Four Major South Korea's Rivers Using Deep Learning Models

Real-Time Chlorophyll-a Forecasting using Machine Learning Framework with Dimension Reduction and Hyperspectral Data

Since water is an essential resource in various fields, it requires constant monitoring. Chlorophyll-a concentration is a crucial indicator of water quality and can be used to monitor water quality. In this study, we developed methods to forecast chlorophyll-a concentrations in real-time using hyperspectral data on IoT platform and various machine learning algorithms. Compared to regular cameras that record information only in the three broad color bands of red, green, and blue, the hyperspectral images of drinking water sources record the data in dozens or even hundreds of distinct small wavelength bands, providing each pixel in an image with a full spectrum. Different machine learning algorithms have been developed using hyperspectral data and field observations of water quality and weather conditions. Previous studies have predicted chlorophyll concentrations using either partial least squares (PLS), which is a dimensionality reduction method, or machine learning. In contrast, our study employed the PLS technique as a preprocessing step to diminish the dimensionality of the hyperspectral data, followed by the application of the machine learning techniques with optimized hyperparameters to improve the precision of the predictions, thereby introducing a real-time mechanism for chlorophyll-a prediction. Consequently, a machine learning algorithm with R2 values of 0.9 or above and sufficiently small RMSE was developed for real-time chlorophyll-a forecasting. Real-time chlorophyll-a forecasting using LightGBM has the best performance, with a mean R2 of 0.963 and a mean RMSE of 2.679. This paper is expected to have applications in algal bloom early detection on monitoring systems.

Recent advances in algal bloom detection and prediction technology using machine learning

Harmful algal blooms (HAB) including red tides and cyanobacteria are a significant environmental issue that can have harmful effects on aquatic ecosystems and human health. Traditional methods of detecting and managing algal blooms have been limited by their reliance on manual observation and analysis, which can be time-consuming and costly. Recent advances in machine learning (ML) technology have shown promise in improving the accuracy and efficiency of algal bloom detection and prediction. This paper provides an overview of the latest developments in using ML for algal bloom detection and prediction using various water quality parameters and environmental factors. First, we introduced ML for algal bloom prediction using regression and classification models. Then we explored image-based ML for algae detection by utilizing satellite images, surveillance cameras, and microscopic images. This study also highlights several real-world examples of successful implementation of ML for algal bloom detection and prediction. These examples show how ML can enhance the accuracy and efficiency of detecting and predicting algal blooms, contributing to the protection of aquatic ecosystems and human health. The study also outlines recent efforts to enhance the field applicability of ML models and suggests future research directions. A recent interest in explainable artificial intelligence (XAI) was discussed in an effort to understand the most influencing environmental factors on algal blooms. XAI facilitates interpretations of ML model results, thereby enhancing the models' usability for decision-making in field management and improving their overall applicability in real-world settings. We also emphasize the significance of obtaining high-quality, field-representative data to enhance the efficiency of ML applications. The effectiveness of ML models in detecting and predicting algal blooms can be improved through management strategies for data quality, such as pre-treating missing data and integrating diverse datasets into a unified database. Overall, this paper presents a comprehensive review of the latest advancements in managing algal blooms using ML technology and proposes future research directions to enhance the utilization of ML techniques.

Effects of typhoon events on coastal hydrology, nutrients, and algal bloom dynamics: Insights from continuous observation and machine learning in semi-enclosed Zhanjiang Bay, China

Typhoons can induce variations in hydrodynamic conditions and biogeochemical processes, potentially escalating the risk of algal bloom occurrences impacting coastal ecosystems. However, the impacts of typhoons on instantaneous changes and the mechanisms behind typhoon-induced algal blooms remain poorly understood. This study utilized high-frequency in situ observation and machine learning model to track the dynamic variations in meteorological, hydrological, physicochemical, and Chlorophyll-a (Chl-a) levels through the complete Typhoon Talim landing in Zhanjiang Bay (ZJB) in July 2023. The results showed that a delayed onset of algal bloom occurring 10 days after typhoon's arrival. Subsequently, as temperatures reached a suitable range, with an ample supply of nutrients and water stability, Chl-a peaked at 121.49 μg L-1 in algal bloom period. Additionally, water temperature and air temperature decreased by 1.61 °C and 2.8 °C during the typhoon, respectively. In addition, wind speed and flow speed increased by 1.34 and 0.015 m s-1 h-1 to peak values, respectively. Moreover, the slow decline of 8.2 % in salinity suggested a substantial freshwater input, leading to an increase in nutrients. For instance, the mean DIN and DIP were 2.2 and 8.5 times higher than those of the pre-typhoon period, resulting in a decrease in DIN/DIP (closer to16) and the alleviation of P limitation. Furthermore, pH and dissolved oxygen (DO) were both low during the typhoon period and then peaked at 8.93 and 19.05 mg L-1 during the algal bloom period, respectively, but subsequently decreased, remaining lower than those of the pre-typhoon period. A preliminary learning machine model was established to predict Chl-a and exhibited good accuracy, with R2 of 0.73. This study revealed the mechanisms of eutrophication status formation and algal blooms occurrence in the coastal waters, providing insights into the effects of typhoon events on tropical coastal biogeochemistry and ecology.

Research progress in water quality prediction based on deep learning technology: a review

Water, an invaluable and non-renewable resource, plays an indispensable role in human survival and societal development. Accurate forecasting of water quality involves early identification of future pollutant concentrations and water quality indices, enabling evidence-based decision-making and targeted environmental interventions. The emergence of advanced computational technologies, particularly deep learning, has garnered considerable interest among researchers for applications in water quality prediction because of its robust data analytics capabilities. This article comprehensively reviews the deployment of deep learning methodologies in water quality forecasting, encompassing single-model and mixed-model approaches. Additionally, we delineate optimization strategies, data fusion techniques, and other factors influencing the efficacy of deep learning-based water quality prediction models, because understanding and mastering these factors are crucial for accurate water quality prediction. Although challenges such as data scarcity, long-term prediction accuracy, and limited deployments of large-scale models persist, future research aims to address these limitations by refining prediction algorithms, leveraging high-dimensional datasets, evaluating model performance, and broadening large-scale model application. These efforts contribute to precise water resource management and environmental conservation.

Deep learning in water protection of resources, environment, and ecology: achievement and challenges

The breathtaking economic development put a heavy toll on ecology, especially on water pollution. Efficient water resource management has a long-term influence on the sustainable development of the economy and society. Economic development and ecology preservation are tangled together, and the growth of one is not possible without the other. Deep learning (DL) is ubiquitous in autonomous driving, medical imaging, speech recognition, etc. The spectacular success of deep learning comes from its power of richer representation of data. In view of the bright prospects of DL, this review comprehensively focuses on the development of DL applications in water resources management, water environment protection, and water ecology. First, the concept and modeling steps of DL are briefly introduced, including data preparation, algorithm selection, and model evaluation. Finally, the advantages and disadvantages of commonly used algorithms are analyzed according to their structures and mechanisms, and recommendations on the selection of DL algorithms for different studies, as well as prospects for the application and development of DL in water science are proposed. This review provides references for solving a wider range of water-related problems and brings further insights into the intelligent development of water science.

