A risk assessment method for remote sensing of cyanobacterial blooms in inland waters

Spatiotemporal dynamics of cyanobacterial blooms: Integrating machine learning and feature selection techniques with uncrewed aircraft systems and autonomous surface vessel data

Cyanobacterial blooms pose significant threats to aquatic ecosystems and public health due to their ability to release harmful toxins, degrade water quality, disrupt aquatic habitats, and endanger human and animal health through contact or consumption of contaminated water. Monitoring phycocyanin (PC), a pigment unique to cyanobacteria, offers a reliable method for detecting and quantifying these blooms, enabling timely interventions to mitigate their impacts. This study aimed to evaluate ten machine learning algorithms (MLAs) for assessing the spatiotemporal variations of cyanobacterial concentrations over an oyster reef in the Western Mississippi Sound (WMS) using remotely sensed imagery from uncrewed aircraft systems (UAS) and in-situ PC concentrations measured by an autonomous surface vessel (ASV). The study further investigated the influence of river discharge and climatic variables on cyanobacterial concentrations using a time-series of cyanobacteria maps. To derive the most accurate PC retrieval model, a comprehensive set of 85 features was initially generated, including individual spectral bands, band ratios, multiple vegetation indices, and three-band indices. Feature selection was performed using a two-step approach that combined Sequential Backward Floating Selection (SBFS) and Exhaustive Feature Selection (EFS). SBFS was first used to iteratively remove features and optimize model performance, while EFS evaluated all possible combinations of the features identified by SBFS to select the best subset. Among the ten MLAs tested, Extreme Gradient Boosting emerged as the top-performing model, achieving an R2 of 0.835, a root mean square deviation of 0.419 μg/l, an unbiased mean absolute relative difference of 0.176 μg/l, and an average percentage difference of 18.072 % in retrieving PC concentration. The novelty of this study lies in its data-driven approach to identifying the most suitable machine learning algorithm and feature subsets for PC retrieval, thereby enhancing the accuracy and robustness of the developed algorithm. The time-series analysis revealed substantial variations in cyanobacterial concentration in the WMS from 2018 to 2022. The highest average concentration occurred in 2019, coinciding with the introduction of diverted Mississippi River water through the Bonnet Carré Spillway, which triggered an unprecedented cyanobacterial bloom. Furthermore, the average PC concentration was consistently higher during the summer months, likely due to elevated air temperatures and increased sunlight promoting cyanobacterial growth. The methodology developed in this study improves the quantitative monitoring of cyanobacterial blooms using UAS imagery and provides valuable insights for future water quality monitoring initiatives in other regions.

Identifying factors influencing reservoir eutrophication using interpretable machine learning combined with shoreline morphology and landscape hydrological features: A case study of Danjiangkou Reservoir, China

Reservoir nearshore areas are influenced by both terrestrial and aquatic ecosystems, making them sensitive regions to water quality changes. The analysis of basin landscape hydrological features provides limited insight into the spatial heterogeneity of eutrophication in these areas. The complex characteristics of shoreline morphology and their impact on eutrophication are often overlooked. To comprehensively analyze the complex relationships between shoreline morphology and landscape hydrological features, with eutrophication, this study uses Danjiangkou Reservoir as a case study. Utilizing Landsat 8 OLI remote sensing data from 2013 to 2022, combined with a semi-analytical approach, the spatial distribution of the Trophic State Index (TSI) during flood discharge periods (FDPs) and water storage periods (WSPs) was obtained. Using Extreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP), explained the relationships between landscape composition, landscape configuration, hydrological topography, shoreline morphology, and TSI, identified key factors at different spatial scales and validated their reliability. The results showed that: (1) There is significant spatial heterogeneity in the TSI distribution of Danjiangkou Reservoir. The eutrophication levels are significant in the shoreline and bay areas, with a tendency to extend inward only during the WSPs. (2) The importance of landscape composition, landscape configuration, hydrological topography, and shoreline morphology to TSI variations during the FDPs are 25.12 %, 29.6 %, 23.09 %, and 22.19 % respectively. Besides shoreline distance, the Landscape Shape Index (LSI) and Hypsometric Integral (HI) are the two most significant environmental variables overall during the FDPs. Forest and grassland areas become the most influential factors during the WSPs. The influence of landscape patterns and hydrological topography on TSI varies at different spatial scales. At the 200 m riparian buffer zone, the increase in cropland and impervious areas significantly elevates eutrophication levels. (3) Morphology complexity, shows a noticeable threshold effect on TSI, with complex shoreline morphology increasing the risk of eutrophication.

