Nathan Swain

Dr. Nathan Swain

Aquaveo, Provo, Utah, USA
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 November 2016 in Environmental Modelling & Software
Verified
Journal Article
Closed access
Nathan SwainNathan Swain
Nathan Swain
SCScott D. Christensen
Scott D. Christensen
ASAlan D. Snow
Alan D. Snow
HDHerman Dolder
Herman Dolder
Gonzalo Enrique Espinoza DávalosGonzalo Enrique Espinoza Dávalos
Gonzalo Enrique Espinoza Dávalos
SBSteven J. Burian
Steven J. Burian

13 August 2026 in Journal of Hydroinformatics
Verified
Journal Article
Open access
TMTasfia Mahjarin
Tasfia Mahjarin
CKCorey Krewson
Corey Krewson
Nathan SwainNathan Swain
Nathan Swain
JSJianting Shi
Jianting Shi
DADaniel P. Ames
Daniel P. Ames
Three-column flow diagram. Five hydrologic data sources feed the Tethys Dash platform, built from plugin architecture, state-driven UI and multi-panel layout components, which lead to seven listed outcomes and two case study panels. Effective water resources management requires tools that integrate hydrologic data, model outputs, and forecasts into actionable decision-making environments. Although numerous web-based platforms support data sharing and visualization, many require substantial programming expertise, limiting adoption by domain scientists. This paper introduces Tethys Dash, an open-source, low-code platform built on the Tethys Platform for creating interactive hydrologic dashboards. The system employs a plugin-based architecture using Python's Intake package, state-driven React components, and a grid-based layout engine to support simultaneous visualization of spatial, temporal, and analytical data without front-end coding. Integration with external services – including HydroShare, GeoServer, THREDDS, and the National Water Prediction Service API – provides dynamic data connectivity. Two case studies, an RFC Max Forecast dashboard and a Great Lakes Water Levels dashboard, demonstrate the platform's support for real-time situational awareness and retrospective analysis. Results indicate that Tethys Dash reduces front-end development effort while providing extensibility and operational relevance for water resources applications.

8 October 2026 in Water
Verified
Journal Article
Open access
PDF file
ACAbin Raj Chapagain
Abin Raj Chapagain
IMIman Maghami
Iman Maghami
DADaniel P. Ames
Daniel P. Ames
SMSujan Chandra Mondol
Sujan Chandra Mondol
Nathan SwainNathan Swain
Nathan Swain
Gustavious Paul WilliamsGustavious Paul Williams
Gustavious Paul Williams
Evapotranspiration (ET) forecasts from the U.S. National Water Model (NWM) carry systematic biases that are most apparent in water-stressed, intensively managed regions. This study develops a machine learning (ML) post-processing framework that bias-corrects 1–7 day accumulated ET (ACCET) forecasts from the NWM medium-range configuration using NWM meteorological forcings, the raw NWM-ACCET forecast, and auxiliary spatial and temporal predictors. Three tree-based models—Random Forest (RF), XGBoost, and LightGBM—were trained on AmeriFlux eddy-covariance observations at four California model-development sites and evaluated using nested five-fold temporally blocked cross-validation with a ±7-day purge window; two additional sites were withheld for independent off-site validation. All three models substantially outperformed the raw NWM forecasts. Pooled out-of-fold performance across the four model-development sites yielded R2 values of 0.832–0.854 and mean-normalized root mean squared error (NRMSE) values of 0.427–0.460, compared with R2 = 0.086 and NRMSE = 1.206 for the raw NWM forecasts. LightGBM and XGBoost were favored over RF in this four-site out-of-fold evaluation. Independent off-site validation yielded R2 values of 0.796–0.874 and NRMSE values of 0.380–0.459, with RF showing the most robust overall performance. Converting ACCET to lead-time-specific increments revealed substantially stronger lead-time degradation than was apparent from the accumulated metrics. Feature-importance and SHapley Additive exPlanations (SHAP) analyses identified wind, lead time, seasonality, and radiation as dominant predictors. The framework offers a practical route to more reliable operational ET forecasts for water management, agriculture, and drought monitoring, with potential for extension to climatically similar regions.