A novel hybrid model based on two-stage data processing and machine learning for forecasting chlorophyll-a concentration in reservoirs

The accurate and efficient prediction of chlorophyll-a (Chl-a) concentration is crucial for the early detection of algal blooms in reservoirs. Nevertheless, predicting Chl-a concentration in multivariate time series poses a significant challenge due to the complex interrelationships within the aquatic environment and the discrete and non-stationary nature of online monitoring of water quality data. To address the aforementioned issue, this paper proposes a novel prediction model named SGMD-KPCA-BiLSTM (SKB) for predicting Chl-a concentration. The model combines two-stage data processing and machine learning (ML). To capture nonlinear relationships in multivariate time series data, the optimal data subset is determined by combining symplectic geometry mode decomposition (SGMD) and kernel principal component analysis (KPCA). This subset is then input into a bidirectional long short-term memory (BiLSTM) model, and the model's hyperparameters are optimized using the sparrow search algorithm (SSA) to improve the accuracy of predictions. The performance of the model was evaluated at Qiaodian Reservoir in Shandong, China. To assess its superiority, the evaluation criteria included the root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), coefficient of determination (R2), frequency histograms of the prediction error, and the Taylor diagram. The prediction performance of five single models, namely the back-propagation (BP) neural network, support vector regression (SVR), long short-term memory (LSTM), convolutional neural network with long short-term memory (CNN-LSTM), and BiLSTM, as well as three hybrid models, namely SGMD-LSTM, SGMD-KPCA-LSTM, and SGMD-BiLSTM, were compared against the SKB model. The results demonstrated that the SKB model performs best in predicting Chl-a concentration (R2 = 96.19%, RMSE = 1.05, MAE = 0.65, MAPE = 0.08). It significantly reduced the prediction error compared to other models for comparison. Furthermore, the multi-step predictive capabilities of the SKB model are also discussed. The analysis shows a decline in predictive performance with larger prediction time steps, and the SKB model exhibits slightly superior performance compared to the other model at corresponding prediction intervals. The model has significant advantages in terms of its ability to accurately predict the non-smooth and nonlinear Chl-a sequences observed by the online monitoring system. This study presents a potential solution for controlling and preventing reservoir eutrophication, as well as an innovative approach for predicting water quality.

Current status and prospects of algal bloom early warning technologies: A Review

In recent years, frequent occurrences of algal blooms due to environmental changes have posed significant threats to the environment and human health. This paper analyzes the reasons of algal bloom from the perspective of environmental factors such as nutrients, temperature, light, hydrodynamics factors and others. Various commonly used algal bloom monitoring methods are discussed, including traditional field monitoring methods, remote sensing techniques, molecular biology-based monitoring techniques, and sensor-based real-time monitoring techniques. The advantages and limitations of each method are summarized. Existing algal bloom prediction models, including traditional models and machine learning (ML) models, are introduced. Support Vector Machine (SVM), deep learning (DL), and other ML models are discussed in detail, along with their strengths and weaknesses. Finally, this paper provides an outlook on the future development of algal bloom warning techniques, proposing to combine various monitoring methods and prediction models to establish a multi-level and multi-perspective algal bloom monitoring system, further improving the accuracy and timeliness of early warning, and providing more effective safeguards for environmental protection and human health.

One-Week-Ahead Prediction of Cyanobacterial Harmful Algal Blooms in Iowa Lakes

Cyanobacterial harmful algal blooms (CyanoHABs) pose serious risks to inland water resources. Despite advancements in our understanding of associated environmental factors and modeling efforts, predicting CyanoHABs remains challenging. Leveraging an integrated water quality data collection effort in Iowa lakes, this study aimed to identify factors associated with hazardous microcystin levels and develop one-week-ahead predictive classification models. Using water samples from 38 Iowa lakes collected between 2018 and 2021, feature selection was conducted considering both linear and nonlinear properties. Subsequently, we developed three model types (Neural Network, XGBoost, and Logistic Regression) with different sampling strategies using the nine selected variables (mcyA_M, TKN, % hay/pasture, pH, mcyA_M:16S, % developed, DOC, dewpoint temperature, and ortho-P). Evaluation metrics demonstrated the strong performance of the Neural Network with oversampling (ROC-AUC 0.940, accuracy 0.861, sensitivity 0.857, specificity 0.857, LR+ 5.993, and 1/LR- 5.993), as well as the XGBoost with downsampling (ROC-AUC 0.944, accuracy 0.831, sensitivity 0.928, specificity 0.833, LR+ 5.557, and 1/LR- 11.569). This study exhibited the intricacies of modeling with limited data and class imbalances, underscoring the importance of continuous monitoring and data collection to improve predictive accuracy. Also, the methodologies employed can serve as meaningful references for researchers tackling similar challenges in diverse environments.

Data fusion strategy based on ultraviolet-visible spectra and near-infrared spectra for simultaneous and accurate determination of key parameters in surface water

Chemical oxygen demand (COD), ammonia nitrogen (AN) and total nitrogen (TN) are the key parameters to reflect the degree of surface water pollution. Ultraviolet - visible (UV-Vis) spectroscopy and near - infrared (NIR) spectroscopy are ideal techniques for rapid monitoring of these indicators. In this study, a strategy based on the fusion of UV-Vis and NIR spectral data (UV-Vis-NIR) for water quality detection was proposed to further improve the quantitative analysis accuracy of spectroscopic methods. Seventy river samples with different levels of pollution were used for spectroscopic analysis. The UV-Vis-NIR fusion spectrum of each water sample was obtained by directly splicing sample's UV-Vis spectrum and NIR diffuse transmission spectrum. The UV-Vis-NIR fusion models were optimized through using different variable selection algorithms. The results show that the UV-Vis-NIR fusion models for surface water COD, AN and TN achieves better prediction results (the root mean square errors of prediction are 6.95, 0.195, and 0.466, respectively) than single-spectroscopic based models. Since better prediction performances were shown under different optimization conditions, the robustness of fusion models were also better than the single-spectroscopic based models. Therefore, the data fusion strategy proposed in this study has a promising application prospect for further accurate and rapid monitoring of surface water quality.

Long short-term memory models of water quality in inland water environments

Water quality is substantially influenced by a multitude of dynamic and interrelated variables, including climate conditions, landuse and seasonal changes. Deep learning models have demonstrated predictive power of water quality due to the superior ability to automatically learn complex patterns and relationships from variables. Long short-term memory (LSTM), one of deep learning models for water quality prediction, is a type of recurrent neural network that can account for longer-term traits of time-dependent data. It is the most widely applied network used to predict the time series of water quality variables. First, we reviewed applications of a standalone LSTM and discussed its calculation time, prediction accuracy, and good robustness with process-driven numerical models and the other machine learning. This review was expanded into the LSTM model with data pre-processing techniques, including the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise method and Synchrosqueezed Wavelet Transform. The review then focused on the coupling of LSTM with a convolutional neural network, attention network, and transfer learning. The coupled networks demonstrated their performance over the standalone LSTM model. We also emphasized the influence of the static variables in the model and used the transformation method on the dataset. Outlook and further challenges were addressed. The outlook for research and application of LSTM in hydrology concludes the review.

