Objectives : Automated machine learning is a recent field of study that automates the process of machine learning model development including proper model selection and optimization. In this study, ...auto H2O, a novel automated machine learning algorithm, was used to develop a model to predict chlorophyll-a (chl-a).Methods : This study used datasets with different observation frequencies of 1h, 2h, 8h, 24h and 1 week for the development of a machine learning model using an auto H2O algorithm to analyze the effects of measurement frequency of input data on model performance. The effect of the concentration of the input datasets on the performance of the model was also compared by building a model using datasets with observed values of chl-a exceeding 30 mg/m3. The model performance was evaluated using three indices mean absolute error (MAE), Nash-Sutcliffe coefficient of efficiency (NSE) and root mean squared error-observation standard deviation ratio (RSR).Results and Discussion : The MAE, NSE, and RSR of the model using the input data with a measurement frequency of 1h were analyzed as 0.8977, 0.9710, and 0.1704, respectively. The higher the measurement frequency of the input data, the better the performance of the model as the NSE of the model using full data was 0.9710, 0.9552, 0.8856, 0.8396, and 0.7509 for the input datasets with 1h, 2h, 8h, 24h and 1 week observation frequencies, respectively. The difference in model performance according to the difference in measurement frequency was larger for the model using data with the measured value of chl-a exceeding 30 mg/m3, as the NSE was analyzed to be 0.8971, 0.8164, 0.5704, 0.5141, and 0.2052, respectively.Conclusion : The auto H2O model for predicting chl-a showed better model performance as the measurement frequency of the input data increased, and the difference in performance according to the measurement frequency was larger in the range of observed chl-a concentrations that exceeded 30 mg/m3.
Water quality control and management in water resources are important for providing clean and safe water to the public. Due to their large area, collection, analysis, and management of a large amount ...of water quality data are essential. Water quality data are collected mainly by manual field sampling, and recently real-time sensor monitoring has been increasingly applied for efficient data collection. However, real-time sensor monitoring still relies on only a few parameters, such as water level, velocity, temperature, conductivity, dissolved oxygen (DO), and pH. Although advanced sensing technologies, such as hyperspectral images (HSI), have been used for the areal monitoring of algal bloom, other water quality sensors for organic compounds, phosphorus (P), and nitrogen (N) still need to be further developed and improved for field applications. The utilization of information and communications technology (ICT) with sensor technology shows great potential for the monitoring, transmission, and management of field water-quality data and thus for developing effective water quality management. This paper presents a review of the recent advances in ICT and field applicable sensor technology for monitoring water quality, mainly focusing on water resources, such as rivers and lakes, and discusses the challenges and future directions.
•There is a lack of information on the use of ultrasonication at large scales/the field.•The efficiency of ultrasonication for algal removal in field is still debatable.•Attenuation of ultrasonic ...intensity needs to be considered in field applications.•Further field data is required for the upscaling of ultrasonication devices.
Algal blooms are a naturally occurring phenomenon which can occur in both freshwater and saltwater. However, due to excess nutrient loading in water bodies (e.g. agricultural runoff and industrial activities), harmful algal blooms (HABs) have become an increasing issue globally, and can even cause health effects in humans due to the release of cyanotoxins. Among currently available treatment methods, sonication has received increasing attention for algal control because of its low impact on ecosystems and the environment. The effects of ultrasound on algal cells are well understood and operating parameter such as frequency, intensity, and duration of exposure has been well studied. However, most studies have been limited to laboratory data interpretation due to complicated environmental conditions in the field. Only a few field and pilot tests in small reservoirs were reported and the applicability of ultrasound for HABs prevention and control is still under question. There is a lack of information on the upscaling of ultrasonication devices for HAB control on larger water bodies, considering field influencing factors such as rainfall, light intensity/duration, temperature, water flow, nutrients loading, and turbidity. In this review article, we address the challenges and field considerations of ultrasonic applications for controlling algal blooms. An extensive literature survey, from the fundamentals of ultrasound techniques to recent ultrasound laboratory and field studies, has been thoroughly conducted and summarized to identify future technical expectations for field applications. Case studies investigating spatial distribution of frequency and pressure during sonication are highlighted with future implications.
Algal blooms have various effects on drinking water supply systems; thus, proper monitoring is essential. Traditional visual identification using a microscope is a time-consuming method and requires ...extensive labor. Recently, advanced machine learning algorithms have been increasingly applied for the development of object detection models. The You-Only-Look-Once (YOLO) model is a novel machine learning algorithm used for object detection; it has been continuously improved in newer versions, and a tiny version of each standard model presented. The tiny versions applied a less complicated architecture using a smaller number of convolutional layers to enable faster object detection than the standard version. This study compared the applicability of the YOLO models for algal image detection from a practical aspect in terms of classification accuracy and inference time. Therefore, automated algal cell detection models were developed using YOLO v3 and YOLO v4, in which a tiny version of each model was also applied. The cell images of 30 algal genera were used for training and testing the models. The model performances were compared using the mean average precision (mAP). The mAP values of the four models were 40.9, 88.8, 84.4, and 89.8 for YOLO v3, YOLO v3-tiny, YOLO v4, and YOLO v4-tiny, respectively, demonstrating that YOLO v4 is more precise than YOLO v3. The tiny version models presented noticeably higher model accuracy than the standard models, allowing up to ten times faster object detection time. These results demonstrate the practical advantage of tiny version models for the application of object detection with a limited number of object classes.
