Integrating temporal decomposition and data-driven approaches for predicting coastal harmful algal blooms.

Frequent coastal harmful algal blooms (HABs) threaten the ecological environment and human health. Biscayne Bay in southeastern Florida also faces algal bloom issues; however, the mechanisms driving these blooms are not fully understood, emphasizing the importance of HAB prediction for effective environmental management. The overarching goal of this study is to offer a robust HAB predictive framework and try to enhance the understanding of HAB dynamics. This study established three scenarios to predict chlorophyll-a concentrations, a recognized representative of HABs: Scenario 1 (S1) using single nonlinear machine learning (ML) algorithms, hybrid Scenario 2 (S2) combining linear models and nonlinear ML algorithms, and hybrid Scenario 3 (S3) combining temporal decomposition and ML (TD-ML) algorithms. The novel-developed S3 TD-ML hybrid models demonstrated superior predictive capabilities, achieving all R2 values above 0.9 and MAPE under 30% in tests, significantly outperforming the S1 with an average R2 of 0.16 and the S2 with an R2 of -0.06. S3 models effectively captured the algal dynamics, successfully predicting complex time series with extremes and noise. In addition, we unveiled the relationship between environmental variables and chlorophyll-a through correlation analysis and found that climate change might intensify the HABs in Biscayne Bay. This research developed a precise predictive framework for early warning and proactive management of HABs, offering potential global applicability and improved prediction accuracy to address HAB challenges.

Impacts of future climate and land use/land cover change on urban runoff using fine-scale hydrologic modeling.

Future changes in land use/land cover (LULC) and climate (CC) affect watershed hydrology. Despite past research on estimating such changes, studies on the impacts of both these nonstationary stressors on urban watersheds have been limited. Urban watersheds have several important details such as hydraulic infrastructure that call for fine-scale models to predict the impacts of LULC and CC on watershed hydrology. In this paper, a fine-scale hydrologic model-Personal Computer Storm Water Management Model (PCSWMM)-was applied to predict the individual and joint impacts of LULC changes and CC on surface runoff attributes (peak and volume) in 3800 urban subwatersheds in Midwest Florida. The subwatersheds a range of characteristics in terms of drainage area, surface imperviousness, ground slope and LULC distribution. The PCSWMM also represented several hydraulic structures (e.g., ponds and pipes) across the subwatersheds. We analyzed changes in the runoff attributes to determine which stressor is most responsible for the changes and what subwatersheds are mostly sensitive to such changes. Six 24-h design rainfall events (5- to 200-year recurrence intervals) were studied under historical (2010) and future (year 2070) climate and LULC. We evaluated the response of the subwatersheds in terms of runoff peak and volume to the design rainfall events using the PCSWMM. The results indicated that, overall, CC has a greater impact on the runoff attributes than LULC change. We also found that LULC and climate induced changes in runoff are generally more pronounced in greater recurrence intervals and subwatersheds with smaller drainage areas and milder slopes. However, no relationship was found between the changes in runoff and original subwatershed imperviousness; this can be due to the small increase in urban land cover projected for the study area. This research helps urban planners and floodplain managers identify the required strategies to protect urban watersheds against future LULC change and CC.

Predicting coastal harmful algal blooms using integrated data-driven analysis of environmental factors.

Coastal harmful algal blooms (HABs) have become one of the challenging environmental problems in the world's thriving coastal cities due to the interference of multiple stressors from human activities and climate change. Past HAB predictions primarily relied on single-source data, overlooked upstream land use, and typically used a single prediction algorithm. To address these limitations, this study aims to develop predictive models to establish the relationship between the HAB indicator - chlorophyll-a (Chl-a) and various environmental stressors, under appropriate lagging predictive scenarios. To achieve this, we first applied the partial autocorrelation function (PACF) to Chl-a to precisely identify two prediction scenarios. We then combined multi-source data and several machine learning algorithms to predict harmful algae, using SHapley Additive exPlanations (SHAP) to extract key features influencing output from the prediction models. Our findings reveal an apparent 1-month autoregressive characteristic in Chl-a, leading us to create two scenarios: 1-month lead prediction and current-month prediction. The Extra Tree Regressor (ETR), with an R2 of 0.92, excelled in 1-month lead predictions, while the Random Forest Regressor (RFR) was most effective for current-month predictions with an R2 of 0.69. Additionally, we identified current month Chl-a, developed land use, total phosphorus, and nitrogen oxides (NOx) as critical features for accurate predictions. Our predictive framework, which can be applied to coastal regions worldwide, provides decision-makers with crucial tools for effectively predicting and mitigating HAB threats in major coastal cities.

Understanding the dynamics of microplastics transport in urban stormwater runoff: Implications for pollution control and management.

The transport of microplastics (MPs) from urban environments to water resources via stormwater runoff poses significant concerns due to its adverse impacts on water safety and aquatic ecosystems. This study presents a modeling approach aimed at understanding the transport mechanisms of MPs in an urban residential setting, considering settling and buoyant MPs. To consider the effect of MP shapes, the settling velocity of various settling MPs in shapes of fibers, films, and fragments was calculated. Using an analogy of sediment transport, a Rouse number criterion was used to analyze the transport of MPs. For buoyant MPs, it was assumed that they transport as wash-load as soon as they float in the water and the travel time for them to reach the storm drain was determined. The calculation of settling velocity revealed the influence of shape on the settling velocity of MPs was particularly pronounced as the equivalent diameter of the MPs increased. The transport mechanism for the smallest settling MPs, irrespective of their shapes, density, and depth of flow, was wash-load. However, for larger MPs, the shape and size distribution of settling MPs, along with the depth of flow and slope significantly influenced their transport mechanisms compared to sediment particles. The influence of weathering on the MPs' transport mechanisms depended on their sizes and shapes. The site-specific characteristics, including slope and surface friction, significantly influenced the velocity of stormwater runoff and, consequently, the extent of MP transport during rain events. Moreover, an evaluation of the transport mechanism of settling MPs was conducted using the reported field data on MP abundance in road dust collected from residential and traffic sites. This study underscores the complexity of MP transport dynamics and provides a foundation for developing targeted strategies to mitigate MP pollution in urban environments.