Advancements of remote data acquisition and processing in unmanned vehicle technologies for water quality monitoring: An extensive review

Regular water quality monitoring is becoming desirable due to the increase in water pollution caused by both climate change and the generation of industrial chemicals. Unmanned vehicles have emerged as key technologies for remote data acquisition, providing fast and accurate methods for water quality monitoring. However, current research on unmanned vehicles has not systematically examined their features and limitations, which are crucial for identifying future research directions and applications of unmanned vehicle technologies. Therefore, this study extensively reviews the advancements in remote data acquisition and processing using unmanned vehicle technologies for water quality monitoring to provide valuable insights for future research. First, the types of unmanned vehicles and their application ranges for water quality monitoring are summarized. Among the unmanned vehicle technologies, unmanned aerial vehicles are considered primary platforms for water quality monitoring due to their wide data acquisition range and their ability to accommodate diverse sensors and samplers. Also, the types of samplers and sensors mounted on the unmanned vehicles are analyzed based on their characteristics. It is concluded that spectral sensors offer the most cost-effective approach for acquiring real-time water quality data. Furthermore, algorithms that convert image data into water quality data are examined, focusing on data preprocessing, analysis, and validation. The findings reveal a close relationship between the analysis of spectral characteristics of each water quality parameter and the wavelength ranges of red and red-edge. Lastly, future research directions for unmanned vehicle technologies are further suggested based on the summarized technological limitations.

The leading global health challenges in the artificial intelligence era

Millions of people's health is at risk because of several factors and multiple overlapping crises, all of which hit the vulnerable the most. These challenges are dynamic and evolve in response to emerging health challenges and concerns, which need effective collaboration among countries working toward achieving Sustainable Development Goals (SDGs) and securing global health. Mental Health, the Impact of climate change, cardiovascular diseases (CVDs), diabetes, Infectious diseases, health system, and population aging are examples of challenges known to pose a vast burden worldwide. We are at a point known as the "digital revolution," characterized by the expansion of artificial intelligence (AI) and a fusion of technology types. AI has emerged as a powerful tool for addressing various health challenges, and the last ten years have been influential due to the rapid expansion in the production and accessibility of health-related data. The computational models and algorithms can understand complicated health and medical data to perform various functions and deep-learning strategies. This narrative mini-review summarizes the most current AI applications to address the leading global health challenges. Harnessing its capabilities can ultimately mitigate the Impact of these challenges and revolutionize the field. It has the ability to strengthen global health through personalized health care and improved preparedness and response to future challenges. However, ethical and legal concerns about individual or community privacy and autonomy must be addressed for effective implementation.

Improving algal bloom detection using spectroscopic analysis and machine learning: A case study in a large artificial reservoir, South Korea

The prediction of algal blooms using traditional water quality indicators is expensive, labor-intensive, and time-consuming, making it challenging to meet the critical requirement of timely monitoring for prompt management. Using optical measures for forecasting algal blooms is a feasible and useful method to overcome these problems. This study explores the potential application of optical measures to enhance algal bloom prediction in terms of prediction accuracy and workload reduction, aided by machine learning (ML) models. Compared to absorption-derived parameters, commonly used fluorescence indices such as the fluorescence index (FI), humification index (HIX), biological index (BIX), and protein-like component improved the prediction accuracy. However, the prediction accuracy was decreased when all optical indices were considered for computation due to increased noise and uncertainty in the models. With the exception of chemical oxygen demand (COD), this study successfully replaced biochemical oxygen demand (BOD), dissolved organic carbon (DOC), and nutrients with selected fluorescence indices, demonstrating relatively analogous performance in either training or testing data, with consistent and good coefficient of determination (R2) values of approximately 0.85 and 0.74, respectively. Among all models considered, ensemble learning models consistently outperformed conventional regression models and artificial neural networks (ANNs). However, there was a trade-off between accuracy and computation efficiency among the ensemble learning models (i.e., Stacking and XGBoost) for algal bloom prediction. Our study offers a glimpse of the potential application of spectroscopic measures to improve accuracy and efficiency in algal bloom prediction, but further work should be carried out in other water bodies to further validate our proposed hypothesis.

Source identification in river pollution incidents using a cellular automata model and Bayesian Markov chain Monte Carlo method

Identification of contaminant sources in rivers is crucial for river protection and emergency response. This study presents an innovative approach for identifying river pollution sources by using Bayesian inference and cellular automata (CA) modeling. A general Bayesian framework is proposed that combines the CA model with observed data to identify unknown sources of river pollution. To reduce the computational burden of the Bayesian inference, a CA contaminant transport model is developed to efficiently simulate pollutant concentration values in the river. These simulated concentration values are then used to calculate the likelihood function of available measurements. The Markov chain Monte Carlo (MCMC) method is used to produce the posterior distribution of contaminant source parameters, which is a sampling-based method that enables the estimation of complex posterior distributions. The suggested methodology is applied to a real case study of the Fen River in Yuncheng City, Shanxi Province, Northern China, and it estimates the release time, release mass, and source location with relative errors below 19%. The research indicates that the proposed methodology is an effective and flexible way to identify the location and concentrations of river contaminant sources.

Self-optimization of training dataset improves forecasting of cyanobacterial bloom by machine learning

Data-driven model (DDM) prediction of aquatic ecological responses, such as cyanobacterial harmful algal blooms (CyanoHABs), is critically influenced by the choice of training dataset. However, a systematic method to choose the optimal training dataset considering data history has not yet been developed. Providing a comprehensive procedure with self-based optimal training dataset-selecting algorithm would self-improve the DDM performance. In this study, a novel algorithm was developed to self-generate possible training dataset candidates from the available input and output variable data and self-choose the optimal training dataset that maximizes CyanoHAB forecasting performance. Nine years of meteorological and water quality data (input) and CyanoHAB data (output) from a site on the Nakdong River, South Korea, were acquired and pretreated via an automated process. An artificial neural network (ANN) was chosen from among the DDM candidates by first-cut training and validation using the entire collected dataset. Optimal training datasets for the ANN were self-selected from among the possible self-generated training datasets by systematically simulating the performance in response to 46 periods and 40 sizes (number of data elements) of the generated training datasets. The best-performing models were screened to identify the candidate models. The best performance corresponded to 6-7 years of training data (∼18 % lower error) for forecasting 1-28 d ahead (1-28 d of forecasting lead time (FLT)). After the hyperparameters of the screened model candidates were fine-tuned, the best-performing model (7 years of data with 14 d FLT) was self-determined by comparing the forecasts with unseen CyanoHAB events. The self-determined model could reasonably predict CyanoHABs occurring in Korean waters (cyanobacteria cells/mL ≥ 1000). Thus, our proposed method of self-optimizing the training dataset effectively improved the predictive accuracy and operational efficiency of the DDM prediction of CyanoHAB.

Water-Quality Assessment and Pollution-Risk Early-Warning System Based on Web Crawler Technology and LSTM

The openly released and measured data from automatic hydrological and water quality stations in China provide strong data support for water environmental protection management and scientific research. However, current public data on hydrology and water quality only provide real-time data through data tables in a shared page. To excavate the supporting effect of these data on water environmental protection, this paper designs a water-quality-prediction and pollution-risk early-warning system. In this system, crawler technology was used for data collection from public real-time data. Additionally, a modified long short-term memory (LSTM) was adopted to predict the water quality and provide an early warning for pollution risks. According to geographic information technology, this system can show the process of spatial and temporal variations of hydrology and water quality in China. At the same time, the current and future water quality of important monitoring sites can be quickly evaluated and predicted, together with the pollution-risk early warning. The data collected and the water-quality-prediction technique in the system can be shared and used for supporting hydrology and in water quality research and management.

