As the automation of nutrient solution management proceeds in the field of hydroponics, effective supporting systems to manage the nutrient solution by computer become needed. This study was attempt to predict the EC of nutrient solution using the neural networks. The multilayer perceptron consisting of 3 layers with the back propagation learning algorithm was selected for EC prediction, of which nine variables in the input layer were the concentrations of each ion and one variable in the output layer the EC of nutrient solution. The meq unit in ion concentration was selected fir input variable in the input layer. After the 10,000 learning sweeps with 108 sample data, the comparison of predicted and measured ECs for 72 test data showed good agreements with the correlation coefficient of 0.998. In addition, the predicted ECs by neural network showed relatively equal or closer to the measured ones than those by current complicated models.

The optimum management of nutrient solution needs the effective combination of fertilizers as well as the accurate control of nutrient solution. This study was attempt to make a supporting system for effective fertilizer combination by using computer and also to develop a EC predicting equation for keeping the EC of solution within the allowable range after application of combined fertilizers. The supporting system consists of three parts : (1) data bases, (2) rules for deciding the kinds and amounts of fertilizers and (3) main control. With input data, the main control automatically constructs the network connecting the related data bases and subsequently executes the operation of searching proper fertilizers through it. For more effective searching, fertilizers are classified into two levels(level 1 and level 2) in consideration of solubility, price, and frequency in use, and searched in that order. The EC prediction equation, a extended form of the Robinson and Stroke's theoretical equation only available for a binary electrolyte, is suggested for predicting the EC of the nutrient solution containing many kinds of inorganic compounds. The comparison of predicted and measured ECs showed good agreements with the high correlation between the predicted EC decrement by ion interaction and the actual one(limiting EC minus measured EC).

Electrical Conductivity (EC) or Total Dissolved Solids (TDS) has been often used to evaluate the water quality in some water education program for children and youth. This study attempted to find out whether EC (or TDS) can be used as a water pollution criteria in water education program. To clarify it, we used the water analysis data of July 2019 and January 2020 from Water Environment Information System. Data from 332 points in Han-river were used to investigate correlation between the parameters, such as BOD, COD, TN, TP vs EC. Correlation(r) for all data of BOD vs. EC was 0.347 for July 2019 and 0.483 for January 2020. No correlation was observed for BOD Ia and BOD Ib for July 2019 (r=-0.041, -0.030, respectively) and BOD Ia for January 2020 (r=0.041). Better correlation for all data of COD vs. EC was obtained (r=0.543 for July 2019 and r=0.610 for January 2020). However, no correlation was observed for COD Ia for January 2020. High vlaue of EC or TDS does not always mean water pollution, especially for clean water environment. Thus, EC (or TDS) alone can not be used as a water pollution criteria.