Novel combination artificial neural network models could not outperform individual models for weather-based cashew yield prediction

Cashew is an important cash crop which is ecologically sensitive, making it vulnerable to climate change. So, the present study compares the performance of stepwise linear regression (SLR), least absolute shrinkage and selection operator (LASSO), elastic net, and artificial neural network (ANN) individually against the ANN model combined with SLR, LASSO, elastic net, and principal components analysis (PCA) for prediction of cashew yield based on weather parameters. The model performances were evaluated using three approaches: (1) Taylor plot; (2) statistical metrics like coefficient of determination (R-2), root mean square error (RMSE), and normalized RMSE (nRMSE); and (3) ranking followed by Kruskal-Wallis and Dunn's post hoc test. The results revealed that during calibration, the R-2 and RMSE ranged from 0.486 to 0.999 and 2.184 to 88.040 kg ha(-1), respectively, while RMSE and nRMSE varied from 3.561 to 242.704 kg ha(-1) and 0.799 to 89.949%, respectively, during validation. Kruskal-Wallis and Dunn's post hoc test revealed LASSO as the best model which was at par with ELNET, SLR, and ELNET-ANN. So, these models can be used for cashew yield prediction for the study area well in advance.

Automated summary

Cashew is an ecologically sensitive cash crop, and this study compared different models for predicting cashew yield based on weather parameters. The results showed that the LASSO model performed the best and can be used for advance prediction of cashew yield.