Microbial community day-to-day dynamics during a spring algal bloom event in a tributary of Three Gorges Reservoir

The microbial food-loop is critical to energy flow in aquatic food webs. We tested the hypothesis that species composition and relative abundance in a microbial community would be modified by the development of toxic algal blooms either by enhanced carbon production or toxicity. This study tracked the response of the microbial community with respect to composition and relative abundance during a 7-day algal bloom event in the Three Gorges Reservoir in May 2018. Chlorophyll a biomass, microscopic identification and cell counting of algae and algal abundance (ind. L^-1) and carbon, nutrient concentrations (total phosphorus and nitrogen, dissolved total phosphorus and nitrogen), and DNA high throughput sequencing were measured daily. Algal density (1.2 × 10⁹ ind. L^-1) and Chlorophyll a (219 μg L^-1) peaked on May 20th-21st, when the phytoplankton community was dominated by Chlorella spp. and Microcystis spp. The concentrations of both dissolved total nitrogen and phosphorus declined during the bloom period. Based on DNA high throughput sequencing data, the relative abundance of eukaryotic phytoplankton, microzooplankton (20-200 μm), mesozooplankton (>200 μm), and fungal communities varied day by day while the prokaryotic community revealed a more consistent structure. Enhanced carbon production during the bloom was closely associated with increased heterotrophic microbial composition in both the prokaryotic and eukaryotic communities. A storm event, however, that caused surface cooling and deep mixing of the water column greatly modified the composition and relative abundance of species in the microbial loop. The high temporal variability and dynamics observed in this study suggest that many factors, and not just algal blooms, were interacting to determine the composition and relative abundance of species of the microbial loop.

Groundwater Quality: The Application of Artificial Intelligence

Humans and all other living things depend on having access to clean water, as it is an indispensable essential resource. Therefore, the development of a model that can predict water quality conditions in the future will have substantial societal and economic value. This can be accomplished by using a model that can predict future water quality circumstances. In this study, we employed a sophisticated artificial neural network (ANN) model. This study intends to develop a hybrid model of single exponential smoothing (SES) with bidirectional long short-term memory (BiLSTM) and an adaptive neurofuzzy inference system (ANFIS) to predict water quality (WQ) in different groundwater in the Al-Baha region of Saudi Arabia. Single exponential smoothing (SES) was employed as a preprocessing method to adjust the weight of the dataset, and the output from SES was processed using the BiLSTM and ANFIS models for predicting water quality. The data were randomly divided into two phases, training (70%) and testing (30%). Efficiency statistics were used to evaluate the SES-BiLSTM and SES-ANFIS models' prediction abilities. The results showed that while both the SES-BiLSTM and SES-ANFIS models performed well in predicting the water quality index (WQI), the SES-BiLSTM model performed best with accuracy (R = 99.95% and RMSE = 0.00910) at the testing phase, where the performance of the SES-ANFIS model was R = 99.95% and RMSE = 2.2941 × 100-07. The findings support the idea that the SES-BilSTM and SES-ANFIS models can be used to predict the WQI with high accuracy, which will help to enhance WQ. The results demonstrated that the SES-BiLSTM and SES-ANFIS models' forecasts are accurate and that both seasons' performances are consistent. Similar investigations of groundwater quality prediction for drinking purposes should benefit from the proposed SES-BiLSTM and SES-ANFIS models. Consequently, the results demonstrate that the proposed SES-BiLSTM and SES-ANFIS models are useful tools for predicting whether the groundwater in Al-Baha city is suitable for drinking and irrigation purposes.

Interpretation of ensemble learning to predict water quality using explainable artificial intelligence

Algal bloom is a significant issue when managing water quality in freshwater; specifically, predicting the concentration of algae is essential to maintaining the safety of the drinking water supply system. The chlorophyll-a (Chl-a) concentration is a commonly used indicator to obtain an estimation of algal concentration. In this study, an XGBoost ensemble machine learning (ML) model was developed from eighteen input variables to predict Chl-a concentration. The composition and pretreatment of input variables to the model are important factors for improving model performance. Explainable artificial intelligence (XAI) is an emerging area of ML modeling that provides a reasonable interpretation of model performance. The effect of input variable selection on model performance was estimated, where the priority of input variable selection was determined using three indices: Shapley value (SHAP), feature importance (FI), and variance inflation factor (VIF). SHAP analysis is an XAI algorithm designed to compute the relative importance of input variables with consistency, providing an interpretable analysis for model prediction. The XGB models simulated with independent variables selected using three indices were evaluated with root mean square error (RMSE), RMSE-observation standard deviation ratio, and Nash-Sutcliffe efficiency. This study shows that the model exhibited the most stable performance when the priority of input variables was determined by SHAP. This implies that on-site monitoring can be designed to collect the selected input variables from the SHAP analysis to reduce the cost of overall water quality analysis. The independent variables were further analyzed using SHAP summary plot, force plot, target plot, and partial dependency plot to provide understandable interpretation on the performance of the XGB model. While XAI is still in the early stages of development, this study successfully demonstrated a good example of XAI application to improve the interpretation of machine learning model performance in predicting water quality.

Prediction of Microcystis Occurrences and Analysis Using Machine Learning in High-Dimension, Low-Sample-Size and Imbalanced Water Quality Data

Machine learning, Deep learning, and water quality data have been used in recent years to predict the outbreak of harmful algae, especially Microcystis, and analyze outbreak causes. However, for various reasons, water quality data are often High-Dimension, Low-Sample- Size (HDLSS), meaning the sample size is lower than the number of dimensions. Moreover, imbalance problems may arise due to bias in the occurrence frequency of Microcystis. These problems make predicting the occurrence of Microcystis and analyzing its causes with machine learning difficult. In this study, a machine learning model that applies Feature Engineering (FE) and Feature Selection (FS) algorithms are used to predict outbreaks of Microcystis and analyze the outbreak factors from imbalanced HDLSS water quality data. The prediction performance was verified with binary classification to determine whether Microcystis would occur in the future by applying three machine learning models to four data patterns. The cause analysis of Microcystis occurrence was performed by visualizing the results of applying FE and FS. For the test data, the predictive performance of FE and FS methods was significantly better than that of the conventional method, with an accuracy of .108 points and an F-value of .691 points higher than the conventional method. A prediction performance increase was observed with a smaller model capacity. Data-driven analysis suggested that total nitrogen, chemical oxygen demand, chlorophyll-a, dissolved oxygen saturation, and water temperature are associated with Microcystis occurrences. The results also indicated that basic statistics of the water quality distribution (especially mean, standard deviation, and skewness) over a year, not the concentrations of water components, are related to the occurrence of Microcystis. These are new findings not found in previous studies and are expected to contribute significantly to future studies of algae. This study provides a method for analyzing water quality data with high-dimensionality and small samples, imbalance problems, or both.

Cyanotoxin-encoding genes as powerful predictors of cyanotoxin production during harmful cyanobacterial blooms in an inland freshwater lake: Evaluating a novel early-warning system

Freshwater harmful cyanobacterial blooms (HCBs) potentially produce excessive cyanotoxins, mainly microcystins (MCs), significantly threatening aquatic ecosystems and public health. Accurately predicting HCBs is thus essential to developing effective HCB mitigation and prevention strategies. We previously developed a novel early-warning system that uses cyanotoxin-encoding genes to predict cyanotoxin production in Harsha Lake, Ohio, USA, in 2015. In this study, we evaluated the efficacy of the early-warning system in forecasting the 2016 HCB in the same lake. We also examined potential HCB drivers and cyanobacterial community composition. Our results revealed that the cyanobacterial community was stable at the phylum level but changed dynamically at the genus level over time. Microcystis and Planktothrix were the major MC-producing genera that thrived in June and July and produced high concentrations of MCs (peak level 10.22 μg·L^-1). The abundances of the MC-encoding gene cluster mcy and its transcript levels significantly correlated with total MC concentrations (before the MC concentrations peaked) and accurately predicted MC production as revealed by logistic equations. When the Microcystis-specific gene mcyG reached approximately 1.5 × 10³ copies·mL^-1 or when its transcript level reached approximately 2.4 copies·mL^-1, total MC level exceeded 0.3 μg L^-1 (a health advisory limit) approximately one week later (weekly sampling scheme). This study suggested that cyanotoxin-encoding genes are promising predictors of MC production in inland freshwater lakes, such as Harsha Lake. The evaluated early-warning system can be a useful tool to assist lake managers in predicting, mitigating, and/or preventing HCBs.

