LakeEnsemblR: An R package that facilitates ensemble modelling of lakes

Tadhg N. Moore; Jorrit P. Mesman; Robert Ladwig; Johannes Feldbauer; Freya Olsson; Rachel M. Pilla; Tom Shatwell; Jason J. Venkiteswaran; Austin D. Delany; Hilary A. Dugan; Kevin C. Rose; Jordan Read

doi:10.1016/j.envsoft.2021.105101

USGS · 70237357

LakeEnsemblR: An R package that facilitates ensemble modelling of lakes

Tadhg N. Moore·Jorrit P. Mesman·Robert Ladwig·Johannes Feldbauer·Freya Olsson·Rachel M. Pilla·Tom Shatwell·Jason J. Venkiteswaran·Austin D. Delany·Hilary A. Dugan·Kevin C. Rose·Jordan Read

View original source ↗Export metadata ↓

Abstract

Model ensembles have several benefits compared to single-model applications but are not frequently used within the lake modelling community. Setting up and running multiple lake models can be challenging and time consuming, despite the many similarities between the existing models (forcing data, hypsograph, etc.). Here we present an R package, LakeEnsemblR, that facilitates running ensembles of five different vertical one-dimensional hydrodynamic lake models (FLake, GLM, GOTM, Simstrat, MyLake). The package requires input in a standardised format and a single configuration file. LakeEnsemblR formats these files to the input required by each model, and provides functions to run and calibrate the models. The outputs of the different models are compiled into a single file, and several post-processing operations are supported. LakeEnsemblR's workflow standardisation can simplify model benchmarking and uncertainty quantification, and improve collaborations between scientists. We showcase the successful application of LakeEnsemblR for two different lakes.

Explore related subjects

Environmental Modelling & Software Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Tadhg N. Moore, Jorrit P. Mesman, Robert Ladwig, Johannes Feldbauer, Freya Olsson, Rachel M. Pilla, Tom Shatwell, Jason J. Venkiteswaran, Austin D. Delany, Hilary A. Dugan, Kevin C. Rose, Jordan Read. 2021. LakeEnsemblR: An R package that facilitates ensemble modelling of lakes. https://doi.org/10.1016/j.envsoft.2021.105101

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2026

Multivariate SWAT streamflow and surface water storage calibration enables upper Mississippi River Basin wetland change scenarios

Surface water storage (e.g., wetlands, lakes) is not typically considered in hydrological model calibrations. We tested a multivariate calibration process, incorporating Sentinel-1 and -2 surface water storage, for a Soil and Water Assessment Tool model across the 0.5 million km 2 Upper Mississippi River Basin. While 19% of the 2000 parameter sets adequately simulated discharge (Kling-Gupta efficiency >0.5), only 5% also adequately simulated surface water storage (mean absolute error <2 m), reducing model output uncertainty. Using the best calibrated model, we found that changes in surface water storage capacity most strongly affected discharge during the first annual peak flow (i.e., floods), when storage was filling. Increases in upstream surface water storage capacity resulted in projected decreases in peak flow and flashiness, with changes persisting downstream to the watershed outlet. Our findings demonstrate the importance of surface water storage in multivariate model calibration processes to inform river discharge and flood impact predictions.

Illinois, Indiana, Iowa, Minnesota, Missouri, Wisc↗

USGS2026

Artificial intelligence with earth observations provides continuous streamflow data across varying wildfire recurrence and recovery scenarios

Wildfires continue to alter watershed hydrology globally. Numerous studies have analyzed post-fire hydrology through before- and after-fire comparisons—often focusing on a single fire event. This has led to a significant gap in research, where continuous, daily streamflow data are needed to capture both the short- and long-term effects of recurring fires. Our study, for the first time, demonstrates how Artificial Intelligence (AI) through Machine Learning/Deep Learning (ML/DL) models can fill this gap by harnessing Earth Observations of burn severity, fire radiative power, and burn dates alongside traditional watershed attributes and drought indicators. We present a highly efficient DL model based on the Long Short-term Memory (LSTM) algorithm that is both reproducible and generalizable across multiple fire-affected watersheds in the western United States. Despite watersheds’ diverse climate conditions and markedly different hydrologic characteristics, the model consistently achieves strong performance, with Kling Gupta Efficiency ranging between 0.7 and 0.9. Our primary contribution is testing the model at a daily time-scale to model three distinct fire scenarios: no significant fire history yet the occurrence of a large fire, a longer return interval and no-fire period between phases of recurring fires, and frequent and repeated fire activity. We further investigate whether a relatively simple ML model such as Support Vector Machine (SVM) can achieve comparable accuracy in capturing these complex post-fire scenarios. By offering this fully open-source, generalizable AI solution powered by Earth Observations, newer and better modeling tools can provide post-fire daily streamflow data—a step in the right direction to safeguard water supply reliability and support watershed management across fire-prone regions worldwide.

California, Colorado, Idaho, Montana↗

USGS2025

METRIC: An interactive framework for integrated visualization and analysis of monitored and expected load reductions for nitrogen, phosphorus, and sediment in the Chesapeake Bay watershed

Reductions of nitrogen, phosphorus, and sediment loads have been the focus of watershed restoration in many regions for improving water quality, including the Chesapeake Bay. Watershed models and riverine monitoring data can provide important information on the progress of load reductions but do not always generate consistent interpretations. A new framework for integrated visualization and analysis of monitoring and modeling data, named “Monitored and Expected Total Reduction Indicator for the Chesapeake (METRIC),” was developed to provide spatially explicit trends for the subwatersheds of the Chesapeake Bay. METRIC contains up-to-date information on nitrogen, phosphorus, and sediment at 83, 66, and 66 stations, respectively, which can help watershed managers gauge expectations on the trajectory and pace of progress at localized scales. These results were further synthesized to better understand the spatial patterns of the response classes ( i.e. , agreement between the expected and monitored trends) across the Chesapeake Bay watershed.

Chesapeake Bay watershed↗