Search Results (6)

Predicting nutrient loads is essential to understanding and managing one of the environmental issues faced by the northern Gulf of Mexico hypoxic zone, which poses a severe threat to the Gulf’s healthy ecosystem and economy. The development of hypoxia in the Gulf of Mexico is strongly associated with the eutrophication process initiated by excessive nutrient loads. Due to the complexities in the excessive nutrient loads to the Gulf of Mexico, it is challenging to understand and predict the underlying temporal variation of nutrient loads. The study was aimed at identifying an optimal predictive machine learning model to capture and predict nonlinear behavior of the nutrient loads delivered from the Mississippi/Atchafalaya River Basin (MARB) to the Gulf of Mexico. For this purpose, monthly nutrient loads (N and P) in tons were collected from US Geological Survey (USGS) monitoring station 07373420 from 1980 to 2020. Machine learning models—including autoregressive integrated moving average (ARIMA), gaussian process regression (GPR), single-layer multilayer perceptron (MLP), and a long short-term memory (LSTM) with the single hidden layer—were developed to predict the monthly nutrient loads, and model performances were evaluated by standard assessment metrics—Root Mean Square Error (RMSE) and Correlation Coefficient (R). The residuals of predictive models were examined by the Durbin–Watson statistic. The results showed that MLP and LSTM persistently achieved better accuracy in predicting monthly TN and TP loads compared to GPR and ARIMA. In addition, GPR models achieved slightly better test RMSE score than ARIMA models while their correlation coefficients are much lower than ARIMA models. Moreover, MLP performed slightly better than LSTM in predicting monthly TP loads while LSTM slightly outperformed for TN loads. Furthermore, it was found that the optimizer and number of inputs didn’t show effects on the LSTM performance while they exhibited impacts on MLP outcomes. This study explores the capability of machine learning models to accurately predict nonlinearly fluctuating nutrient loads delivered to the Gulf of Mexico. Further efforts focus on improving the accuracy of forecasting using hybrid models which combine several machine learning models with superior predictive performance for nutrient fluxes throughout the MARB. Full article

The Northern Gulf of Mexico hosts a severe dead zone, an oxygen-depleted area spanning 1,618,000 hectares, threatening over 40% of the U.S. fishing industry and causing annual losses of USD 82 million. Using a System Dynamics (SD) approach, this study examined the Mississippi–Atchafalaya River Basin (MARB), a major contributor to hypoxia in the Gulf. A dynamic model, developed with Vensim software version 10.2.1 andexisting data, represented the physical, biological, and chemical processes leading to eutrophication and simulated dead zone formation over time. Various policies were assessed, considering natural system variability. The findings showed that focusing solely on nitrogen control reduced the dead zone but required greater intensity or managing other inputs to meet environmental goals. Runoff control policies delayed nutrient discharge but did not significantly alter long-term outcomes. Extreme condition tests highlighted the critical role of runoff dynamics, dependent on nitrogen load relative to flow volume from upstream. The model suggests interventions should not just reduce eutrophication inputs but enhance factors slowing down the process, allowing natural denitrification to override anthropogenic nitrification. Full article

To minimize the eutrophication pressure along the Gulf of Mexico or reduce the size of the hypoxic zone in the Gulf of Mexico, it is important to understand the underlying temporal and spatial variations and correlations in excess nutrient loads, which are strongly associated with the formation of hypoxia. This study’s objective was to reveal and visualize structures in high-dimensional datasets of nutrient yield distributions throughout the Mississippi/Atchafalaya River Basin (MARB). For this purpose, the annual mean nutrient concentrations were collected from thirty-three US Geological Survey (USGS) water stations scattered in the upper and lower MARB from 1996 to 2020. Eight surface water quality indicators were selected to make comparisons among water stations along the MARB over the past two decades. Principal component analysis (PCA) was used to comprehensively evaluate the nutrient yields across thirty-three USGS monitoring stations and identify the major contributing nutrient loads. The results showed that all samples could be analyzed using two main components, which accounted for 81.6% of the total variance. The PCA results showed that yields of orthophosphate (OP), silica (SI), nitrate–nitrites (NO₃-NO₂), and total suspended sediment (TSS) are major contributors to nutrient yields. It also showed that land-planted crops, density of population, domestic and industrial discharges, and precipitation are fundamental causes of excess nutrient loads in MARB. These factors are of great significance for the excess nutrient load management and pollution control of the Mississippi River. It was found that the average nutrient yields were stable within the sub-MARB area, but the large nitrogen yields in the upper MARB and the large phosphorus yields in the lower MARB were of great concern. t-distributed stochastic neighbor embedding (t-SNE) revealed interesting nonlinear and local structures in nutrient yield distributions. Clustering analysis (CA) showed the detailed development of similarities in the nutrient yield distribution. Moreover, PCA, t-SNE, and CA showed consistent clustering results. This study demonstrated that the integration of dimension reduction techniques, PCA, and t-SNE with CA techniques in machine learning are effective tools for the visualization of the structures of the correlations in high-dimensional datasets of nutrient yields and provide a comprehensive understanding of the correlations in the distributions of nutrient loads across the MARB. Full article