Simultaneous feature engineering and interpretation: Forecasting harmful algal blooms using a deep learning approach

Routine monitoring for harmful algal blooms (HABs) is generally undertaken at low temporal frequency (e.g., weekly to monthly) that is unsuitable for capturing highly dynamic variations in cyanobacteria abundance. Therefore, we developed a model incorporating reverse time attention with a decay mechanism (RETAIN-D) to forecast HABs with simultaneous improvements in temporal resolution, forecasting performance, and interpretability. The usefulness of RETAIN-D in forecasting HABs was illustrated by its application to two sites located in the lower sections of the Nakdong and Yeongsan rivers, South Korea, where HABs pose a critical water quality issue. Three variations of recurrent neural network models, i.e., long short-term memory (LSTM), gated recurrent unit (GRU), and reverse time attention (RETAIN), were adopted for comparisons of performance with RETAIN-D. Input features encompassing meteorological, hydrological, environmental, and biological factors were used to forecast cyanobacteria abundance (total cyanobacteria cell counts and cell counts of dominant cyanobacteria taxa). Incorporation of a decay mechanism into the deep learning structure in RETAIN-D allowed forecasts of HABs on a high temporal resolution (daily) without manual feature engineering, increasing the usefulness of resulting forecasts for water quality and resources management. RETAIN-D yielded a high degree of accuracy (RMSE = 0.29-1.67, R² = 0.76-0.98, MAE = 0.18-1.14, SMAPE = 9.77-87.94% for test sets; on natural log scales) across model outputs and sites, successfully capturing high variability and irregularities in the time series. RETAIN-D showed higher accuracy than RETAIN (except for comparable accuracy in forecasting Microcystis abundance at the Nakdong River site) and outperformed LSTM and GRU across all model outputs and sites. Ambient temperature had high importance in forecasting cyanobacteria abundance across all model outputs and sites, whereas the relative importance of other input features varied by the output and site. Increases in contributions with increasing irradiance, decreasing flow rates, and increasing residence time were more pronounced in summer than other seasons. Differences in the contributions of input features among different time steps (1 to 7 days prior to forecasting) were larger in the Yeongsan River site. RETAIN-D is applicable to a wide range of forecasting models that can benefit from improved temporal resolution, performance, and interpretability.

An Improved Transfer Learning Model for Cyanobacterial Bloom Concentration Prediction

The outbreak of cyanobacterial blooms is a serious water environmental problem, and the harm it brings to aquatic ecosystems and water supply systems cannot be underestimated. It is very important to establish an accurate prediction model of cyanobacterial bloom concentration, which is a challenging issue. Machine learning techniques can improve the prediction accuracy, but a large amount of historical monitoring data is needed to train these models. For some waters with an inconvenient geographical location or frequent sensor failures, there are not enough historical data to train the model. To deal with this problem, a fused model based on a transfer learning method is proposed in this paper. In this study, the data of water environment with a large amount of historical monitoring data are taken as the source domain in order to learn the knowledge of cyanobacterial bloom growth characteristics and train the prediction model. The data of the water environment with a small amount of historical monitoring data are taken as the target domain in order to load the model trained in the source domain. Then, the training set of the target domain is used to participate in the inter-layer fine-tuning training of the model to obtain the transfer learning model. At last, the transfer learning model is fused with a convolutional neural network to obtain the prediction model. Various experiments are conducted for a 2 h prediction on the test set of the target domain. The results show that the proposed model can significantly improve the prediction accuracy of cyanobacterial blooms for the water environment with a low data volume.

Towards Synoptic Water Monitoring Systems: A Review of AI Methods for Automating Water Body Detection and Water Quality Monitoring Using Remote Sensing

Water features (e.g., water quantity and water quality) are one of the most important environmental factors essential to improving climate-change resilience. Remote sensing (RS) technologies empowered by artificial intelligence (AI) have become one of the most demanded strategies to automating water information extraction and thus intelligent monitoring. In this article, we provide a systematic review of the literature that incorporates artificial intelligence and computer vision methods in the water resources sector with a focus on intelligent water body extraction and water quality detection and monitoring through remote sensing. Based on this review, the main challenges of leveraging AI and RS for intelligent water information extraction are discussed, and research priorities are identified. An interactive web application designed to allow readers to intuitively and dynamically review the relevant literature was also developed.

Long-term prediction of sea surface chlorophyll-a concentration based on the combination of spatio-temporal features

Harmful algal blooms (HABs) events have a serious impact on marine fisheries and marine management. They occur globally with high frequency and are characterized by a long duration and difficult governance. HABs incidents have occurred in the South China Sea (SCS), and the frequency of occurrence has been on the rise in recent decades. Predicting the long-term chlorophyll-a (Chl-a) concentration has the potential to facilitate long-term monitoring and early warning of HABs events. Currently, long-term predictions of ocean circulation and temperature are common, while long-term predictions of marine biochemistry are still in their infancy. Traditional Chl-a prediction methods have problems, such as low accuracy and the inability to carry out long-term predictions. This research improved the CNN-LSTM model by combining spatio-temporal features to predict Chl-a concentrations. This model can extract both the temporal and spatial features of Chl-a, expand the dataset, and improve the prediction accuracy and training speed. The predictions were made using a Chl-a dataset for the Reed Tablemount in the SCS. The time series of Chl-a used was the satellite data of NASA's official website from January 2002 to June 2020. The results indicate that the predictions of the CNN-LSTM model are better than those of the LSTM and SARIMA models. The five-year long-term rolling prediction of Chl-a was carried out, and the three-year Pearson correlation coefficient reached 0.5. The novelty of this study is the realization of a three-year long-term prediction of Chl-a concentrations. The Mann-Kendall trend test method and the least square method were used to fit the straight line to detect the trend of the five-year predicted value and the true value, respectively. The results indicated that the prediction value and true value of the sea surface Chl-a from 2015 to 2020 both exhibited an overall upward trend. In addition, the prediction performance of the model in large-scale prediction is better than that in small-scale prediction.

Convolution Neural Network for the Prediction of Cochlodinium polykrikoides Bloom in the South Sea of Korea

In this study, the occurrence of Cochlodinium polykrikoides bloom was predicted based on spatial information. The South Sea of Korea (SSK), where C. polykrikoides bloom occurs every year, was divided into three concentrated areas. For each domain, the optimal model configuration was determined by designing a verification experiment with 1–3 convolutional neural network (CNN) layers and 50–300 training times. Finally, we predicted the occurrence of C. polykrikoides bloom based on 3 CNN layers and 300 training times that showed the best results. The experimental results for the three areas showed that the average pixel accuracy was 96.22%, mean accuracy was 91.55%, mean IU was 81.5%, and frequency weighted IU was 84.57%, all of which showed above 80% prediction accuracy, indicating the achievement of appropriate performance. Our results show that the occurrence of C. polykrikoides bloom can be derived from atmosphere and ocean forecast information.

