurrence. We found that RF provided the highest accuracy (> 90%), as well as the smallest percentages of class-specific errors (i.e. commission and omission errors), when compared to SVM and MLP. Latitude was the most important predictor of frost occurrence when using RF. Conversely, MLP performed worst, especially for classifying frost occurrence versus non-occurrence, and therefore had the highest percentage of class-specific errors. Our findings lead us to conclude that RF is the most proficient algorithm for forecasting frost occurrence from local-scale geomorphological data, without the need for high-cost investment in micro-meteorological sensors to monitor climate frost events linking temperature to plant damage. With increasing global climate extreme events, accurate risk zoning is essential for planning strategies of plantation at the landscape scale.