Este artigo apresenta uma abordagem através demodelosbaseadosem ML(MachineLearning)aplicadosemImagens NDVI (Normalized Difference Vegetation Index) para estimativasda produtividade na cultura da Cana-de-Açúcar. O uso de técnicas humanas baseadas em experiências cognitivas épredominantepara prever a produtividade. Asimagens utilizadas foram o NDVI fornecido pelo satélite Sentinel-2, sendo que os conjuntos de dados foramobtidosa partir dos pontos de georreferenciamento dos talhões e aplicados às imagenspara extração e processadas. Osmodelos dosalgoritmos preditivos utilizados foram:(i)CNN (Convolution Neural Network), (ii) KNN (K-Nearest Neighbors), (iii) RF (Random Forest), (iv) SVM (Support Vector Machie), (v) AdaBoost (AdaptiveBoosting). O algoritmo de RF apresentou-seomaiseficiente, de modoque osresultadospara oDP (Desvio Padrão)e a fórmulapara oMSE(Mean Square Error) obtiveram30,71 toneladas (t)e oMAE (Mean Absolute Error) obteve 3,73 (t). Narelaçãodas estimativas, a fórmuladoDP para o MSE obteve 34,71 (t) e o MAE de 3,97 (t). O EM (Erro Médio) para as estimativasfoide-8,80% e o algoritmo RF de 0,012%. Os resultados mostraram-seconsistentes para as estimavas da produtividade na cultura da Cana-de-Açúcar.
This article presents an approach through models based on ML (Machine Learning) applied to NDVI (Normalized Difference Vegetation Index) images to estimate productivity in the sugarcane crop. The use of human techniques based on cognitive experiences is predominant to anticipate productivity. The images used were provided by the NDVI Sentinel-2 satellite, since the datasets were obtained from two georeferenced points, two plots and applied to the images for extraction and processing. Two predictive algorithms are used for the models: (i) CNN (Convolution Neural Network), (ii) KNN (K-Nearest Neighbors), (iii) RF (Random Forest), (iv) SVM (Support Vector Machie) , (v) AdaBoost (Adaptive Boost). The RF algorithm was presented or more efficient, so that the results for the DP (Standard Deviation) and the formula for the MSE (Mean Square Error) obtained 30.71 tons (t) and the MAE (Mean Absolute Error) obtained 3.73(t). Regarding the estimates, the DP formula for the MSE obtains 34.71 (t) and the MAE of 3.97 (t). The EM (Mean Error) for the estimates was -8.80% and the RF algorithm was 0.012%. The results will show consistency for the productivity estimates in the sugarcane crop.