Application of Machine Learning for eutrophication analysis and algal bloom prediction in an urban river: A 10-year study of the Han River, South Korea

The increasing release of nutrients to aquatic environments has led to great concern regarding eutrophication and the risk of unwanted algal blooms. Based on observational data of 20 water quality parameters measured on a monthly basis at 40 stations from 2011 to 2020, this study applied different Machine Learning (ML) algorithms to suggest the best option for algal bloom prediction in the Han River, a large river in South Korea. Eight different ML algorithms were categorized into several groups of statistical learning, regression family, and deep learning, and were then compared for their suitability to predict the chlorophyll-derived trophic index (TSI-Chla). ML algorithms helped identify the most important water quality parameters contributing to algal bloom prediction. The ML results confirmed that eutrophication and algal proliferation were governed by the complex interplay between nutrients (nitrogen and phosphorus), organic contaminants, and environmental factors. Of the models tested, the adaptive neuro-fuzzy inference system (ANFIS) exhibited the best performance owing to its consistent and outperforming prediction both quantitatively (i.e., via regression) and qualitatively (i.e., via classification), which was evidenced by the lowest value of mean absolute error (MAE) of 0.09, and the highest F1-score, Recall and Precision of 0.97, 0.98 and 0.96, respectively. In a further step, a representative web application was constructed to assist common users to predict the trophic status of the Han River. This study demonstrated that ML techniques are not only promising for highly accurate water quality modeling of urban rivers, but also reduce time and labor intensity for experiments, which decreases the number of monitored water quality parameters, providing further insights into the driving factors of water quality deterioration. They ultimately help devise proactive strategies for sustainable water management.

Prediction of harmful algal blooms in large water bodies using the combined EFDC and LSTM models

Harmful algal blooms (HABs) is a worldwide water environmental problem. HABs usually happens in short time and is difficult to be controlled. Early warning of HABs using data-driven models is prospective in making time for taking precaution against HABs. High-frequency water quality monitoring data are necessary to improve the reliability of the model, but it is expensive. This research used environmental fluid dynamics code (EFDC) to extend one-point data obtained by only one instrument to the whole 249 ha water area instead of multi-instruments monitoring, followed by Long short-term memory (LSTM) to predict the HABs in the whole water body. Correlation analysis and principal component analysis were used to reduce the data dimension and improve model accuracy. Finally, the LSTM model was calibrated to predict chlorophyll-a (Chl-a) for the next 1 to 3 time steps. The Nash-Sutcliffe efficiency coefficient (NSE) and mean absolute percentage error (MAPE) of EFDC-LSTM were 0.797-0.991 and 2.74-13.16%, respectively, suggesting the promising utilization of this model in early warning systems for HABs. EFDC-LSTM achieves high-precision HABs forecasting in a cost-effective manner, providing a reliable way to detect HABs in advance.

A Remote Sensing and Machine Learning-Based Approach to Forecast the Onset of Harmful Algal Bloom

In the last few decades, harmful algal blooms (HABs, also known as “red tides”) have become one of the most detrimental natural phenomena in Florida’s coastal areas. Karenia brevis produces toxins that have harmful effects on humans, fisheries, and ecosystems. In this study, we developed and compared the efficiency of state-of-the-art machine learning models (e.g., XGBoost, Random Forest, and Support Vector Machine) in predicting the occurrence of HABs. In the proposed models the K. brevis abundance is used as the target, and 10 level-02 ocean color products extracted from daily archival MODIS satellite data are used as controlling factors. The adopted approach addresses two main shortcomings of earlier models: (1) the paucity of satellite data due to cloudy scenes and (2) the lag time between the period at which a variable reaches its highest correlation with the target and the time the bloom occurs. Eleven spatio-temporal models were generated, each from 3 consecutive day satellite datasets, with a forecasting span from 1 to 11 days. The 3-day models addressed the potential variations in lag time for some of the temporal variables. One or more of the generated 11 models could be used to predict HAB occurrences depending on availability of the cloud-free consecutive days. Findings indicate that XGBoost outperformed the other methods, and the forecasting models of 5–9 days achieved the best results. The most reliable model can forecast eight days ahead of time with balanced overall accuracy, Kappa coefficient, F-Score, and AUC of 96%, 0.93, 0.97, and 0.98 respectively. The euphotic depth, sea surface temperature, and chlorophyll-a are always among the most significant controlling factors. The proposed models could potentially be used to develop an “early warning system” for HABs in southwest Florida.

Assessing the Performance of Deep Learning Algorithms for Short-Term Surface Water Quality Prediction

This study aimed to investigate the applicability of deep learning algorithms to (monthly) surface water quality forecasting. A comparison was made between the performance of an autoregressive integrated moving average (ARIMA) model and four deep learning models. All prediction algorithms, except for the ARIMA model working on a single variable, were tested with univariate inputs consisting of one of two dependent variables as well as multivariate inputs containing both dependent and independent variables. We found that deep learning models (6.31–18.78%, in terms of the mean absolute percentage error) showed better performance than the ARIMA model (27.32–404.54%) in univariate data sets, regardless of dependent variables. However, the accuracy of prediction was not improved for all dependent variables in the presence of other associated water quality variables. In addition, changes in the number of input variables, sliding window size (i.e., input and output time steps), and relevant variables (e.g., meteorological and discharge parameters) resulted in wide variation of the predictive accuracy of deep learning models, reaching as high as 377.97%. Therefore, a refined search identifying the optimal values on such influencing factors is recommended to achieve the best performance of any deep learning model in given multivariate data sets.

LSTM Networks to Improve the Prediction of Harmful Algal Blooms in the West Coast of Sabah

Harmful algal bloom (HAB) events have alarmed authorities of human health that have caused severe illness and fatalities, death of marine organisms, and massive fish killings. This work aimed to perform the long short-term memory (LSTM) method and convolution neural network (CNN) method to predict the HAB events in the West Coast of Sabah. The results showed that this method could be used to predict satellite time series data in which previous studies only used vector data. This paper also could identify and predict whether there is HAB occurrence in the region. A chlorophyll a concentration (Chl-a; mg/L) variable was used as an HAB indicator, where the data were obtained from MODIS and GEBCO bathymetry. The eight-day dataset interval was from January 2003 to December 2018. The results obtained showed that the LSTM model outperformed the CNN model in terms of accuracy using RMSE and the correlation coefficient r as the statistical criteria.

Developing a Novel Water Quality Prediction Model for a South African Aquaculture Farm

Providing an accurate prediction of water quality parameters for improved water quality management is a topical issue in the aquaculture industry. Conventional prediction methods have shown different challenges like a poor generalization, poor prediction accuracy, and high time complexity. Aiming at these challenges, a novel hybrid prediction model with ensemble empirical mode decomposition (EEMD) and deep learning (DL) long-short term memory (LSTM) neural network is proposed in this paper. In this innovative hybrid EEMD-DL-LSTM model, firstly, the integrity of the datasets is enhanced by applying moving average filtering and linear interpolation techniques of water quality parameter datasets pre-treatment. Secondly, the measured real sensor water quality parameters dataset is decomposed with the aid of the EEMD algorithm into disparate IMFs and a corresponding residual item. Thirdly, a multi-feature selection process is applied to make a careful selection of a strongly correlated group of IMFs with the measured real water quality parameter datasets and integrate them as inputs to the DL-LSTM neural network. The presented model is built on water quality sensor data collected from an Abalone farm in South Africa. The performance of the novel hybrid prediction model is validated by comparing the results against the real datasets. To measure the overall accuracy of the novel hybrid prediction model, different statistical indices, namely the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE), are used.

