Comparison of Machine Learning-Based Predictive Models of the Nutrient Loads Delivered from the Mississippi/Atchafalaya River Basin to the Gulf of Mexico

Keyphrases

• Gulf of Mexico 100%
• Machine Learning Based 100%
• Mississippi-Atchafalaya River 100%
• Learning-based Predictive Model 100%
• Nutrient Load 100%
• Long Short-term Memory 55%
• Autoregressive Integrated Moving Average (ARIMA) 44%
• Multilayer Perceptron 44%
• Gaussian Process Regression 33%
• Correlation Coefficient 22%
• Machine Learning Models 22%
• Excess nutrients 22%
• United States Geological Survey 11%
• Environmental Issues 11%
• Prediction Accuracy 11%
• Nonlinear Behavior 11%
• Memory Performance 11%
• Performance Prediction 11%
• Northern Gulf of Mexico 11%
• Machine Learning 11%
• Hypoxia 11%
• Hybrid Model 11%
• Temporal Variation 11%
• Healthy Ecosystems 11%
• Monitoring Station 11%
• Hypoxic Zone 11%
• Load Performance 11%
• Mean Square Error 11%
• Eutrophication Process 11%
• Predictive Model 11%
• Nutrient Fluxes 11%
• Model Evaluation 11%
• Survey Monitoring 11%
• Nutrient Modeling 11%
• Machine Learning Prediction 11%
• Healthy Economy 11%

Earth and Planetary Sciences

• Gulf of Mexico 100%
• Machine Learning 100%
• Mississippi 100%
• Long Short-Term Memory Network 83%
• Long Short-Term Memory 83%
• Self Organizing Systems 66%
• Kriging 50%
• Machine Learning Model 50%
• Correlation Coefficient 33%
• Geological Survey 16%
• Environmental Issue 16%
• Temporal Variation 16%
• Eutrophication 16%
• Monitoring Station 16%
• Hybrid Model 16%