Many studies have attempted to predict chlorophyll-a concentrations using multiple regression models and validating them with a hold-out technique. In this study commonly used machine learning ...models, such as Support Vector Regression, Bagging, Random Forest, Extreme Gradient Boosting (XGBoost), Recurrent Neural Network (RNN), and Long–Short-Term Memory (LSTM), are used to build a new model to predict chlorophyll-a concentrations in the Nakdong River, Korea. We employed 1–step ahead recursive prediction to reflect the characteristics of the time series data. In order to increase the prediction accuracy, the model construction was based on forward variable selection. The fitted models were validated by means of cumulative learning and rolling window learning, as opposed to the hold–out technique. The best results were obtained when the chlorophyll-a concentration was predicted by combining the RNN model with the rolling window learning method. The results suggest that the selection of explanatory variables and 1–step ahead recursive prediction in the machine learning model are important processes for improving its prediction performance.
In this study, an ensemble machine learning model was developed to predict the recovery rate of water quality in a water treatment plant after a disturbance. XGBoost, one of the most popular ensemble ...machine learning models, was used as the main framework of the model. Water quality and operational data observed in a pilot plant were used to train and test the model. Disturbance was determined when the observed turbidity was higher than the given turbidity criteria. Therefore, the recovery rate of water quality at a time t was defined during the falling limb of the turbidity recovery period. It was considered as a relative ratio of the differences between the peak and observed turbidities at time t to the difference between the peak turbidity and turbidity criteria. The root mean square error–observation standard deviation ratio of the XGBoost model improved from 0.730 to 0.373 by pretreatment, removing the observation for the rising limb of the disturbance from the training data. Moreover, Shapley value analysis, a novel explainable artificial intelligence method, was used to provide a reasonable interpretation of the model’s performance.
Microcystis sp. is one of the most common harmful cyanobacteria that release toxic substances. Counting algal cells is often used for effective control of harmful algal blooms. However, Microcystis ...sp. is commonly observed as a colony, so counting individual cells is challenging, as it requires significant time and labor. It is urgent to develop an accurate, simple, and rapid method for counting algal cells for regulatory purposes, estimating the status of blooms, and practicing proper management of water resources. The flow cytometer and microscope (FlowCAM), which is a dynamic imaging particle analyzer, can provide a promising alternative for rapid and simple cell counting. However, there is no accurate method for counting individual cells within a Microcystis colony. Furthermore, cell counting based on two-dimensional images may yield inaccurate results and underestimate the number of algal cells in a colony. In this study, a three-dimensional cell counting approach using a novel model algorithm was developed for counting individual cells in a Microcystis colony using a FlowCAM. The developed model algorithm showed satisfactory performance for Microcystis sp. cell counting in water samples collected from two rivers, and can be used for algal management in fresh water systems. KCI Citation Count: 0
An excessive increase in algae often has various undesirable effects on drinking water supply systems, thus proper management is necessary. Algal monitoring and classification is one of the ...fundamental steps in the management of algal blooms. Conventional microscopic methods have been most widely used for algal classification, but such approaches are time-consuming and labor-intensive. Thus, the development of alternative methods for rapid, but reliable algal classification is essential where an advanced machine learning technique, known as deep learning, is considered to provide a possible approach for rapid algal classification. In recent years, one of the deep learning techniques, namely the convolutional neural network (CNN), has been increasingly used for image classification in various fields, including algal classification. However, previous studies on algal classification have used CNNs that were arbitrarily chosen, and did not explore possible CNNs fitting algal image data. In this paper, neural architecture search (NAS), an automatic approach for the design of artificial neural networks (ANN), is used to find a best CNN model for the classification of eight algal genera in watersheds experiencing algal blooms, including three cyanobacteria (Microcystis sp., Oscillatoria sp., and Anabaena sp.), three diatoms (Fragilaria sp., Synedra sp., and two green algae (Staurastrum sp. and Pediastrum sp.). The developed CNN model effectively classified the algal genus with an F1-score of 0.95 for the eight genera. The results indicate that the CNN models developed from NAS can outperform conventional CNN development approaches, and would be an effective tool for rapid operational responses to algal bloom events. In addition, we introduce a generic framework that provides a guideline for the development of the machine learning models for algal image analysis. Finally, we present the experimental results from the real-world environments using the framework and NAS.