Estimation of the Chlorophyll-A Concentration of Algae Species Using Electrical Impedance Spectroscopy

Algae are a significant component of a biological monitoring program in an aquatic ecosystem. They are ideally suited for water quality assessments because of their nutrient requirements, rapid reproduction rate, and very short life cycle. Algae composition and temporal variation in abundances are important in determining the trophic level of lakes, and those can be estimated by the Chlorophyll-a (Chl-a) concentration of the species. In this work, a non-destructive method was employed to estimate the Chlorophyll-a concentration of multiple algae species using electrical impedance spectroscopy (EIS). The proposed EIS method is rapid, cheaper, and suitable for in situ measurements compared with the other available non-destructive methods, such as spectrophotometry and hyperspectral or multispectral imaging. The electrical impedances in different frequencies ranging from 1 to 100 kHz were observed using an impedance converter system. Significant observations were identified within 3.5 kHz for multiple algae species and therefore reported in the results. A positive correlation was found between the Chlorophyll-a and the measured impedance of algae species at different frequencies. Later, EIS models were developed for the species in 1–3.5 kHz. A correlation of 90% was found by employing a least squares method and multiple linear regression. The corresponding coefficients of determination were obtained as 0.9, 0.885, and 0.915, respectively for 49 samples of Spirulina, 41 samples of Chlorella, and 26 samples of mixed algae species. The models were later validated using a new and separate set of samples of algae species.

A Review of Recent Machine Learning Advances for Forecasting Harmful Algal Blooms and Shellfish Contamination

Harmful algal blooms (HABs) are among the most severe ecological marine problems worldwide. Under favorable climate and oceanographic conditions, toxin-producing microalgae species may proliferate, reach increasingly high cell concentrations in seawater, accumulate in shellfish, and threaten the health of seafood consumers. There is an urgent need for the development of effective tools to help shellfish farmers to cope and anticipate HAB events and shellfish contamination, which frequently leads to significant negative economic impacts. Statistical and machine learning forecasting tools have been developed in an attempt to better inform the shellfish industry to limit damages, improve mitigation measures and reduce production losses. This study presents a synoptic review covering the trends in machine learning methods for predicting HABs and shellfish biotoxin contamination, with a particular focus on autoregressive models, support vector machines, random forest, probabilistic graphical models, and artificial neural networks (ANN). Most efforts have been attempted to forecast HABs based on models of increased complexity over the years, coupled with increased multi-source data availability, with ANN architectures in the forefront to model these events. The purpose of this review is to help defining machine learning-based strategies to support shellfish industry to manage their harvesting/production, and decision making by governmental agencies with environmental responsibilities.

Water Quality Prediction Using Artificial Intelligence Algorithms

During the last years, water quality has been threatened by various pollutants. Therefore, modeling and predicting water quality have become very important in controlling water pollution. In this work, advanced artificial intelligence (AI) algorithms are developed to predict water quality index (WQI) and water quality classification (WQC). For the WQI prediction, artificial neural network models, namely nonlinear autoregressive neural network (NARNET) and long short-term memory (LSTM) deep learning algorithm, have been developed. In addition, three machine learning algorithms, namely, support vector machine (SVM), K-nearest neighbor (K-NN), and Naive Bayes, have been used for the WQC forecasting. The used dataset has 7 significant parameters, and the developed models were evaluated based on some statistical parameters. The results revealed that the proposed models can accurately predict WQI and classify the water quality according to superior robustness. Prediction results demonstrated that the NARNET model performed slightly better than the LSTM for the prediction of the WQI values and the SVM algorithm has achieved the highest accuracy (97.01%) for the WQC prediction. Furthermore, the NARNET and LSTM models have achieved similar accuracy for the testing phase with a slight difference in the regression coefficient (RNARNET = 96.17% and RLSTM = 94.21%). This kind of promising research can contribute significantly to water management.

A comprehensive review of deep learning applications in hydrology and water resources

The global volume of digital data is expected to reach 175 zettabytes by 2025. The volume, variety and velocity of water-related data are increasing due to large-scale sensor networks and increased attention to topics such as disaster response, water resources management, and climate change. Combined with the growing availability of computational resources and popularity of deep learning, these data are transformed into actionable and practical knowledge, revolutionizing the water industry. In this article, a systematic review of literature is conducted to identify existing research that incorporates deep learning methods in the water sector, with regard to monitoring, management, governance and communication of water resources. The study provides a comprehensive review of state-of-the-art deep learning approaches used in the water industry for generation, prediction, enhancement, and classification tasks, and serves as a guide for how to utilize available deep learning methods for future water resources challenges. Key issues and challenges in the application of these techniques in the water domain are discussed, including the ethics of these technologies for decision-making in water resources management and governance. Finally, we provide recommendations and future directions for the application of deep learning models in hydrology and water resources.

Advances in forecasting harmful algal blooms using machine learning models: A case study with Planktothrix rubescens in Lake Geneva

The development of anthropic activities during the 20th century increased the nutrient fluxes in freshwater ecosystems, leading to the eutrophication phenomenon that most often promotes harmful algal blooms (HABs). Recent years have witnessed the regular and massive development of some filamentous algae or cyanobacteria in Lake Geneva. Consequently, important blooms could result in detrimental impacts on economic issues and human health. In this study, we tried to lay the foundation of an HAB forecast model to help scientists and local stakeholders with the present and future management of this peri-alpine lake. Our forecast strategy was based on pairing two machine learning models with a long-term database built over the past 34 years. We created HAB groups via a K-means model. Then, we introduced different lag times in the input of a random forest (RF) model, using a sliding window. Finally, we used a high-frequency dataset to compare the natural mechanisms with numerical interaction using individual conditional expectation plots. We demonstrate that some HAB events can be forecasted over a year scale. The information contained in the concentration data of the cyanobacteria was synthesized in the form of four intensity groups that directly depend on the P. rubescens concentration. The categorical transformation of these data allowed us to obtain a forecast with correlation coefficients that stayed above a threshold of 0.5 until one year for the counting cells and two years for the biovolume data. Moreover, we found that the RF model predicted the best P. rubescens abundance for water temperatures around 14°C. This result is consistent with the biological processes of the toxic cyanobacterium. In this study, we found that the coupling between K-means and RF models could help in forecasting the development of the bloom-forming P. rubescens in Lake Geneva. This methodology could create a numerical decision support tool, which should be a significant advantage for lake managers.

River algal blooms are well predicted by antecedent environmental conditions

River algal blooms have become a challenging environmental problem worldwide due to strong interference of human activities and megaprojects (e.g., big dams and large-scale water transfer projects). Previous studies on algal blooms were mainly focused on relatively static water bodies (i.e., lakes and reservoirs), but less on the large rivers. As the largest tributary of the Yangtze River of China and the main freshwater source of the South-to-North Water Diversion Project (SNWDP), the Han River has experienced frequent algal blooms in recent decades. Here we investigated the algal blooms during a decade (2003-2014) in the Han River by two gradient boosting machine (GBM) models with k-fold cross validation, which used explanatory variables from current 10-day (GBMc model) or previous 10-day period (GBMp model). Our results advocate the use of GBMp due to its higher accuracy (median Kappa = 0.9) and practical predictability (using antecedent observations) compared to GBMc. We also revealed that the algal blooms in the Han River were significantly modulated by antecedent water levels in the Han River and the Yangtze River and water level variation in the Han River, whereas the nutrient concentrations in the Han River were usually above thresholds and not limiting algal blooms. This machine-learning-based study potentially provides scientific guidance for preemptive warning and risk management of river algal blooms through comprehensive regulation of water levels during the dry season by making use of water conservancy measures in large rivers.

