Search

Objectives:The purpose of this study is to compare single models according to the missing value handling techniques for predicting leachate generation.Methods:Input factors such as landfill gas generation, and weather data (precipitation, wind speed, radiation, temperature, and relative humidity) were used from June 2002 to October 2018. Linear interpolation and mean method were used as the missing value handling technique. The experiment was conducted by dividing the data into train and test data according to the optimal ratio. Various single models were used, and the prediction performance of the model was compared and evaluated using coefficient of determination (R2).Results and Discussion:The gated recurrent unit (GRU) model was the best among the single models. In the GRU model, R2 was 0.867 for linear interpolation and R2 was 0.839 for the mean method, so that the GRU model using linear interpolation was most suitable for predicting leachate generation. In the ANN model, R2 of linear interpolation (0.862) was higher than that of mean method (0.828). In the long short-term memory (LSTM) model, R2 was 0.779 for linear interpolation and 0.762 for mean method. In the random forest (RF) model, R2 for linear interpolation (0.700) was also higher than that for the mean method (0.665). The model performance was excellent in the order GRU>ANN>LSTM>RF. The linear interpolation for the missing value handling technique was superior to the mean method in all models used in this experiment.Conclusion:The GRU using linear interpolation was the most suitable model for predicting landfill leachate generation.

Purpose : This study aims to suggest an optimal model for predicting photovoltaic (PV) power generation by comparing single and hybrid models that include particulate matter in the atmosphere as input parameters.Methods : From December 2016 to December 2019, 1 MW-class PV power generation data in Jindo-gun, Jeollanam-do and meteorological data and particulate matter data from Mokpo were used. Radiation, sunshine time, pressure, temperature, humidity, wind speed, wind direction, snow load, precipitation, PM10, and PM2.5 were used as input parameters. We used single models such as random forest (RF), artificial neural network (ANN), long short-term memory (LSTM), and gate recurrent unit (GRU) and hybrid model such as LSTM-ANN and GRU-ANN. Coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were used to compare and evaluate the prediction performance of the models.Results and Discussion : The variable importance through RF was as follows: radiation (77.66%), day light hours (4.85%), pressure (4.16%), temperature (3.98%), humidity (2.25%), wind speed (2.21%), PM10 (2.72%), PM2.5 (1.65%), wind direction (1.44%), snow cover (0.05%), and precipitation (0.02%). GRU-ANN showed the highest R2 (0.838) among the models and lower epoch (8) than GRU using the early stop.Conclusion : The GRU-ANN model was the most suitable for forecasting PV power generation including particulate matter.

Objectives : In this study, we select input factors for machine learning models to predict dissolved oxygen (DO) in Gyeongan Stream and compare results of performance evaluation indicators to find the optimal model.Methods : The water quality data from the specific points of Gyeongan Stream were collected between January 15, 1998 and December 30, 2019. The pretreatment data were divided into train and test data with the ratio of 7:3. We used random forest (RF), artificial neural network (ANN), convolutional neural network (CNN), and gated recurrent unit (GRU) among machine learning. RF and ANN were tested by both random split and time series data, while CNN and GRU conducted the experiment using only time series data. Performance evaluation indicators such as square of the correlation coefficient (R2), root mean square error (RMSE), and mean absolute error (MAE) were used to compare the optimal results for the models.Results and Discussion : Based on the RF variable importance results and references, water temperature, pH, electrical conductivity, PO4-P, NH4-N, total phosphorus, suspended solids, and NO3-N were used as input factors. Both RF and ANN performed better with time series data than random split. The model performance was good in order of RF > CNN > GRU > ANN.Conclusions : The eight input factors (water temperature, pH, electrical conductivity, PO4-P, NH4-N, total phosphorus, suspended solids, and NO3-N) were selected for machine learning models to predict DO in Gyeongan Stream. The best model for DO prediction was the RF model with time series data. Therefore, we suggest that the RF with the eight input factors could be used to predict the DO in streams.

Objective:Coagulation of Moringa oleifera seeds was studied to determine the optimal conditions in treating a turbid water.Method:Jar-test experiments were performed at various rapid mixing (90-250 rpm; 1-2 min), slow mixing (10-60 rpm; 10-50 min), initial turbidity (100-500 NTU), coagulant doses (200-1,500 mg/L), and pH (2-12) in synthetic wastewater. Response surface analysis was used to optimize the coagulation in jar-test experiments.Results and Discussion:The optimal conditions for turbidity removal with M. oleifera were 200 rpm of rapid-mixing speed for 1 min, 40 rpm of slow-mixing speed for 20 min, and pH 8. The coagulation efficiency was found to be dependent on initial turbidity of water samples. Highest turbidity removals (96.5%) were obtained for water with very high initial turbidity (500 NTU). The effects of initial turbidity and coagulant dose were successfully analyzed by the response surface analysis. Within the design boundaries, turbidity removal was more sensitive to changes in initial turbidity than to changes in coagulant dose.Conclusions:The quadratic model between initial turbidity and coagulant for turbidity removal was shown. M. oleifera can be used as a potential coagulant especially for high turbidity water.

