Predicting high-frequency variation in stream solute concentrations with water quality sensors and machine learning

Keyphrases

• Machine Learning 100%
• Solute 100%
• Solute Concentration 100%
• High-frequency Variability 100%
• Stream Solute 100%
• Water Quality Sensor 100%
• Support Vector Machine 40%
• Random Forest 40%
• Sensor Technology 20%
• New Hampshire 20%
• Earth System 20%
• Dissolved Oxygen 20%
• Turbidity 20%
• Temporal Variation 20%
• Machine Learning Algorithms 20%
• System Function 20%
• Specific Sensors 20%
• Stream Water 20%
• Stream Discharge 20%
• Fluorescent Dissolved Organic Matter 20%
• Specific Conductivity 20%
• Discrete Sampling 20%
• New Sensors 20%
• Random Forest Algorithm 20%
• Predicted No Effect Concentration 20%
• Nash-Sutcliffe Efficiency 20%
• Support Vector Machine Algorithm 20%
• Two-machine 20%
• Hubbard Brook Experimental Forest 20%
• Reference Flow 20%
• Ecosystem System 20%
• Stream Sampling 20%
• Solute Yield 20%

Engineering

• Solute Concentration 100%
• Random Forest 100%
• Learning System 100%
• Support Vector Machine 100%
• Fine Scale 33%
• System Function 33%
• Earth System 33%
• Temporal Variation 33%
• Sutcliffe 33%
• Machine Learning Algorithm 33%
• Electrical Conductivity 33%

Earth and Planetary Sciences

• Machine Learning 100%
• Support Vector Machine 100%
• Turbidity 33%
• United States of America 33%
• Temporal Variation 33%
• New Hampshire 33%
• Organic Matter 33%
• Dissolved Oxygen 33%