Machine learning-based water quality prediction using octennial in-situ Daphnia magna biological early warning system data.

Biological early warning system (BEWS) has been globally used for surface water quality monitoring. Despite its extensive use, BEWS has exhibited limitations, including difficulties in biological interpretation and low alarm reproducibility. This study addressed these issues by applying machine learning (ML) models to eight years of in-situ BEWS data for Daphnia magna. Six ML models were adopted to predict contamination alarms from Daphnia behavioral parameters. The light gradient boosting machine model demonstrated the most significant improvement in predicting alarms from Daphnia behaviors. Compared with the traditional BEWS alarm index, the ML model enhanced the precision and recall by 29.50% and 43.41%, respectively. The speed distribution index and swimming speed were significant parameters for predicting water quality warnings. The nonlinear relationships between the monitored Daphnia behaviors and water physicochemical water quality parameters (i.e., flow rate, Chlorophyll-a concentration, water temperature, and conductivity) were identified by ML models for simulating Daphnia behavior based on the water contaminants. These findings suggest that ML models have the potential to establish a robust framework for advancing the predictive capabilities of BEWS, providing a promising avenue for real-time and accurate assessment of water quality. Thereby, it can contribute to more proactive and effective water quality management strategies.

Decoupling ion concentrations from effluent conductivity profiles in capacitive and battery electrode deionizations using an artificial intelligence model.

Owing to its simplicity of measurement, effluent conductivity is one of the most studied factors in evaluations of desalination performance based on the ion concentrations in various ion adsorption processes such as capacitive deionization (CDI) or battery electrode deionization (BDI). However, this simple conversion from effluent conductivity to ion concentration is often incorrect, thereby necessitating a more congruent method for performing real-time measurements of effluent ion concentrations. In this study, a random forest (RF)-based artificial intelligence (AI) model was developed to address this shortcoming. The proposed RF model showed an excellent prediction accuracy when it was first validated in predicting the effluent conductivity for both CDI (R2 = 0.86) and BDI (R2 = 0.95) data. Moreover, the RF model successfully predicted the concentration of each ion (Na⁺, K⁺, Ca2⁺, and Cl⁻) from the conductivity values. The accuracy of the ion concentration prediction was even higher than that of the effluent conductivity prediction, likely owing to the linear correlation between the input and output variables of the dataset. The effect of the sampling interval was also evaluated for conductivity and ion concentrations, and there was no significant difference up to sampling intervals of <80 s based on the error value of the model. These findings suggest that an RF model can be used to predict ion concentrations in CDI/BDI, which may be used as core indicators in evaluating desalination performance.

A study of cyanobacterial bloom monitoring using unmanned aerial vehicles, spectral indices, and image processing techniques.

Last 5 years, the deterioration of water quality caused by algal bloom has emerged as a serious issue in Korea. The method of on-site water sampling to check algal bloom and cyanobacteria is problematic by only partially measuring the site and not fully representing the field, while at the same time, consuming a lot of time and manpower to complete it. In this study, the different spectral indices reflecting the spectral characteristics of photosynthetic pigments were compared. We monitored harmful algal bloom and cyanobacteria in Nakdong rivers with multispectral sensor images from unmanned aerial vehicles (UAVs). The multispectral sensor images were used to assess the applicability of estimating cyanobacteria concentration based on field sample data. Several wavelength analysis techniques were conducted in June, August, and September 2021, when algal bloom intensified, including the analysis of images from multispectral cameras using normalized difference vegetation index (NDVI), green normalized difference vegetation index (GNDVI), blue normalized difference vegetation index (BNDVI), and normalized difference red edge index (NDREI). Radiation correction was performed using the reflection panel to minimize interference that could distort the analysis results of the UAVs image. Regarding field application and correlation analysis, correlation value of NDREI was the highest at 0.7203 in June. And NDVI was the highest at 0.7607 and 0.7773 in August and September, respectively. Based on the results obtained from this study, it is found that it is possible to quickly measure and judge the distribution status of cyanobacteria. In addition, the multispectral sensor installed to the UAV can be considered as a basic technology for monitoring the underwater environment.

New machine learning-based automatic high-throughput video tracking system for assessing water toxicity using Daphnia Magna locomotory responses.

