Continuous monitoring of surface water resources is often challenging due to the lack of monitoring systems in remote areas and the high spatial distribution of water bodies. The Google Earth Engine (GEE) platform, which houses a large set of remote sensing datasets and geospatial processing power, has been applied in various aspects of surface water resources monitoring to solve some of the challenges. PyGEE-SWToolbox is a freely available Google Earth Engine-enabled open-source toolbox developed with Python to be run in Jupyter Notebooks that provides an easy-to-use graphical user interface (GUI) that enables the user to obtain time series of Landsat, Sentinel-1, and Sentinel-2 satellite imagery, pre-process them, and extract surface water using water indices, such as the Normalized Difference Water Index (NDWI), Modified NDWI (MNDWI), Automated Water Extraction Index (AWEI), and Dynamic Surface Water Extent (DSWE). The validation of the toolbox is carried out at four reservoir and lake locations: Elephant Butte Lake, Hubbard Creek Reservoir, Clearwater Lake, and Neversink Reservoir in the United States. A time series of the water surface area generated from PyGEE-SWToolbox compared to the observed surface areas yielded good results, with $R^2$ ranging between 0.63 and 0.99 for Elephant Butte Lake, Hubbard Creek Reservoir, and Clearwater Lake except the Neversink Reservoir with a maximum $R^2$ of 0.52. The purpose of PyGEE-SWToolbox is to provide water resource managers, engineers, researchers, and students a user-friendly environment to utilize the GEE platform for water resource monitoring and generation of datasets. The toolbox is accompanied by a step-by-step user manual and Readme documentation for installation and usage.

Streamflow monitoring for flood warning and watershed management applications in the United States is a cost-intensive venture, and usually performed by government agencies such as the US Geological Survey (USGS). With reduced resources across the federal agencies towards environmental monitoring, agencies and stakeholders are challenged to respond with cross-cutting, collaborative, and low-cost alternatives for streamflow monitoring. One such alternative is using low-cost environmental sensors and developing a real-time gage/sensor network using IoT (Internet of Things) devices. With this technology, smaller watersheds (e.g., HUC-8 and HUC-10 level) can be equipped with low-cost gages at many locations and a clear picture of the hydrological response can be obtained. This paper presents the development and implementation of a low-cost real-time water monitoring network for the Falling Water River (FWR) watershed in the middle Tennessee region in the US. To develop and implement this gage network, the following three tasks were performed: (i) assemble a low-cost, real-time internet enabled water level gage, (ii) field-test the sensor prototype and, (iii) deploy the sensors and build a network. A collaborative partnership was developed with stakeholders including the Tennessee Department of Environment and Conservation, Tennessee Department of Transportation, Burgess Falls State Park, City of Cookeville, and Friends of Burgess Falls. The performance of the gages in water level estimation was compared with the water levels measured with a nearby USGS streamgage. The comparison was performed for the 2020–2022 time period and at two levels: event-based comparison and a long-term comparison. Nine storm events were selected for the comparison, which showed “Very Good” agreement in terms of Coefficient of Determination (R²), Nash–Suttcliffe Efficiency (NSE), and percent bias (PBIAS) (except for four events). The mean squared error (MSE) ranged between 0.07 and 1.06 while the root mean squared error (RMSE) ranged between 3 inches and 12 inches. A long-term comparison was performed using Wilcoxon Signed-Rank test and Loess Seasonal Decomposition analysis, which showed that the differences between the two datasets is not significant and that they trended well across the two year period. The gages are currently installed along the main channel and tributaries of the Falling Water River, which also include portions of the Window Cliffs State Natural Area. With continued support from the stakeholders, the number of sensors are projected to increase, resulting in a dense sensor network across the watershed. This will over time enable the stakeholders to have a spatially variable hydrological response of the Falling Water River Watershed.

Water depth affects many aspects of wetland ecology, hydrology, and biogeochemistry. However, acquiring water depth data is often difficult due to inadequate monitoring or insufficient funds. Satellite-derived bathymetry (SBD) data provides cost-effective and rapid estimates of the water depth across large areas. However, the applicability and performance of these techniques for inland wetlands have not been thoroughly evaluated. Here, a time series of bathymetry data for inland wetlands in West Kentucky and Tennessee were derived from Landsat 8 images using two widely used empirical models, Stumpf and a modified Lyzenga model and three machine learning models, Random Forest, Support Vector regression, and k-Nearest Neighbor. We processed satellite images using Google Earth Engine and compared the performance of water depth estimation among the different models. The performance assessment at validation sites resulted in an RMSE in the range of 0.18–0.47 m and R² in the range of 0.71–0.83 across all models for depths 3.5 m, an RMSE = 1.43–1.78 m and R² = 0.57–0.65 was obtained. Overall, the empirical models marginally outperformed the machine learning models, although statistical tests indicated the results from all the models were not significantly different. Testing of the models beyond the domain of the training and validation data suggested the potential for model transferability to other regions with similar hydrologic and environmental characteristics.

The prevalence of unforeseen floods has heightened the need for more accurate flood simulation and forecasting models. Even though forecast stations are expanding across the United States, the coverage is usually limited to major rivers and urban areas. Most rural and sub-urban areas, including recreational areas such as the Window Cliffs State Natural Area, do not have such forecast stations and as such, are prone to the dire effects of unforeseen flooding. In this study, four machine learning model architectures were developed based on the long short-term memory, random forest, and support vector regression techniques to forecast water depths at the Window Cliffs State Natural Area, located within the Cane Creek watershed in Putnam County, Tennessee. Historic upstream and downstream water levels and absolute pressure were used to forecast the future water levels downstream of the Cane Creek watershed. The models were tested with lead times of 3, 4, 5, and 6 h, revealing that the model performances reduced with an increase in lead time. Even though the models yielded low errors of 0.063–0.368 ft MAE, there was an apparent delay in predicting the peak water depths. However, including rainfall data in the forecast showed a promising improvement in the models’ performance. Tests conducted on the Cumberland River in Tennessee showed a promising improvement in model performance when trained with larger data.

Migratory waterfowl (i.e., ducks, geese, and swans) management relies on landscape bioenergetic models to inform on-the-ground habitat conditions and conservation practices. Therefore, conservation planners rely on accurate predictions of wetland habitats for waterfowl at regional scales. Unharvested flooded corn is a popular management tool on public and private lands that greatly increases landscape-level energy compared to other wetlands; thus, landscape bioenergetic models are particularly sensitive to these habitat features. Despite their importance to conservation planning and implementation, the abundance and distribution of unharvested flooded corn fields across North America is unknown. Furthermore, training data is difficult to collect and accurate predictions are challenging given their unique attributes and discreteness at landscape-level lens. Advances in multispectral imagery and deep learning algorithms may enable continuous and autonomous detection of these habitat features. Therefore, we conducted modeling experiments using training data of unharvested flooded corn fields in West Tennessee and multispectral imagery collected from Sentinel-2 satellite missions. We performed several experiments using individual band combination composites and/or vegetation indices to identify optimal bands using MRUNET architectures. We subsequently used 3 ensemble models of important individual networks. We found the use of multispectral bands was necessary and although the CIR composite and OSAVI index improved precision, the 12-band composite increased recall, the metric we were most interested in. Moreover, all ensembles exhibited poor performance. Here, we present results of our initial modeling experiments and suggest future modeling exercises including temporal image and vegetation index stacking using multi-modal and/or recurrent neural network architectures.