This data release includes digital orthophotos acquired from a fixed-wing aircraft and field measurements of flow velocity and depth from the Tanana and Yukon Rivers, Alaska, obtained July 1 - 3, 2025.  This parent data release includes links to child pages for the data sets produced during the study (see child item links below):1. Digital orthophotos of the Tanana and Yukon Rivers in Alaska acquired from a fixed-wing aircraft on July 2, 2025. 2. Acoustic Doppler Current Profiler (ADCP) field measurements of flow velocity and depth from the Yukon and Tanana Rivers. The Yukon River ADCP measurements were collected on July 1 and 2, 2025. The Tanana River ADCP measurements were collected on July 3, 2025.Please refer to the individual child pages for further detail about each data set.

This data release provides a Compilation of Images from River Reaches across the United States (CIRRUS). These images were retrieved programmatically using the Google Maps Application Programming Interface (API). The data set consists of a total of 281,024 individual images from rivers throughout the contiguous U.S. and Alaska, with an emphasis on locations likely to have rapids. For the purposes this data release, rapids are defined as areas of a river where the water surface is wavy, irregular, or even broken (i.e., whitewater), presumably due to high flow velocities and turbulence, that stand out from adjacent areas of smoother flow and are thus visible in satellite and aerial imagery. The image compilation provided herein was created to support remote sensing and deep learning applications. For example, developing automated tools for recognizing images that contain rapids could help to inform planning of recreational activities, assessment of habitat conditions, and estimation of river discharge.Please refer to the "Entity and attribute" and "Process step" sections of the metadata for further detail regarding these files and how they were produced, but the following is a brief summary of the contents of this data release.The individual images themselves are stored in a *.jpg file format and provided in a series of uncompressed tar folders.The file image_list.csv contains a listing of all the images in CIRRUS with fields for image file name, a root name for each site, the latitude and longitude of the image center, the zoom level, a time stamp for when the image was retrieved from the API, the two- and four-digit hydrologic unit codes (HUCs), the tar folder containing the image, and the predicted probability of the image containing rapids from the rapids classifier model trained on the baseline rapids class dataset (i.e., without masking or active learning).The file rapids_split_regions.csv provides information on which HUC4 regions were assigned to the train, validation, or test subsets when developing and evaluating models for classifying rapids. The two fields in this file are the HUC4 code and rapid_split, which has values of "train", "test", or "val" (short for validation) that indicate which subset the images from that HUC4 were assigned to during the rapids classifier development and testing. This file consists of 227 rows. Of all 245 HUC4 codes, 3 were removed because they are entirely in Mexico (HUC4 1310, 1311, 1312), 9 were removed from HUC2 20 (Hawaii Region), 4 from HUC2 21 (Caribbean Region), and 2 from the HUC22 (South Pacific Region). No images in these removed regions are included in this data release.The file river_mask_labels.csv provides metadata for the image-mask pairs used to train a segmentation model for isolating the river channel within an image. This file contains fields for image file name, a root name for each site, the latitude and longitude of the image center, the zoom level, a time stamp for when the image was retrieved from the API, a binary variable indicating that the image has a mask (1 in all cases for this file), the two- and four-digit hydrologic unit codes (HUCs), and a field named rapid_split that indicates whether the image was used for training, validation, or testing using the HUC4-based train-test-validation split described above because the same approach was used for developing the segmentation models as well.The file river_mask_dataset.tar is an uncompressed tar file containing 885 image-mask pairs used to train the river segmentation model. The images are stored as 640x640 JPEGs, and the masks are stored as bit-compressed NumPy arrays (NPY). When extracted from the tar file, the masks can be loaded into Python using this code (replacing mask_path with the name of a specific mask): mask = np.load("mask_path.npy"); mask = np.unpackbits(mask, axis=-1).The file rapids_labels.csv provides metadata for the images used to train a model for classifying the presence or absence of rapids within an image. This file contains fields for image file name, a root name for each site, the latitude and longitude of the image center, the zoom level, a time stamp for when the image was retrieved from the API, a binary variable indicating whether a water mask was available for the image, a binary variable indicating whether the image contains rapids, the two- and four-digit hydrologic unit codes (HUCs), a field named rapid_split that indicates whether the image was used for training, validation, or testing using the HUC4-based train-test-validation split described above, a binary field indicating whether the image was labeled through active learning, and a binary field indicating whether a mask had been applied to the image.The file rapids_label_dataset.tar is an uncompressed tar file containing 4,975 images that have been labeled as rapids or non-rapids. The labels for this dataset are stored in rapids_labels.csv. This dataset includes 4,465 unmasked images. 510 of those images also appear as masked images, which are denoted by appending an "m" to the end of the file name. The masked images occur only in the train split (no validation or test images have masked counterparts).The file known_rapids_locations.tar is an uncompressed tar file containing images from locations with known rapids based on the National Hydrography Dataset and an OpenStreetMap rapids layer.The file File_Overview.csv contains a brief summary of the code developed to process the images included in this data release and to develop segmentation models for producing river masks and classification models for identifying rapids. The fields in this file include the folder name within the rapid-detection-collection-code-release.zip zip folder, code file name, and a brief description of the purpose of each code file.The file rapid-detection-collection-code-release.zip is a zip folder that contains all the code files described in File_Overview.csv as well as a README.txt file that provides guidance on how to use the code.Users are advised to thoroughly read the metadata file associated with this data release to understand the appropriate use and limitations of the data provided herein.Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.Although this information product, for the most part, is in the public domain, the data set also contains copyrighted materials as noted on the watermark for each image obtained using the Google Maps API. Permission to reproduce copyrighted items must be secured from the copyright owner. The following entities retain copyright on all images: "© 2025 Airbus, Maxar Technologies, USDA FPAC/GEO".