Predicting and analyzing the algal population dynamics of a grass-type lake with explainable machine learning

Algal blooms, exacerbated by climate change and eutrophication, have emerged as a global concern. In this study, we introduce a novel interpretable machine learning (ML) workflow tailored for investigating the dynamics of algal populations in grass-type lakes, Liangzi lake. Utilizing seven ML methods and incorporating the covariance matrix adaptation evolution strategy (CMA-ES), we predict algal density across three distinct time periods, resulting in the construction of a total of 30 ML models. The CMA-ES-CatBoost model consistently demonstrates superior predictive accuracy and generalization capability across these periods. Through the collective validation of various interpretable tools, we identify water temperature and permanganate index as the two most critical water quality parameters (WQIs) influencing algal density in Liangzi Lake. Additionally, we quantify the independent and interactive effects of WQIs on algal density, pinpointing key thresholds and trends. Furthermore, we determine the minimum combination of WQIs that achieves near-optimal predictive performance, striking a balance between accuracy and cost-effectiveness. These findings offer a scientific and economically efficient foundation for governmental agencies to formulate strategies for water quality management and sustainable development.

A Digital Twin Lake Framework for Monitoring and Management of Harmful Algal Blooms

Harmful algal blooms (HABs) caused by lake eutrophication and climate change have become one of the most serious problems for the global water environment. Timely and comprehensive data on HABs are essential for their scientific management, a need unmet by traditional methods. This study constructed a novel digital twin lake framework (DTLF) aiming to integrate, represent and analyze multi-source monitoring data on HABs and water quality, so as to support the prevention and control of HABs. In this framework, different from traditional research, browser-based front ends were used to execute the video-based HAB monitoring process, and real-time monitoring in the real sense was realized. On this basis, multi-source monitored results of HABs and water quality were integrated and displayed in the constructed DTLF, and information on HABs and water quality can be grasped comprehensively, visualized realistically and analyzed precisely. Experimental results demonstrate the satisfying frequency of video-based HAB monitoring (once per second) and the valuable results of multi-source data integration and analysis for HAB management. This study demonstrated the high value of the constructed DTLF in accurate monitoring and scientific management of HABs in lakes.

Microcystins risk assessment in lakes from space: Implications for SDG 6.1 evaluation

Cyanobacterial blooms release a large number of algal toxins (e.g., Microcystins, MCs) and seriously threaten the safety of drinking water sources what the SDG 6.1 pursues (to provide universal access to safe drinking water by 2030, United Nations Sustainable Development Goal). Nevertheless, algal toxins in lake water have not been routinely monitored and evaluated well and frequently so far. In this study, a total of 100 large lakes (>25 km2) in densely populated eastern China were studied, and a remote sensing scheme of human health risks from MCs based on Sentinel-3 OLCI data was developed. The spatial and temporal dynamics of MCs risk in eastern China lakes since OLCI satellite observation data (2016-2021) were first mapped. The results showed that most of the large lakes in eastern China (80 out of 100) were detected with the occurrence of a high risk of more than 1 pixel (300×300 m) at least once. Fortunately, in terms of lake areas, the frequency of high human health risks in most waters (70.93% of total lake areas) was as less as 1%. This indicates that drinking water intakes can be set in most waters from the perspective of MCs, yet the management departments are required to reduce cyanobacterial blooms. This study highlights the potential of satellite in monitoring and assessing the risk of algal toxins and ensuring drinking water safety. It is also an important reference for SDG 6.1 reporting for lakes that lack routine monitoring.

