Estimate soil moisture of maize by combining support vector machine and chaotic whale optimization algorithm

Soil moisture of maize has an extremely important impact on the growth and development of maize. Failure to accurately estimate soil moisture will lead to severe reductions in maize yields and thus intensify the global food crisis, so it is extremely important to accurately estimate soil moisture of maize. This study proposes a new hybrid machine learning model (SVM-SWOA) that incorporates the Whale Optimization Algorithm (WOA) into sinusoidal chaotic graphs and couples it with a support vector machine (SVM). The model is with both high convergence speed and high accuracy. After using the data from two maize agricultural districts in Iowa, USA for model creation, Taylor plots and significance tests were used to enable the model for identifying input variables. To verify the performance of the model, SVM-SWOA was comprehensively evaluated with both SVM and SVMWOA models. Results showed that SVM-SWOA was improved 14%, 13%, 41.5%, and 14% over SVM-WOA at 60 cm depth for MAE, RMSE, MAPE, and MBE, respectively, and 20%, 29.5%, 44.5%, and 38% over SVM, respectively. It implies that the SVM-SWOA meta-heuristic algorithm can provide better guidance for smart agriculture and precision irrigation.

Automated summary

This study proposes a new hybrid machine learning model (SVM-SWOA) that combines the Whale Optimization Algorithm (WOA) and support vector machine (SVM), which shows high convergence speed and accuracy. Results indicate that the SVM-SWOA model outperforms traditional SVM and SVMWOA models in estimating maize soil moisture, providing better guidance for smart agriculture and precision irrigation.