Analysis of Copernicus’ ERA5 Climate Reanalysis Data as a Replacement for Weather Station Temperature Measurements in Machine Learning Models for Olive Phenology Phase Prediction

Abstract

Knowledge of phenological events and their variability can help to determine final yield, plan management approach, tackle climate change, and model crop development. THe timing of phenological stages and phases is known to be highly correlated with temperature which is therefore an essential component for building phenological models. Satellite data and, particularly, Copernicus’ ERA5 climate reanalysis data are easily available. Weather stations, on the other hand, provide scattered temperature data, with fragmentary spatial coverage and accessibility, as such being scarcely efficacious as unique source of information for the implementation of predictive models. However, as ERA5 reanalysis data are not real temperature measurements but reanalysis products, it is necessary to verify whether these data can be used as a replacement for weather station temperature measurements. The aims of this study were: (i) to assess the validity of ERA5 data as a substitute for weather station temperature measurements, (ii) to test different machine learning models for the prediction of phenological phases while using different sets of features, and (iii) to optimize the base temperature of olive tree phenological model. The predictive capability of machine learning models and the performance of different feature subsets were assessed when comparing the recorded temperature data, ERA5 data, and a simple growing degree day phenological model as benchmark. Data on olive tree phenology observation, which were collected in Tuscany for three years, provided the phenological phases to be used as target variables. The results show that ERA5 climate reanalysis data can be used for modelling phenological phases and that these models provide better predictions in comparison with the models trained with weather station temperature measurements.

Application of Copernicus Data for Climate-Relevant Urban Planning Using the Example of Water, Heat, and Vegetation

“…In principle, therefore, there already exists a wide range of forward-looking approaches to using climate and environmental data. This data is as provided in particular by Copernicus, for the derivation of climate projections (e.g., [29,[37][38][39]) and for the use of past, present, and projected data for the identification of expected climate-and weather-related challenges at the local level (e.g., [40][41][42][43]).…”

Comparison of Climate Reanalysis and Remote-Sensing Data for Predicting Olive Phenology through Machine-Learning Methods

“…These indices can also be used to predict other phenological parameters [10]. We considered climate and MODIS-derived features to improve the prediction of phenological events based only on temperature, as in [34,40].…”

“…The baseline model used as a benchmark for this study was random forest because, in recent studies [40], the random-forest model had better accuracy than that of the original GDD baseline technique detailed in [34,40]. Random-forest operates by constructing several decision trees during training, and outputting the most voted class as the prediction of all the trees.…”

“…In order to avoid overfitting, and ensure the stability and efficiency of the model, parameter estimation using grid search with cross-validation was performed over the following parameters and values: number of trees (number of estimators, 100, 200, 300), the minimal number of samples required to be at a leaf node (2, 3, 5, 7), maximal depth of the tree (7,9,11,13,15), and minimal cost-complexity pruning (0, 0.0001, 0.001, 0.01, 0.1). As demonstrated in [34,40], the selection of the base temperature for GDD calculation plays an important role in determining model accuracy. A new value was proposed for the base temperature in order to optimize olive phenology prediction below the original base temperature set at 10 • C. Indeed, at lower temperature values, the RMSE of the model improved.…”

Application of COPERNICUS Data for Climate-Relevant Urban Planning Using the Example of Water, Heat, and Vegetation

“…In principle, therefore, there already exists a wide range of forward-looking approaches to the use of climate and environmental data, as provided in particular by Copernicus, for the derivation of climate projections (e.g., [11][12][13][14]) and for the use of past, present, and projected data for the identification of expected climate-and weather-related challenges at the local level (e.g., [15][16][17][18].…”