RESUMO
We have evaluated the agronomic performance of table cassava cultivars fertilized with phosphorus doses in the Brazilian Semiarid Region. Two agricultural crops were grown at the Rafael Fernandes Experimental Farm, Mossoró, RN, from June/2018 to April/2019 and from June/2019 to April/2020. The experimental design was in randomized blocks, arranged in subdivided plots, with four replications. In the plots, doses of phosphorus were applied (0, 60, 120, 180 and 240 kg P2O5 ha-1), and in the subplots, the table cassava cultivars (Água Morna, BRS Gema de Ovo, Recife and Venâncio). The following were evaluated: dry matter of leaf, stem, and commercial root; harvest index; commercial root number; commercial productivity and aerial part productivity. The cultivars used had high root and aerial part productivities indicating that their irrigated cultivation is appropriate under the conditions of the Semiarid region of Rio Grande do Norte. The cultivars Água Morna, BRS Gema de Ovo and Recife are more efficient in the use of phosphorus, obtaining high productivity even in the absence of phosphate fertilization. The cultivar Venâncio is more responsive to phosphate fertilization, as it needs an input of this nutrient to increase its productivity.
RESUMO
BACKGROUND: Weed control can be economically viable if implemented at the necessary time to minimize interference. Empirical mathematical models have been used to determine when to start the weed control in many crops. Furthermore, empirical models have a low generalization capacity to understand different scenarios. However, computational development facilitated the implementation of supervised machine learning models, as artificial neural networks (ANNs), capable of understanding complex relationships. The objectives of our work were to evaluate the ability of ANNs to estimate yield losses in onion (model crop) due to weed interference and compare with multiple linear regression (MLR) and empirical models. RESULTS: MLR constructed from non-destructive and destructive methods show R2 and root mean square error (RMSE) values varying between 0.75% and 0.82%, 13.0% and 19.0%, respectively, during testing step. The ANNs has higher R2 (higher than 0.95) and lower RMSE (less than 6.95%) compared to MLR and empirical models for training and testing steps. ANNs considering only the coexistence period and system have similar performance to MLR models. However, the insertion of variables related to weed density (non-destructive ANN) or fresh matter (destructive ANN) increases the predictive capacity of the networks to values close to 99% correct. CONCLUSION: The best performing ANNs can indicate the beginning of weed control since they can accurately estimate losses due to competition. These results encourage future studies implementing ANNs based on computer vision to extract information about the weed community.