Evaluate River Water Salinity in a Semi‐Arid Agricultural Watershed by Coupling Ensemble Machine Learning Technique with SWAT Model

Abstract

This study is to establish a new approach to estimate river salinity of semi‐arid agricultural watershed and identify drivers by using hydrologic modeling and machine learning. We augmented the limitations of the Soil and Water Assessment Tool (SWAT) to model salinity by coupling with eXtreme Gradient Boosting (XGBoost), a decision‐tree‐based ensemble machine learning algorithm. Streamflow, precipitation, elevation, main reach length, and dominant soil texture of the top two layers were used along with NO3, NO2, and total phosphorus (TP) output from a calibrated SWAT model are used as predictors to Total Dissolved Solids (TDS) in the XGBoost algorithm. Then, the SWAT model simulations of streamflow, NO3+NO2, and TP from 2000 to 2015 are used as inputs of the XGBoost model to predict monthly water TDS distribution along the river. The predicted river water TDS showed a higher concentration as going downstream from El Paso (inlet) through the Hudspeth canal to Fort Quitman (outlet). Finally, this study carried out cause analysis focusing on soil physical characteristics. The soil salinity level is directly affected by the soil permeability and irrigation water. As a result, the highest TDS is shown in sites with silt loam, whereas the lowest TDS was shown in sites with very cobbly soil. Silt soils can hold more water and are slower to drain than soils of a sand type. These analyses can be used to better understand the mitigation of water salinity.

Salt transport in a large agro-urban river basin: Modeling, controlling factors, and management strategies

“…Bailey et al (2019), Maleki et al (2021), Tirabadi et al (2021) each developed salinity modules for the SWAT hydrological model (Arnold et al, 1998) for simulating salinity transport at the watershed scale, but only introduced the model, leaving salt management scenario analysis for future studies. Jung et al (2021) used output from SWAT (streamflow, precipitation, elevation, reach length, soil texture, nutrient loads) and machine learning to predict monthly total dissolved solids in the Rio Grande River, Texas. Huang and Foo (2002) used relationships between freshwater inflows, tidal activity, and wind to predict salinity variation in the Apalochicola River Florida.…”

Closing remarks to the featured collection: Water security—New technologies, strategies, policies, and institutions

“…Chen et al (2021) proposed an interval two‐stage classified allocation model to address the nonstationarity and uncertainty in optimal allocations of regional water resources. Jung et al (2022) overcame the limitations of the Soil and Water Assessment Tool (SWAT) to model salinity in a watershed within the Rio Grande basin by coupling SWAT with eXtreme Gradient Boosting (XGBoost), a decision‐tree‐based ensemble machine learning algorithm and identified both temporal and spatial trends. Lou et al (2022) put forward an information‐based method, supplemented with a coupling strength index, to quantify soil moisture–precipitation feedback characteristics in a case study of Illinois.…”