Risks from flooding and poor water quality are evident at a range of spatial scales and climate change will exacerbate these risks in the future. Natural infrastructure (NI), consisting of structural or perennial vegetation, measures that provide multiple ecosystem benefits have the potential to reduce flood and water quality risks. In this study, we intersected watershed-scale risks to flooding and nitrate export in the Mississippi-Atchafalaya River Basin (MARB) of the central U.S. with potential locations of seven NI practices (row crop conversion, water, and sediment control basins, depressional wetlands, nitrate-removal wetlands, riparian buffers, and floodplain levees and row crop change) to prioritize where NI can be most effective for combined risk reduction at watershed scales. Spatial data from a variety of publicly-available databases were analyzed at a 10 m grid cell to locate NI practices using a geographic information system (GIS). NI practices were presented at the regional basin scale and local Iowa-Cedar watershed in eastern Iowa to show individual practice locations. A prioritization scheme was developed to show the optimal watersheds for deploying NI practices to minimize flooding and water quality risks in the MARB. Among the 84 HUC4 basins in the MARB, 28 are located in the Upper Mississippi and Ohio Rivers basins. The Wabash and Iowa-Cedar basins (HUCs 0512 and 0708, respectively) within these basins were found to rank among the uppermost quintile for nearly all practices evaluated, indicating widespread opportunities for NI implementation. Study results are a launching point from which to improve the connections between watershed scale risks and the potential use of NI practices to reduce these risks. Full article

This study investigated the annual and seasonal variations in nutrient loads (NO₂⁻ + NO₃⁻ and orthophosphate) delivered to the Gulf of Mexico from the Mississippi-Atchafalaya River Basin (MARB) and examined the water quality variations. The results indicate that (1) annually, the mean NO₂⁻ + NO₃⁻ and orthophosphate loads showed a steady increase during 1996–1999, a persistent level during 2000–2007, and a moderate increase during 2008–2016; (2) seasonally, NO₂⁻ + NO₃⁻ and orthophosphate in MARB in spring and summer were higher than those in autumn and winter. Analysis of variance (ANOVA) identified highly significant differences among seasonal loads; and (3) the median value of NO₂⁻ + NO₃⁻ in normal weather conditions were higher than that during and right after the hurricanes, while the median value of orthophosphate loads in normal weather conditions was higher than that during the hurricanes, but higher than that right after hurricanes. The two-sample t-test indicates a significant difference (p < 0.046) in orthophosphate loads before and after Hurricane Katrina. Moreover, it is found that there is a significant (p < 0.01) increase in nutrient loads during normal weather conditions. The results indicate that hurricane seasons can significantly influence the nutrient loads from the MARB to the Gulf of Mexico. Full article

This study is a part of the Conservation Effects Assessment Project (CEAP) aimed to quantify the environmental and economic benefits of conservation practices implemented in the cultivated cropland throughout the United States. The Soil and Water Assessment Tool (SWAT) model under the Hydrologic United Modeling of the United States (HUMUS) framework was used in the study. An automated flow calibration procedure was developed and used to calibrate runoff for each 8-digit watershed (within 20% of calibration target) and the partitioning of runoff into surface and sub-surface flow components (within 10% of calibration target). Streamflow was validated at selected gauging stations along major rivers within the river basin with a target R² of >0.6 and Nash and Sutcliffe Efficiency of >0.5. The study area covered the entire Mississippi and Atchafalaya River Basin (MARB). Based on the results obtained, our analysis pointed out multiple challenges to calibration such as: (1) availability of good quality data, (2) accounting for multiple reservoirs within a sub-watershed, (3) inadequate accounting of elevation and slopes in mountainous regions, (4) poor representation of carrying capacity of channels, (5) inadequate capturing of the irrigation return flows, (6) inadequate representation of vegetative cover, and (7) poor representation of water abstractions (both surface and groundwater). Additional outstanding challenges to large-scale hydrologic model calibration were the coarse spatial scale of soils, land cover, and topography. Full article