The water and climate data for Lake Erie, including: Soil moisture, streamflow, water temperature, evaporation, baseflow. This dataset is associated with the following publication: Chang, F., M. Astitha, Y. Yuan, C. Tang, P. Vlahos, V. Cover, and U. Khaira. A New Approach to Predict Tributary Phosphorus Loads Using Machine Learning– and Physics-Based Modeling Systems.. Artificial Intelligence for the Earth Systems. American Meteorological Society, Boston, MA, USA, 2(3): 1-20, (2023).

The datasets include hydrological parameters such as streamflow, soil moisture and water temperature, and meteorological data such as precipitation, max and min temperature, evaporation from 2002 to 2017 for Lake Erie. This dataset is associated with the following publication: Feng Chang, C., V. Cover, C. Tang, P. Vlahos, D. Wanik, J. Yan, J. Bash, and M. Astitha. Linking multi-media modeling with machine learning to assess and predict lake chlorophyll a concentrations. JOURNAL OF GREAT LAKES RESEARCH. International Association for Great Lakes Research, Ann Arbor, MI, USA, 47(6): 1656-1670, (2021).

The datasets include hydrological parameters such as streamflow, soil moisture and water temperature, and meteorological data such as precipitation, max and min temperature, evaporation from 2002 to 2017 for Lake Erie. This dataset is associated with the following publication: Feng Chang, C., V. Cover, C. Tang, P. Vlahos, D. Wanik, J. Yan, J. Bash, and M. Astitha. Linking multi-media modeling with machine learning to assess and predict lake chlorophyll a concentrations. JOURNAL OF GREAT LAKES RESEARCH. International Association for Great Lakes Research, Ann Arbor, MI, USA, 47(6): 1656-1670, (2021).

This dataset allows the user to explore the potential impacts of various environmental and anthropogenic drivers on observed growing season total phosphorus concentrations in lakes and streams across the United States.

The Archive.zip data set contains R source code and inputs and selected outputs associated with regression analyses used to estimate total phosphorus loads for selected sites on Great Lakes tributaries for water years 2014–2018

Please review Zhang et al. (2021) for details on study design and datasets (https://doi.org/10.1016/j.watres.2022.118443). In summary, predictor and response variable data was acquired from the Chesapeake Bay Program and USGS. This data was subjected to a trend analysis to estimate the MK linear slope change for both predictor and response variables. After running a cluster analysis on the scaled TN loading time series (the response variable), the cluster assignment was paired with the slope estimates from the suite of predictor variables tied to the nutrient inventory and static geologic and land use variables. From there, an RF analysis was executed to link trends in anthropogenic driver and other contextual environmental factors to the identified trend cluster types. After calibrating the RF model, likelihood of improving, relatively static, or degrading catchments across the Chesapeake Bay were identified for the 2007 to 2018 period. Tabular data is available on the journal website and PUBMED, and the predictor/response variable data can be downloaded individually in the USGS and Chesapeake Bay Program links listed in the data access section. Portions of this dataset are inaccessible because: This data was generate by other federal entities and are housed in their respective data warehouse domains (e.g., USGS and Chesapeake Bay Program). Furthermore, the data can be accessed on the journal website as well as NCBI PUBMED (https://pubmed.ncbi.nlm.nih.gov/35461100/). They can be accessed through the following means: Combined dataset can be accessed on the journal website (https://www.sciencedirect.com/science/article/pii/S0043135422003979?via%3Dihub#ack0001) and will soon be available on NCBI (https://pubmed.ncbi.nlm.nih.gov/35461100/). The predictor variable data can be accessed from the Chesapeake Bay Program (https://cast.chesapeakebay.net/) and USGS (https://pubs.er.usgs.gov/publication/ds948 and https://www.sciencebase.gov/catalog/item/5669a79ee4b08895842a1d47). Format: Please review Zhang et al. (2021) for details on study design and datasets (https://doi.org/10.1016/j.watres.2022.118443). In summary, predictor and response variable data was acquired from the Chesapeake Bay Program and USGS. This data was subjected to a trend analysis to estimate the MK linear slope change for both predictor and response variables. After running a cluster analysis on the scaled TN loading time series (the response variable), the cluster assignment was paired with the slope estimates from the suite of predictor variables tied to the nutrient inventory and static geologic and land use variables. From there, an RF analysis was executed to link trends in anthropogenic driver and other contextual environmental factors to the identified trend cluster types. After calibrating the RF model, likelihood of improving, relatively static, or degrading catchments across the Chesapeake Bay were identified for the 2007 to 2018 period. Tabular data is available on the journal website and PUBMED, and the predictor/response variable data can be downloaded individually in the USGS and Chesapeake Bay Program links listed in the data access section. This dataset is associated with the following publication: Zhang, Q., J. Bostic, and R. Sabo. Regional patterns and drivers of total nitrogen trends in the Chesapeake Bay watershed: Insights from machine learning approaches and management implications. WATER RESEARCH. Elsevier Science Ltd, New York, NY, USA, 218: 1-15, (2022).