Daphnia magna is an important organism in ecotoxicity studies because it is sensitive to toxic substances and easy to culture in laboratory conditions. Its locomotory responses as a biomarker are highlighted in many studies. Over the last several years, multiple high-throughput video tracking systems have been developed to measure the locomotory responses of Daphnia magna. These high-throughput systems, used for high-speed analysis of multiple organisms, are essential for efficiently testing ecotoxicity. However, existing systems are lacking in speed and accuracy. Specifically, speed is affected in the biomarker detection stage. This study aimed to develop a faster and better high-throughput video tracking system using machine learning methods. The video tracking system consisted of a constant temperature module, natural pseudo-light, multi-flow cell, and an imaging camera for recording videos. To measure Daphnia magna movements, we developed a tracking algorithm for automatic background subtraction using k-means clustering, Daphnia classification using machine learning methods (random forest and support vector machine), and tracking each Daphnia magna location using the simple online real-time tracking algorithm. The proposed tracking system with random forest performed the best in terms of identification (ID) precision, ID recall, ID F1 measure, and ID switches, with scores of 79.64%, 80.63%, 78.73%, and 16, respectively. Moreover, it was faster than existing tracking systems such as Lolitrack and Ctrax. We conducted an experiment to observe the impact of toxicants on behavioral responses. Toxicity was measured manually in the laboratory and automatically using the high-throughput video tracking system. The median effective concentration of Potassium dichromate measured in the laboratory and using the device was 1.519 and 1.414, respectively. Both measurements conformed to the guideline provided by the Environmental Protection Agency of the United States; therefore, our method can be used for water quality monitoring. Finally, we observed Daphnia magna behavioral responses in different concentrations after 0, 12, 18, and 24 h and found that there was a difference in movement according to the concentration at all hours.

Application of jetventurimixer for developing low-energy-demand and highly efficient aeration process of wastewater treatment.

In biological wastewater treatment, the oxygen supply in an aeration tank is the most important factor for removing organic pollutants, but it takes a large amount of electricity to generate the oxygen supply required. The Jetventurimixer (JVM) is a device that applies Bernoulli's principle, and the difference in flow rate pressure through the impeller is generated by the rotational force. Due to this physical mechanism, this device can supply oxygen in the atmosphere to the bioreactor without additional power. In this study, the JVM-based aeration process was developed for more efficient water treatment that demands lower energy. Parameters were measured for validating the efficiency and lower power demands, including the oxygen mass transfer characteristics and power efficiency. The results indicated that all parameters related to the oxygen mass transfer characteristics were advanced in performance by more than 200 % compared to those of the conventional air diffuser. In the case of power efficiency, it was confirmed that performance was 153-176 % higher. Therefore, it was confirmed that the JVM provides high-efficiency and low-energy benefits to the aeration process and, based on these advantages, the developed system seems to require further studies and validation for application to the water treatment system.

Pyrolytic Remediation and Ecotoxicity Assessment of Fuel-Oil-Contaminated Soil.

Oil-contaminated soil is a major societal problem for humans and the environment. In this study, the pyrolysis method was applied to oil-contaminated soil used as a landfill and gas station site in Korea. The removal efficiency of the main components of oil-contaminated soils, such as total petroleum hydrocarbons (TPH), polyaromatic hydrocarbons (PAHs), unresolved complex mixture (UCM), and alkylated PAHs (Alk-PAHs) were measured, and the effect of temperature, treatment time, and moisture content on pyrolysis efficiency was studied. In order to evaluate the risk of soil from which pollutants were removed through pyrolysis, integrated ecotoxicity was evaluated using Daphnia magna and Allivibrio fischeri. The chemical and biological measurements in this study include contaminants of emerging concerns (CECs). Results showed that the pyrolysis was more efficient with higher treatment temperatures, moisture content, and treatment times. In addition, toxicity was reduced by 99% after pyrolysis, and the degree of toxicity was evaluated more sensitively in Allivibrio fischeri than in Daphnia magna. This study shows that weathered oil-contaminated soil can be effectively treated in a relatively short time through pyrolysis, as well as provides information on efficient conditions and the assessment of ecotoxicity.

Transparent, water-stable, cellulose nanofiber-based packaging film with a low oxygen permeability.

Herein, we report on a transparent, water-stable, high oxygen barrier packaging film made from a combination of cellulose nanofiber (CNF) and a fluoropolymer (FP) coating. Nanofibrillation of the hardwood kraft pulp was carried out using succinic anhydride pretreatment and aqueous counter collision (ACC) technique to obtain ultrafine (5-7 nm) succinylated cellulose nanofibers (SCNF), which was readily fabricated into a thin coating (on PET film) as well as a self-standing film. Introducing the FP topcoat on SCNF enabled a synergistic enhancement of both oxygen barrier performance and stability against water-swelling.

Hierarchical Chitin Fibers with Aligned Nanofibrillar Architectures: A Nonwoven-Mat Separator for Lithium Metal Batteries.

Here, we introduce regenerated fibers of chitin (Chiber), the second most abundant biopolymer after cellulose, and propose its utility as a nonwoven fiber separator for lithium metal batteries (LMBs) that exhibits an excellent electrolyte-uptaking capability and Li-dendrite-mitigating performance. Chiber is produced by a centrifugal jet-spinning technique, which allows a simple and fast production of Chibers consisting of hierarchically aligned self-assembled chitin nanofibers. Following the scrutinization on the Chiber-Li-ion interaction via computational methods, we demonstrate the potential of Chiber as a nonwoven mat-type separator by monitoring it in Li-O2 and Na-O2 cells.