Effectiveness of potato late blight (Phytophthora infestans) forecast by meteorological estimation in mountainous terrain based on CARAH rules

Potato late blight (PLB) caused by Phytophthora infestans (Mont.) de Bary, its incidence and development are highly dependent on meteorological conditions. To solve the problem of PLB in mountainous terrain under the condition of limited meteorological monitoring capability, the air temperature and humidity was estimated based on the basic meteorological datasets, the forecast effect of the onset period and infection cycle of PLB based on CARAH rules was evaluated. The average MAE, RMSE and CI of the estimated air temperature and observations were 1.17 °C, 1.52 °C and 0.95, respectively. The average MAE, RMSE and CI of the estimated relative humidity and observations were 8.0 %, 10.7 % and 0.53, respectively. The curve of the infection cycle of PLB at different locations were estimated from the basic meteorological datasets based on the CARAH rules, and the false alarm and missing ratios were 8.8 % and 4.6 % respectively. It may be delayed by 1 or 2 fungal generations compared to the observations, and then the protective fungicide should be adjusted to a systemic fungicide. The false alarm of the infection cycle of PLB may increase in dry air conditions, and the missing report may occur in humid condition.

Improving the accuracy of air relative humidity prediction using hybrid machine learning based on empirical mode decomposition: a comparative study

This paper proposes a hybrid air relative humidity prediction based on preprocessing signal decomposition. New modelling strategy was introduced based on the use of the empirical mode decomposition, variational mode decomposition, and the empirical wavelet transform, combined with standalone machine learning to increase their numerical performances. First, standalone models, i.e., extreme learning machine, multilayer perceptron neural network, and random forest regression, were used for predicting daily air relative humidity using various daily meteorological variables, i.e., maximal and minimal air temperatures, precipitation, solar radiation, and wind speed, measured at two meteorological stations located in Algeria. Second, meteorological variables are decomposed into several intrinsic mode functions and presented as new input variables to the hybrid models. The comparison between the models was achieved based on numerical and graphical indices, and obtained results demonstrate the superiority of the proposed hybrid models compared to the standalone models. Further analysis revealed that using standalone models, the best performances are obtained using the multilayer perceptron neural network with Pearson correlation coefficient, Nash-Sutcliffe efficiency, root-mean-square error, and mean absolute error of approximately ≈0.939, ≈0.882, ≈7.44, and ≈5.62 at Constantine station, and ≈0.943, ≈0.887, ≈7.72, and ≈5.93 at Sétif station, respectively. The hybrid models based on the empirical wavelet transform decomposition exhibited high performances with Pearson correlation coefficient, Nash-Sutcliffe efficiency, root-mean-square error, and mean absolute error of approximately ≈0.950, ≈0.902, ≈6.79, and ≈5.24, at Constantine station, and ≈0.955, ≈0.912, ≈6.82, and ≈5.29, at Sétif station. Finally, we show that the new hybrid approaches delivered high predictive accuracies of air relative humidity, and it was concluded that the contribution of the signal decomposition was demonstrated and justified.