Effects of rainfall characteristics on runoff quality parameters within an industrial sector in Tennessee, USA.

The relationship between rainfall characteristics and pollutant discharge has rarely been investigated in industrial sectors. To address this need, we investigated the pollutant concentrations of surface runoff and the correlation between pollutant discharge and rainfall characteristics using the self-reported stormwater quality data collected under the Tennessee Multi-Sector Permit program for two industrial facilities in West Tennessee. The variation of certain stormwater quality parameters over this period was utilized as an indicator to evaluate the effectiveness of control measures implemented at these two facilities. Furthermore, the Water Quality Index (WQI) as an indicator to assess the temporal changes in stormwater quality at industrial facilities was determined using the Weighted Sum (WSM) and Canadian Council of Ministers of the Environment (CCME) methods. The principal component analysis (PCA) and Pearson correlation coefficient were utilized to understand the correlation between runoff quality parameters, rainfall characteristics, and the sources of pollutants. The results demonstrated lower WQI indices using the WSM method compared to the CCME method. The data analysis revealed that 93.1%, 100%, 86.2%, and 48.3% of Al, Mg, Cu, and Fe experienced a concentration greater than the benchmark level, respectively. There was a significant relationship between Total suspended solids (TSS) and Al, Chemical Oxygen Demand (COD), Fe, oil and grease (O&G), and Zn concentrations. As a result, TSS could be a priority pollutant for designing various best management practices (BMPs) and low impact developments (LIDs). The result of the PCA and Pearson correlation coefficient showed that Al concentration made a significant correlation with the rainfall depth and rainfall duration. This analysis also illustrated that biochemical oxygen demand (BOD5), COD, and O&G concentrations were highly correlated with antecedent dry days (ADDs). However, pH was more related to rainfall depth and rainfall intensity. This study informs both regulatory agencies and industry stakeholders regarding the importance of evaluating self-reported stormwater quality data.

Water quality characterization of storm and irrigation runoff from a container nursery.

Commercial nurseries grow specialty crops for resale using a variety of methods, including containerized production, utilizing soilless substrates, on a semipervious production surface. These "container" nurseries require daily water application and continuous availability of mineral nutrients. These factors can generate significant nutrients [total nitrogen (TN), and total phosphorus (TP)] and sediment [total suspended solids (TSS)] in runoff, potentially contributing to eutrophication of downstream water bodies. Runoff is collected in large ponds known as tailwater recovery basins for treatment and reuse or discharge to receiving streams. We characterized TSS, TN, and TP, electrical conductivity (EC), and pH in runoff from a 5.2 ha production portion of a 200-ha commercial container nursery during storm and irrigation events. Results showed a direct correlation between TN and TP, runoff and TSS, TN and EC, and between flow and pH. The Storm Water Management Model (SWMM) was used to characterize runoff quantity and quality of the site. We found during irrigation events that simulated event mean concentrations (EMCs) of TSS, TN, and TP were 30, 3.1 and 0.35 mg·L-1, respectively. During storm events, TSS, TN and TP EMCs were 880, 3.7, and 0.46 mg·L-1, respectively. EMCs of TN and TP were similar to that of urban runoff; however, the TSS EMC from nursery runoff was 2-4 times greater. The average loading of TSS, TN and TP during storm events was approximately 900, 35 and 50 times higher than those of irrigation events, respectively. Based on a 10-year SWMM simulation (2008-2018) of runoff from the same nursery, annual TSS, TN and TP load per ha during storm events ranged from 9230 to 13,300, 65.8 to 94.0 and 9.00 to 12.9 kg·ha-1·yr-1, respectively. SWMM was able to characterize runoff quality and quantity reasonably well. Thus, it is suitable for characterizing runoff loadings from container nurseries.

Water supply and runoff capture reliability curves for hypothetical rainwater harvesting systems for locations across the U.S. for historical and projected climate conditions.

The data presented in this article are related to the research article entitled "Assessing climate change impacts on the reliability of rainwater harvesting systems" (Alamdari et al., 2018) [1]. This article evaluated the water supply and runoff capture reliability of rainwater harvesting (RWH) systems for locations across the U.S. for historical and projected climate conditions. Hypothetical RWH systems with varying storage volumes, rooftop catchment areas, irrigated areas, and indoor wSater demand based upon population from selected locations were simulated for historical (1971-1998) and projected (2041-2068) periods, the latter dataset was developed using dynamic downscaling of North American Regional Climate Change (CC) Assessment Program (NARCCAP). A computational model, the Rainwater Analysis and Simulation Program (RASP), was used to compute RWH performance with respect to the reliability of water supply and runoff capture. The reliability of water supply was defined as the proportion of demands that are met; and the reliability of runoff capture was defined as the amount stored and reused, but not spilled. A series of contour plots using the four design variables and the reliability metrics were developed for historical and projected conditions. Frequency analysis was also used to characterize the long-term behavior of rainfall and dry duration at each location. The full data set is made publicly available to enable critical or extended analysis of this work.