Please review Zhang et al. (2021) for details on study design and datasets (https://doi.org/10.1016/j.watres.2022.118443). In summary, predictor and response variable data was acquired from the Chesapeake Bay Program and USGS. This data was subjected to a trend analysis to estimate the MK linear slope change for both predictor and response variables. After running a cluster analysis on the scaled TN loading time series (the response variable), the cluster assignment was paired with the slope estimates from the suite of predictor variables tied to the nutrient inventory and static geologic and land use variables. From there, an RF analysis was executed to link trends in anthropogenic driver and other contextual environmental factors to the identified trend cluster types. After calibrating the RF model, likelihood of improving, relatively static, or degrading catchments across the Chesapeake Bay were identified for the 2007 to 2018 period. Tabular data is available on the journal website and PUBMED, and the predictor/response variable data can be downloaded individually in the USGS and Chesapeake Bay Program links listed in the data access section. Portions of this dataset are inaccessible because: This data was generate by other federal entities and are housed in their respective data warehouse domains (e.g., USGS and Chesapeake Bay Program). Furthermore, the data can be accessed on the journal website as well as NCBI PUBMED (https://pubmed.ncbi.nlm.nih.gov/35461100/). They can be accessed through the following means: Combined dataset can be accessed on the journal website (https://www.sciencedirect.com/science/article/pii/S0043135422003979?via%3Dihub#ack0001) and will soon be available on NCBI (https://pubmed.ncbi.nlm.nih.gov/35461100/). The predictor variable data can be accessed from the Chesapeake Bay Program (https://cast.chesapeakebay.net/) and USGS (https://pubs.er.usgs.gov/publication/ds948 and https://www.sciencebase.gov/catalog/item/5669a79ee4b08895842a1d47). Format: Please review Zhang et al. (2021) for details on study design and datasets (https://doi.org/10.1016/j.watres.2022.118443). In summary, predictor and response variable data was acquired from the Chesapeake Bay Program and USGS. This data was subjected to a trend analysis to estimate the MK linear slope change for both predictor and response variables. After running a cluster analysis on the scaled TN loading time series (the response variable), the cluster assignment was paired with the slope estimates from the suite of predictor variables tied to the nutrient inventory and static geologic and land use variables. From there, an RF analysis was executed to link trends in anthropogenic driver and other contextual environmental factors to the identified trend cluster types. After calibrating the RF model, likelihood of improving, relatively static, or degrading catchments across the Chesapeake Bay were identified for the 2007 to 2018 period. Tabular data is available on the journal website and PUBMED, and the predictor/response variable data can be downloaded individually in the USGS and Chesapeake Bay Program links listed in the data access section. This dataset is associated with the following publication: Zhang, Q., J. Bostic, and R. Sabo. Regional patterns and drivers of total nitrogen trends in the Chesapeake Bay watershed: Insights from machine learning approaches and management implications. WATER RESEARCH. Elsevier Science Ltd, New York, NY, USA, 218: 1-15, (2022).

In this data release, we provide data to describe the water quality in Green Lake, Wisconsin, from 1905 to 2020, primarily the constituents for which it is impaired, including near-surface total phosphorus concentrations and metalimnetic dissolved oxygen concentrations, and quantify the water and phosphorus inputs to the lake. We also provide inputs to and outputs from the General Lake Model coupled to the Aquatic Ecodynamics modeling library (GLM-AED) hydrodynamic water-quality model to describe the factors that have caused low dissolved oxygen concentrations in the metalimnion of Green Lake; and quantify how changes in phosphorus loading should affect near-surface total phosphorus and chlorophyll-a concentrations, water clarity, and the minimum dissolved oxygen concentrations in the metalimnion the lake. This data release includes 5 zipped files in child items: (1) Met_Stream_Lake_data, which contains morphology, meteorology, atmospheric deposition, water quality data and mass balance data for the lake; (2) GLM_calibration, which contains inputs to and outputs from the GLM model for which physical parameters in the model were calibrated; (3) GLMAED_Calibration, which contains inputs to and outputs from the GLM-AED model for which physical, chemical, and biological parameters in the model were calibrated; (4) GLMAED_MOMCauses, which contains all of the data needed to run the model to determine the causes of metalimnetic oxygen minima (MOM), and the outputs from the model; and (5) GLMAED_ChangesInPhosphorusLoading, which contains all of the data needed to run the model to determine how dissolved oxygen, near surface total phosphorus, and near-surface chlorophyll-a concentrations respond to changes in phosphorus loading from the watershed, and the outputs from the model.

The primary data set consists of continuous water-quality data (temperature, specific conductance, pH, dissolved oxygen, turbidity, nitrate plus nitrite, and streamflow) from in-situ equipment, and discrete water-quality samples (total nitrogen, total phosphorus, suspended sediment concentration, and suspended sediment sieve diameter) collected during site visits at the USGS streamgage Iroquois River near Foresman, Indiana, April 7, 2015 to July 19, 2018. These continuous and discrete measurements were used to develop regression models which may be used to compute concentrations and loads of total nitrogen and total phosphorus. The secondary data set consists of daily streamflow, daily nitrate, daily turbidity and daily specific conductance values collected continuously by in-situ monitors at Iroquois River near Foresman, Indiana March 20, 2015 to July 19, 2018 which serve as input explanatory variables for the developed regression models to compute total nitrogen and total phosphorus at Iroquois River near Foresman. The tertiary data set for March 20, 2015 to July 19, 2018 is the output data set that was developed by application of the regression models and includes the computed daily mean total nitrogen and total phosphorus concentrations (concentration, upper 95-percent prediction interval, and lower 95-percent prediction interval) and daily mean total nitrogen and total phosphorus loads (load, upper 95-percent prediction interval, and lower 95-percent prediction interval).

Monitoring data from Minnesota and from national surveys of lakes and streams that were used in the analysis for the paper: Predicting lake chlorophyll from stream phosphorus concentrations. mod.mn.R.txt: R script for fitting TP-Chl model using Minnesota data mod.nat.R.txt: R script for fitting TP-Chl model using national data dat.nat.1.csv: National stream TP data dat.nat.2.csv: National lake Chl data dat.mn.1.csv: Minnesota lake Chl data dat.mn.2.csv: Minnesota stream TP data. Citation information for this dataset can be found in Data.gov's References section.