Objective : Present research discussed the utilization of pumpkin-seed residue (PSR) after oil extraction with methanol as an adsorbent for methylene blue (MB) removal from aqueous solution.Method : The experiment was carried out to evaluate the influence of PSR adsorbent dose (7.5-25 g/L), initial MB concentration (25-200 mg/L), contact time (30-120 min), pH (3-11), and temperature (293-333 K). Adsorption isotherms were modeled with the Langmuir, Freundlich, and Temkin isotherms. The kinetic data were analyzed using pseudo-first-order and pseudo-second-order models.Results and Discussion : A pseudo-equilibrium state was reached within 30 min of contact time at low initial MB concentration (25-50 mg/L) and 90 min at high concentration (100-200 mg/L). Increasing pH and temperature caused an increase in adsorption capacity. Thermodynamic studies demonstrated that the adsorption process was spontaneous with Gibb’s free-energy values ranging between -15.78 to -13.87 kJ/mol and endothermic with an enthalpy value of 0.011 kJ/mol. The adsorption equilibrium data fitted well with the Freundlich adsorption isotherm. The maximum monolayer adsorption capacity was 20.33 mg/g. Tempkin isotherm model clarified that the heat of sorption process was 6.28 J/mol. The adsorption kinetics was found to follow the pseudo-second order kinetics model and its rate constant was 0.002-0.278 g/mg･min.Conclusions : Findings of the present study indicated that the PSR can be successfully used for removal of MB from aqueous solution. Therefore, the PSR was shown to have good potential as a biosorbent for MB removal.

This study evaluates the efficacy of titanium tetrachloride (TiCl 4 ) on phosphorus (P) removal in synthetic wastewater. Jar test experiments were performed at various TiCl 4 concentration (0.25-0.59 mM), and intensities of slow (30-60 rpm) and rapid (100-250 rpm) mixings to determine the conditions at which P removal was most efficient. The P-removal efficiency was highest (about 99%) at TiCl 4 concentration ([TiCl 4 ])=0.39 mM with rapid-mixing intensity=100 rpm and slow-mixing intensity=30 rpm. The slow-mixing intensity was more sensitive than the rapid-mixing intensity to the P removal efficiency when [TiCl 4 ] was low (0.25≤[TiCl 4 ]≤0.27 mM). Key Words : Coagulation, Mixing Intensity, pH, Phosphorus, Titanium Tetrachloride 요약: 본 연구는 TiCl 4 의 농도(0.25-0.59 mM)와 급속교반속도(100-250 rpm), 완속교반속도(30-60 rpm)의 변화가 인 제거효율에 미치는 영향을 알아보고자 하였다. 응집제 농도가 0.25≤[TiCl 4 ]≤0.39 mM 범위에서 인 제거 효율은 TiCl 4 의 농도가 증가할수록 증가하였으며 처리후 인의 농도는 0.2 mg/L 이하였다. 응집제 농도 0.39 mM, 급속교반속도 100 rpm, 완속교반속도 30 rpm에서 인 제거효율이 약 99%로 가장 높았다. TiCl

This work experimentally determined the effect of thermal and microwave pretreatments on the anaerobic digestion of mixtures of municipal primary and secondary sludges in semi-continuous mesophilic digesters at hydraulic retention times (HRT) of 20, 15, 10, 7, and 5 days. The ratio of soluble chemical oxygen demand (COD) to total COD in thermally pretreated and microwaved sludges at 80°C was 2.7 and 3.2 times higher than that of raw sludge, respectively. The volatile solids (VS) and COD removal efficiencies in all three di gesters fed with raw (control), thermally pretreated (TM), and microwaved (MW) sludges decreased as the HRT was reduced. The highest relative improvement in VS removal compared to the control occurred at the HRT of 5 days in the TM and MW (29 and 41% higher than the control, respectively). At this HRT, improvement in the COD removal efficiencies in the TM and MW compared to the control was 28 and 53%, respectively. Improvements in biogas production compared with the control increased in both the TM and MW as the HRT was reduced to 5 days. The relative improvement in daily biogas production compared to the control from the TM and MW was 33 and 53% higher than the control at the HRT of 5 days, respectively. The results show that microwave pretreatment is more effective than thermal pretreatment in increasing the solubilization degree and mesophilic anaerobic biodegradability of sewage sludge.

Solubilization of sewage sludge creates favorable conditions for anaerobic microorganisms to produce biogas. In this paper, we quantify the effect of heating pretreatment on the degree of solubilization of sewage sludge. The pretreatment process was carried out using a lab-scale industrial microwave unit (2450 MHz frequency). Response surface analysis was applied to determine the combination of temperature-increase rate (ramp rate) (2.9 to 17.1℃/min) and terminal temperature (52 to 108℃). Both ramp rate and temperature significantly affected the solubilization degree of sludge. Within the design boundaries, the conditions predicted to maximize the solubilization degree of 15.8% were determined to be 2.9℃/min and 104℃.