Mapping Freshwater Chlorophyll-a Concentrations at a Regional Scale Integrating Multi-Sensor Satellite Observations with Google Earth Engine

Monitoring harmful algal blooms (HABs) in freshwater over regional scales has been implemented through mapping chlorophyll-a (Chl-a) concentrations using multi-sensor satellite remote sensing data. Cloud-free satellite measurements and a sufficient number of matched-up ground samples are critical for constructing a predictive model for Chl-a concentration. This paper presents a methodological framework for automatically pairing surface reflectance values from multi-sensor satellite observations with ground water quality samples in time and space to form match-up points, using the Google Earth Engine cloud computing platform. A support vector machine model was then trained using the match-up points, and the prediction accuracy of the model was evaluated and compared with traditional image processing results. This research demonstrates that the integration of multi-sensor satellite observations through Google Earth Engine enables accurate and fast Chl-a prediction at a large regional scale over multiple years. The challenges and limitations of using and calibrating multi-sensor satellite image data and current and potential solutions are discussed.

Deep learning for predicting the occurrence of cardiopulmonary diseases in Nanjing, China

The efficiency of disease prevention and medical care service necessitated the prediction of incidence. However, predictive accuracy and power were largely impeded in a complex system including multiple environmental stressors and health outcome of which the occurrence might be episodic and irregular in time. In this study, we established four different deep learning (DL) models to capture inherent long-term dependencies in sequences and potential complex relationships among constituents by initiating with the original input into a representation at a higher abstract level. We collected 504,555 and 786,324 hospital outpatient visits of grouped categories of respiratory (RESD) and circulatory system disease (CCD), respectively, in Nanjing from 2013 through 2018. The matched observations in time-series that might pose risk to cardiopulmonary health involved conventional air pollutants concentrations and metrological conditions. The results showed that a well-trained network architecture built upon long short-term memory block and a working day enhancer achieved optimal performance by three quantitative statistics, i.e., 0.879 and 0.902 of Nash-Sutcliffe efficiency, 0.921% and 0.667% of percent bias, and 0.347 and 0.312 of root mean square error-standard deviation ratio for RESD and CCD hospital visits, respectively. We observed the non-linear association of nitrogen dioxide and ambient air temperature with CCD hospital visits. Furthermore, these two environmental stressors were identified as the most sensitive predictive variables, and exerted synergetic effect for two health outcomes, particular in winter season. Our study indicated that high-quality surveillance data of atmospheric environments could provide novel opportunity for anticipating temporal trend of cardiopulmonary health outcomes based on DL model.

Prediction of Chlorophyll-a Concentrations in the Nakdong River Using Machine Learning Methods

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.

Recent Advances in Information and Communications Technology (ICT) and Sensor Technology for Monitoring Water Quality

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.

Water quality prediction based on recurrent neural network and improved evidence theory: a case study of Qiantang River, China

Water quality prediction is an effective method for managing and protecting water resources by providing an early warning against water quality deterioration. In general, the existing water quality prediction methods are based on a single shallow model which fails to capture the long-term dependence in historical time series and is more likely to cause a high rate of false alarms and false negatives in practical water monitoring application. To resolve these problems, a new model combining recurrent neural network (RNN) with improved Dempster/Shafer (D-S) evidence theory (RNNs-DS) is proposed in this paper. Among them, the RNNs which can handle the long-term dependence in historical time series effectively are used to realize the preliminary prediction of water quality. And the improved D-S evidence theory is used to synthesize the prediction results of RNNs. In addition, an improved strategy based on correlation analysis method is presented for evidence theory to obtain the number of evidence, which reduces uncertainty in evidence selection effectively. Besides, a new basic probability assignment function which based on modified softmax function is proposed. The new function can effectively solve the problems of weight allocation failure in the traditional function. Then, data about permanganate index, pH, total phosphorus, and dissolved oxygen from Jiuxishuichang monitoring station near Qiantang River, Zhejiang Province, China is used to verify the proposed model. Compared with support vector regression (SVR) and backpropagation neural network (BPNN) and three RNN models, the new model shows higher accuracy and better stability as indicated by four indices. Finally, the engineering application of the RNNs-DS algorithm has been realized on the self-developed water environmental monitoring and forecasting system, which can provide effective support for early risk assessment and prevention in water environment.

Synergy of ICESat-2 and Landsat for Mapping Forest Aboveground Biomass with Deep Learning

Spatially continuous estimates of forest aboveground biomass (AGB) are essential to supporting the sustainable management of forest ecosystems and providing invaluable information for quantifying and monitoring terrestrial carbon stocks. The launch of the Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) on September 15th, 2018 offers an unparalleled opportunity to assess AGB at large scales using along-track samples that will be provided during its three-year mission. The main goal of this study was to investigate deep learning (DL) neural networks for mapping AGB with ICESat-2, using simulated photon-counting lidar (PCL)-estimated AGB for daytime, nighttime, and no noise scenarios, Landsat imagery, canopy cover, and land cover maps. The study was carried out in Sam Houston National Forest located in south-east Texas, using a simulated PCL-estimated AGB along two years of planned ICESat-2 profiles. The primary tasks were to investigate and determine neural network architecture, examine the hyper-parameter settings, and subsequently generate wall-to-wall AGB maps. A first set of models were developed using vegetation indices calculated from single-date Landsat imagery, canopy cover, and land cover, and a second set of models were generated using metrics from one year of Landsat imagery with canopy cover and land cover maps. To compare the effectiveness of final models, comparisons with Random Forests (RF) models were made. The deep neural network (DNN) models achieved R2 values of 0.42, 0.49, and 0.50 for the daytime, nighttime, and no noise scenarios respectively. With the extended dataset containing metrics calculated from Landsat images acquired on different dates, substantial improvements in model performance for all data scenarios were noted. The R2 values increased to 0.64, 0.66, and 0.67 for the daytime, nighttime, and no noise scenarios. Comparisons with Random forest (RF) prediction models highlighted similar results, with the same R2 and root mean square error (RMSE) range (15–16 Mg/ha) for daytime and nighttime scenarios. Findings suggest that there is potential for mapping AGB using a combinatory approach with ICESat-2 and Landsat-derived products with DL.

Development and evaluation of a deep learning approach for modeling seasonality and trends in hand-foot-mouth disease incidence in mainland China

The high incidence, seasonal pattern and frequent outbreaks of hand, foot, and mouth disease (HFMD) represent a threat for millions of children in mainland China. And advanced response is being used to address this. Here, we aimed to model time series with a long short-term memory (LSTM) based on the HFMD notified data from June 2008 to June 2018 and the ultimate performance was compared with the autoregressive integrated moving average (ARIMA) and nonlinear auto-regressive neural network (NAR). The results indicated that the identified best-fitting LSTM with the better superiority, be it in modeling dataset or two robustness tests dataset, than the best-conducting NAR and seasonal ARIMA (SARIMA) methods in forecasting performances, including the minimum indices of root mean square error, mean absolute error and mean absolute percentage error. The epidemic trends of HFMD remained stable during the study period, but the reported cases were even at significantly high levels with a notable high-risk seasonality in summer, and the incident cases projected by the LSTM would still be fairly high with a slightly upward trend in the future. In this regard, the LSTM approach should be highlighted in forecasting the epidemics of HFMD, and therefore assisting decision makers in making efficient decisions derived from the early detection of the disease incidents.