Identification and estimation of lodging in bread wheat genotypes using machine learning predictive algorithms

BACKGROUND: Lodging or stem bending decreases wheat yield quality and quantity. Thus, the traits reflected in early lodging wheat are helpful for early monitoring to some extent. In order to identify the superior genotypes and compare multiple linear regression (MLR) with support vector regression (SVR), artificial neural network (ANN), and random forest regression (RF) for predicting lodging in Iranian wheat accessions, a total of 228 wheat accessions were cultivated under field conditions in an alpha-lattice experiment, randomized incomplete block design, with two replications in two cropping seasons (2018–2019 and 2019–2020). To measure traits, a total of 20 plants were isolated from each plot and were measured using image processing. RESULTS: The lodging score index (LS) had the highest positive correlation with plant height (r = 0.78**), Number of nodes (r = 0.71**), and internode length 1 (r = 0.70**). Genotypes were classified into four groups based on heat map output. The most lodging-resistant genotypes showed a lodging index of zero or close to zero. The findings revealed that the RF algorithm provided a more accurate estimate (R(2) = 0.887 and RMSE = 0.091 for training data and R(2) = 0.768 and RMSE = 0.124 for testing data) of wheat lodging than the ANN and SVR algorithms, and its robustness was as good as ANN but better than SVR. CONCLUSION: Overall, it seems that the RF model can provide a helpful predictive and exploratory tool to estimate wheat lodging in the field. This work can contribute to the adoption of managerial approaches for precise and non-destructive monitoring of lodging.