Flow backward alleviated the river algal blooms

Mechanistic understanding and prediction of river algal blooms remain challenging. It is generally believed that these blooms are formed by the slowdown of water dynamics in tributaries due to the support of the main stream. However, few studies have investigated the impact of flow backward caused by the difference in water dynamics between the main stream and tributaries. Here, we focus on the eutrophication issue in the middle-lower reaches of the Han River, which is affected by the Middle Route of the South-to-North Water Diversion Project (SNWDP), the largest inter-basin water transfer project in Asia. We discover that the reversal of the Yangtze River water level could effectively alleviate the occurrence of Han River water blooms. The Yangtze River frequently back flows into the lower reaches of the Han River, with the probability of such events increasing as it nears the confluence (20 km from the Yangtze: 9.5 %, 10 km: 19.0 %, 8 km: 28.6 %). This flow backward carries nutrients that reduce the nitrogen to phosphorus ration (N:P), leading to a shift in the nutrient structure of the Han River. This change is concomitant with a significant decline in algae biomass (Chlorophyll-a = 11.19 µg·L-1 and algae density = 0.41×107 cells·L-1 under natural flow, Chlorophyll-a = 5.19 µg·L-1 and algae density = 0.18×107 cells·L-1 under flow backward), as well as a weakening of the correlation (R) between diatom density and chlorophyll-a concentration, i.e., R = 0.38 (p>0.05) under flow backward conditions versus R = 0.72 (p<0.01) under natural flow conditions. As phosphorus limitation typically suppresses algae growth, the correlation between diatom density and chlorophyll-a concentration can help to reveal the dominance of diatoms, with stronger correlations indicating greater diatom dominance. Consequently, our study provides evidence that the flow backward can alleviate river algal blooms by weakening the growth advantage of diatoms. This study could prove valuable in investigating the eutrophication mechanism within the complex hydrodynamic conditions of rivers. SYNOPSIS: Flow backward caused by the water level difference between the main streams and tributary alleviated the occurrence of river algal blooms in the confluence area.

Multivariable integrated risk assessment for cyanobacterial blooms in eutrophic lakes and its spatiotemporal characteristics

Climate change has catalyzed the global expansion of cyanobacterial blooms in eutrophic , lakes and threatens water security. In most studies, the cyanobacterial bloom risk levels in lakes were evaluated using field-collected data from multiple indicators or spatially continuous data from one cyanobacteria-related indicator. Nevertheless, the occurrence of cyanobacterial blooms in lakes has clear spatial heterogeneity and is affected by numerous factors. Therefore, we developed a multivariable integrated risk assessment framework for cyanobacterial blooms in lakes using five spatially continuous datasets to estimate the risk level of cyanobacterial blooms at the pixel scale (250 m). The spatial and temporal variations in cyanobacterial bloom risk levels from May 1, 2002, to October 31, 2020, were investigated for three typical eutrophic lakes in China: Lakes Taihu, Chaohu, and Dianchi. Seasons and regions of high cyanobacterial bloom risk were identified for each lake. Environmental characteristics were discussed. A long-term investigation revealed that owing to its warm climate, the cyanobacterial risk levels in summer and autumn were much higher than those in the other two seasons. At the synoptic scale, Lake Taihu had a lower cyanobacterial bloom risk than Lakes Chaohu and Dianchi. A further comparison found that precipitation, wind speed, and temperature were responsible for the differences in cyanobacterial bloom risk levels among the three lakes. At the pixel scale, the risk map indicated that the cyanobacterial bloom risk levels of Lake Taihu were unevenly distributed, and the cyanobacterial bloom risk of the lakeshore was higher than that of the other subregions. Nutrient levels played the most critical role in the regional differences in cyanobacterial bloom risk levels in a lake. While the differences of cyanobacterial bloom risk levels in three lakes were resulted by the climates. Bloom events were defined and classified as "long-term bloom" or "flash bloom" according to their duration (over or below a year). Overall, this study can assist in advanced water management with a pixel-scale evaluation of cyanobacterial bloom risk levels.

