Comparison of the machine learning and AquaCrop models for quinoa crops

One of the main causes having low crop efficiency in Peru is poor management water resources; which why objective this article to estimate amount irrigation required quinoa crops through a comparison between machine learning and AquaCrop models. For development study, meteorological data from province Jauja descriptive were processed simulation period was established June December 2020. From carried out, it determined that best model predict Adaptive Boosting (AdaBoost) observed mean standard deviation AdaBoost models (mean = 19.681 SD 4.665) behave similarly 19.838 5.04). In addition, result ANOVA has P-value indicator with value 0.962 smaller margin error relation absolute (MAE) 0.629. Likewise, identified that, for 190 days, 472.35 mm carry out process red crops.