Skip to main content
Advanced Search

Folders: ROOT > ScienceBase Catalog > National and Regional Climate Adaptation Science Centers > Northeast CASC > FY 2017 Projects > “Hyperscale” Modeling to Understand and Predict Temperature Changes in Midwest Lakes ( Show direct descendants )

31 results (56ms)   

Location

Folder
ROOT
_ScienceBase Catalog
__National and Regional Climate Adaptation Science Centers
___Northeast CASC
____FY 2017 Projects
_____“Hyperscale” Modeling to Understand and Predict Temperature Changes in Midwest Lakes
Filters
Date Range
Extensions
Types
Contacts
Categories
Tag Types
Tag Schemes
View Results as: JSON ATOM CSV
thumbnail
Multiple modeling frameworks were used to predict daily temperatures at 0.5m depth intervals for a set of diverse lakes in the U.S. states of Minnesota and Wisconsin. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added...
thumbnail
This dataset includes model inputs that describe weather conditions for the 68 lakes included in this study. Weather data comes from gridded estimates (Mitchell et al. 2004). There are two comma-separated files, one for weather data (one row per model timestep) and one for ice-flags, which are used by the process-guided deep learning model to determine whether to apply the energy conservation constraint (the constraint is not applied when the lake is presumed to be ice-covered). The ice-cover flag is a modeled output and therefore not a true measurement (see "Predictions" and "pb0" model type for the source of this prediction). This dataset is part of a larger data release of lake temperature model inputs and outputs...
Abstract (from Ecological Society of America): Successful management of natural resources requires local action that adapts to larger‐scale environmental changes in order to maintain populations within the safe operating space (SOS) of acceptable conditions. Here, we identify the boundaries of the SOS for a managed freshwater fishery in the first empirical test of the SOS concept applied to management of harvested resources. Walleye (Sander vitreus) are popular sport fish with declining populations in many North American lakes, and understanding the causes of and responding to these changes is a high priority for fisheries management. We evaluated the role of changing water clarity and temperature in the decline...
thumbnail
This dataset provides model specifications used to estimate water temperature from a process-based model (Hipsey et al. 2019). The format is a single JSON file indexed for each lake based on the "site_id". This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
thumbnail
This dataset includes model inputs that describe local weather conditions for Sparkling Lake, WI. Weather data comes from two sources: locally measured (2009-2017) and gridded estimates (all other time periods). There are two comma-delimited files, one for weather data (one row per model timestep) and one for ice-flags, which are used by the process-guided deep learning model to determine whether to apply the energy conservation constraint (the constraint is not applied when the lake is presumed to be ice-covered). The ice-cover flag is a modeled output and therefore not a true measurement (see "Predictions" and "pb0" model type for the source of this prediction). This dataset is part of a larger data release of...
thumbnail
This dataset includes model inputs (specifically, weather and flags for predicted ice-cover) and is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
Abstract (from arXiv): This paper introduces a novel framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed as physics-guided neural network (PGNN), leverages the output of physics-based model simulations along with observational features to generate predictions using a neural network architecture. Further, this paper presents a novel framework for using physics-based loss functions in the learning objective of neural networks, to ensure that the model predictions not only show lower errors on the training set but are also scientifically consistent with the known physics on the unlabeled set. We illustrate the effectiveness...
thumbnail
Climate change has been shown to influence lake temperatures in different ways. To better understand the diversity of lake responses to climate change and give managers tools to manage individual lakes, we focused on improving prediction accuracy for daily water temperature profiles in 68 lakes in Minnesota and Wisconsin during 1980-2018. The data are organized into these items: Spatial data - One shapefile of polygons for all 68 lakes in this study (.shp, .shx, .dbf, and .prj files) Model configurations - Model parameters and metadata used to configure models (1 JSON file, with metadata for each of 68 lakes, indexed by "site_id") Model inputs - Data formatted as model inputs for predicting temperature a. Lake...
thumbnail
This dataset includes compiled water temperature data from an instrumented buoy on Lake Mendota, WI and discrete (manually sampled) water temperature records from North Temperate Lakes Long-TERM Ecological Research Program (NTL-LTER; https://lter.limnology.wisc.edu/). The buoy is supported by both the Global Lake Ecological Observatory Network (gleon.org) and the NTL-LTER. This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
Abstract (from arXiv): This paper proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physical models, while generating outputs consistent with physical laws, and achieving good generalizability. Standard RNNs, even when producing superior prediction accuracy, often produce physically inconsistent results and lack generalizability. We further enhance this approach by using a pre-training method that leverages the simulated data from a physics-based model to address the scarcity of observed...
Abstract (from Ecosphere): Understanding invasive species spread and projecting how distributions will respond to climate change is a central task for ecologists. Typically, current and projected air temperatures are used to forecast future distributions of invasive species based on climate matching in an ecological niche modeling approach. While this approach was originally developed for terrestrial species, it has also been widely applied to aquatic species even though aquatic species do not experience air temperatures directly. In the case of lakes, species respond to lake thermal regimes, which reflect the interaction of climate and lake attributes such as depth, size, and clarity. The result is that adjacent...
Categories: Publication; Types: Citation
thumbnail
