Fusion of Spectroscopy and Cobalt Electrochemistry Data for Estimating Phosphate Concentration in Hydroponic Solution

Abstract

Phosphate is a key element affecting plant growth. Therefore, the accurate determination of phosphate concentration in hydroponic nutrient solutions is essential for providing a balanced set of nutrients to plants within a suitable range. This study aimed to develop a data fusion approach for determining phosphate concentrations in a paprika nutrient solution. As a conventional multivariate analysis approach using spectral data, partial least squares regression (PLSR) and principal components regression (PCR) models were developed using 56 samples for calibration and 24 samples for evaluation. The R2 values of estimation models using PCR and PLSR ranged from 0.44 to 0.64. Furthermore, an estimation model using raw electromotive force (EMF) data from cobalt electrodes gave R2 values of 0.58–0.71. To improve the model performance, a data fusion method was developed to estimate phosphate concentration using near infrared (NIR) spectral and cobalt electrochemical data. Raw EMF data from cobalt electrodes and principle component values from the spectral data were combined. Results of calibration and evaluation tests using an artificial neural network estimation model showed that R2 = 0.90 and 0.89 and root mean square error (RMSE) = 96.70 and 119.50 mg/L, respectively. These values are sufficiently high for application to measuring phosphate concentration in hydroponic solutions.

Model Predictive Control via Output Feedback Neural Network for Improved Multi-Window Greenhouse Ventilation Control

“…The first hidden layer used 45 nodes and the hyperbolic tangent (Tanh) activation, while the second hidden layer used 30 nodes and the rectified linear unit (ReLU) activation function ( Table 2). In the previous study [20], the results were verified through various combinations of active functions in the hidden nodes and parameter values, but no significant correlation was found. For training, the Levenberg-Marquardt algorithm was used, a gradient descent method for avoiding local minima and overfitting [20] of the 73,440 samples used for model development; training used 70%, validation 15%, and testing 15%.…”

“…Models based on neural networks are suitable for both linear and nonlinear modeling and have been applied to greenhouse environment modeling and control logic [18][19][20]. Many studies have reported reliable results in environmental prediction modeling using artificial neural networks [18,[21][22][23][24].…”

Multivariate Standard Addition Cobalt Electrochemistry Data Fusion for Determining Phosphate Concentration in Hydroponic Solution

“…Recently, fusion technique has been applied to detect phosphate in hydroponic solutions. For example, Jung et al [35] used two types of sensors, i.e. NIR spectroscopy and cobalt electrode, to develop fusion for detecting PO 4 ion concentration in a paprika nutrient solution.…”

“…Though many approaches based on unique or associative fusion techniques have been used, the cobalt electrode has not been deployed yet in practical applications. This is because of some weaknesses such as it needs frequently abrading and electrode surface treating constantly to ensure induce oxidation reaction, which affects changes in the electrode signal band [35], [36]. Moreover, MSAM is considered to be the most suitable method for compensating the shortcomings of ISEs sensing systems.…”

Combination of Multivariate Standard Addition Technique and Deep Kernel Learning Model for Determining Multi-Ion in Hydroponic Nutrient Solution

“…However, none of technical strategies has radically resolved the drawbacks of ISEs. Other investigations focused on predicting the ions that are not available through an ion-selective electrode (as such , , and Mg) were examined by fusing the datasets acquired from an array of available ISEs [ 20 , 27 , 28 , 29 ].…”