Main Article Content
In protected agriculture, deficiency of an essential element may drastically affect plant growth, appearance and most importantly yield. Information about nutrient deficiencies in crops grown in controlled environment is essential to optimize food productivity. In this study, near infrared reflectance spectroscopy (NIRS) analysis was used to identify nitrogen (N) deficiency coupled with pattern recognition methods in mini-cucumber plants grown under non-soil conditions. Leaves at the first three nodes of nitrogen deficient plants and control plant were used for NIRS data acquisition. K-nearest neighbors (KNN) and artificial neural network (ANN) were applied to build diagnostics models, respectively. Some parameters of the model were optimized by cross-validation. The performance of the KNN model and the ANN model based on NIRS data was compared. Experiment results showed that the ANN model was better than the KNN model. The optimal ANN model was achieved when principle component factors were equal to 5 and identification rate of the ANN model were 100% in both the training set and the prediction set. This study demonstrated that the NIRS coupled with ANN pattern recognition method can be successfully applied to the diagnostics of nitrogen deficiency in minicucumber plant grown under non-soil conditions.
Key words: Deficiency, nitrogen, near infrared reflectance spectroscopy (NIRS), artificial neural network.