Hysteresis effects of meteorological variation-induced algal blooms: A case study based on satellite-observed data from Dianchi Lake, China (1988-2020)

As one of three top-priority eutrophic lakes in China, Dianchi Lake has received national attention due to its severe eutrophication in recent decades. Meteorological factors are the main factors driving the formation and persistence of algae blooms. In addition, meteorological variation-induced algal blooms usually have a hysteresis effect. However, there have been few quantitative studies on this hysteresis effect. In the present study, Landsat images were used to extract the dynamic characteristics of changes in algal blooms in Dianchi Lake from 1988 to 2020. The hysteresis effect of meteorological factors driving algal blooms was studied by employing the modified lag-correlation method. The results showed that the algal blooms in Dianchi Lake were most severe between 1998 and 2008. During the periods of algal blooms, the values of air temperature (AT) and precipitation (PP) were significantly higher, while those wind velocity (WV) and sunshine duration (SSD) were obviously lower, than the corresponding annual mean values. AT and PP were significantly positively correlated with algal bloom factors in both the formation and persistence stages of algal blooms, while SSD and WV both promoted their regression, but these effects were less significant in the persistence period than in the formation period. Moreover, rainfall led to a decrease in SSD and WV, indirectly contributing to algal blooms. Furthermore, AT, PP and SSD are the main factors impacting the duration of persistent blooms. The time periods during which each meteorological factor was most influential were as follows: 1) AT - 25-30 days before the maximum bloom. 2) PP - within the first 10 days before the maximum bloom. 3) Both SSD and WV - 15-20 days before the maximum bloom. The results of this study support the prediction of algal blooms in Dianchi Lake.

A deep learning method for cyanobacterial harmful algae blooms prediction in Taihu Lake, China

Cyanobacterial Harmful Algae Blooms (CyanoHABs) in the eutrophic lakes have become a global environmental and ecological problem. In this study, a CNN-LSTM integrated model for predicting the CyanoHABs area was proposed and applied to the prediction of the CyanoHABs area in Taihu Lake. Firstly, the time-series data of the CyanoHABs area in Taihu Lake for 20 years were accurately obtained using MODIS images from 2000 to 2019 based on the FAI method. Then, a principal component analysis was performed on the daily meteorological data for the month before the outbreak of CyanoHABs in Taihu Lake from 2000 to 2019 to determine the meteorological factors closely related to the outbreak of CyanoHABs. Finally, the features of CyanoHABs area and meteorological data were extracted by Convolutional Neural Networks (CNN) model and used as the input of Long Short Term Memory Network (LSTM). An integrated CNN-LSTM model approach was constructed for predicting the CyanoHABs area. The results show that high R² (0.91) and low mean relative error (17.42%) verified the validity of the FAI index to extract the CyanoHABs area in Taihu Lake; the meteorological factors closely related to the CyanoHABs outbreak in Taihu Lake are mainly temperature, relative humidity, wind speed, and precipitation; the CNN-LSTM integrated model has better prediction effect for both training and test sets compared with the CNN and LSTM models. This study provides an effective method for predicting temporal changes in the CyanoHABs area and offers new ideas for scientific and effective regulation of inland water safety.

Are the existing guidelines sufficient for the assessment of bathing water quality? The example of Polish lakes

The safety of beachgoers and swimmers is determined by the presence or absence of microbial contaminants and cyanobacterial toxins in the water. This study compared the assessment of bathing waters according to the Bathing Water Directive, which is based on the concentration of fecal contaminants, with some modifications, and a new method based on the concentration of chlorophyll-a, which corresponds to the World Health Organization (WHO) guidelines used for determining cyanobacterial density in the water posing threat to people health. The results obtained from the method based on chlorophyll-a concentration clearly showed that the number of bathing waters in Poland with sufficient and insufficient quality were higher in 2018 and 2019, compared to the method based on microbial contamination. The closing of bathing waters based only on the visual confirmation of cyanobacterial blooms might not be enough to prevent the threat to swimmers' health. The multivariate analyses applied in this study seem to confirm that chlorophyll-a concentration with associated cyanobacterial density might serve as an additional parameter for assessing the quality of bathing waters, and in the case of small water reservoirs, might indirectly inform about the conditions and changes in water ecosystems.