This dataset includes evaluation data ("test" data) and performance metrics for water temperature predictions from multiple modeling frameworks. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added physical constraint for...
thumbnail
This dataset includes model inputs that describe local weather conditions for Lake Mendota, WI. Weather data comes from two sources: locally measured (2009-2017) and gridded estimates (all other time periods). There are two comma-delimited files, one for weather data (one row per model timestep) and one for ice-flags, which are used by the process-guided deep learning model to determine whether to apply the energy conservation constraint (the constraint is not applied when the lake is presumed to be ice-covered). The ice-cover flag is a modeled output and therefore not a true measurement (see "Predictions" and "pb0" model type for the source of this prediction). This dataset is part of a larger data release of lake...
thumbnail
This dataset includes evaluation data ("test" data) and performance metrics for water temperature predictions from multiple modeling frameworks. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added physical constraint for...
thumbnail
Multiple modeling frameworks were used to predict daily temperatures at 0.5m depth intervals for a set of diverse lakes in the U.S. states of Minnesota and Wisconsin. Process-Based (PB) models were configured and calibrated with training data to reduce root-mean squared error. Uncalibrated models used default configurations (PB0; see Winslow et al. 2016 for details) and no parameters were adjusted according to model fit with observations. Deep Learning (DL) models were Long Short-Term Memory artificial recurrent neural network models which used training data to adjust model structure and weights for temperature predictions (Jia et al. 2019). Process-Guided Deep Learning (PGDL) models were DL models with an added...
thumbnail
This dataset provides shapefile of outlines of the 68 lakes where temperature was modeled as part of this study. The format is a shapefile for all lakes combined (.shp, .shx, .dbf, and .prj files). This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
thumbnail
This dataset includes compiled water temperature data from a variety of sources, including the Water Quality Portal (Read et al. 2017), the North Temperate Lakes Long-TERM Ecological Research Program (https://lter.limnology.wisc.edu/), the Minnesota department of Natural Resources, and the Global Lake Ecological Observatory Network (gleon.org). This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
thumbnail
This dataset includes "test data" compiled water temperature data from an instrumented buoy on Lake Mendota, WI and discrete (manually sampled) water temperature records from North Temperate Lakes Long-TERM Ecological Research Program (NTL-LTER; https://lter.limnology.wisc.edu/). The buoy is supported by both the Global Lake Ecological Observatory Network (gleon.org) and the NTL-LTER. The dataset also includes Lake Mendota model erformance as measured as root-mean squared errors relative to temperature observations during the test period. This dataset is part of a larger data release of lake temperature model inputs and outputs for 68 lakes in the U.S. states of Minnesota and Wisconsin (http://dx.doi.org/10.5066/P9AQPIVD).
Abstract (from arXiv): To simultaneously address the rising need of expressing uncertainties in deep learning models along with producing model outputs which are consistent with the known scientific knowledge, we propose a novel physics-guided architecture (PGA) of neural networks in the context of lake temperature modeling where the physical constraints are hard coded in the neural network architecture. This allows us to integrate such models with state of the art uncertainty estimation approaches such as Monte Carlo (MC) Dropout without sacrificing the physical consistency of our results. We demonstrate the effectiveness of our approach in ensuring better generalizability as well as physical consistency in MC...
map background search result map search result map Process-guided deep learning predictions of lake water temperature Process-guided deep learning water temperature predictions: 1 Spatial data (GIS polygons for 68 lakes) Process-guided deep learning water temperature predictions: 3 Model inputs (meteorological inputs and ice flags) Process-guided deep learning water temperature predictions: 2 Model configurations (lake metadata and parameter values) Process-guided deep learning water temperature predictions: 4 Training data Process-guided deep learning water temperature predictions: 4a Lake Mendota detailed training data Process-guided deep learning water temperature predictions: 5 Model prediction data Process-guided deep learning water temperature predictions: 5c All lakes historical prediction data Process-guided deep learning water temperature predictions: 6 Model evaluation (test data and RMSE) Process-guided deep learning water temperature predictions: 6c All lakes historical evaluation data Process-guided deep learning water temperature predictions: 6a Lake Mendota detailed evaluation data Process-guided deep learning water temperature predictions: 3c All lakes historical inputs Process-guided deep learning water temperature predictions: 3a Lake Mendota inputs Process-guided deep learning water temperature predictions: 3b Sparkling Lake inputs Process-guided deep learning water temperature predictions: 3b Sparkling Lake inputs Process-guided deep learning water temperature predictions: 4a Lake Mendota detailed training data Process-guided deep learning water temperature predictions: 6a Lake Mendota detailed evaluation data Process-guided deep learning water temperature predictions: 3a Lake Mendota inputs Process-guided deep learning predictions of lake water temperature Process-guided deep learning water temperature predictions: 3 Model inputs (meteorological inputs and ice flags) Process-guided deep learning water temperature predictions: 2 Model configurations (lake metadata and parameter values) Process-guided deep learning water temperature predictions: 4 Training data Process-guided deep learning water temperature predictions: 5 Model prediction data Process-guided deep learning water temperature predictions: 5c All lakes historical prediction data Process-guided deep learning water temperature predictions: 6 Model evaluation (test data and RMSE) Process-guided deep learning water temperature predictions: 6c All lakes historical evaluation data Process-guided deep learning water temperature predictions: 3c All lakes historical inputs Process-guided deep learning water temperature predictions: 1 Spatial data (GIS polygons for 68 lakes)