This data release provides field measurements of water depth and aerial and satellite images from the Mulchatna River in Alaska. These data were used to assess the feasibility of mapping the bathymetry of this remote, proglacial river, located in Lake Clark National Park and Preserve, using several depth retrieval algorithms. This approach could facilitate geomorphic and habitat monitoring by agencies tasked with managing remote, hard to access landscapes, like the National Park Service. This project is a collaboration between the National Park Service's Water Resources Division and Alaska Regional Office and the USGS Observing Systems Division.Please refer to the "Entity and attribute" and "Process step" sections of the metadata for further detail regarding these files and how they were produced, but the following is a brief summary of the contents of this data release. The NAD_1983_2011_StatePlane_Alaska_5_FIPS_5005 projected coordinate system is used throughout and the coordinates and depths have units of meters.The file MulchatnaDepthFieldData.csv contains field measurements of water depth, with columns for easting and northing spatial coordinates and depths.The files MulchatnaXS1adcp.zip and MulchatnaXS2adcp.zip contain acoustic Doppler current profiler (ADCP) data from two cross sections where discharge measurements were made. Each zip folder contains MATLAB *.mat files that were exported from the SonTek RSQ software package, with a separate *.mat file for each of four passes across the channel. In addition, the output *.mat files produced by the QRev software (described in the Process Step section of the metadata) with calculated discharges and uncertainties are also included in the two zip folders. Please note that these discharge measurements were not made in accordance with standard USGS protocols and did not include compass calibrations, system checks, or temperature checks and assumed that the edges of the channel closer to the banks than the end of each ADCP transect made no contribution to the total discharge.The file ReachMasks.zip contains channel masks created by digitizing polygons on the orthomosaic derived from the aerial imagery. The polygons were saved as individual shapefiles for the full study area and for each of the three reaches.The file WVgeorefSubsets.zip contains geo-referenced WorldView2 satellite image subsets for the full study area and for each of the three reaches, saved as ENVI .dat files with associated header (.hdr) files.The file MulchDSMsub.tif is a digital surface model (DSM) derived from aerial imagery acquired by the National Park Service and processed using a structure-from-motion workflow, saved in a GeoTIFF format. Note that this DSM is not referenced to an established vertical coordinate system and elevations within the DSM are only accurate relative to one another. These data were only used for estimating local channel slopes and should not be used as absolute elevations for other purposes.The file MulchSubMos.tif is an orthomosaic derived from aerial imagery acquired by the National Park Service and processed using a structure-from-motion workflow, saved in a GeoTIFF format.Users are advised to thoroughly read the metadata file associated with this data release to understand the appropriate use and limitations of the data provided herein.Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.Although this information product, for the most part, is in the public domain, it also may contain copyrighted materials as noted in the text. Permission to reproduce copyrighted items must be secured from the copyright owner. MAXAR retains the copyright on all the images: "© 2024 MAXAR".

This data release provides aerial images acquired through the National Agricultural Imagery Program (NAIP) used to test a method for inferring image acquisition time from shadow orientation. For many applications, such as linking remotely sensed data to streamflow recorded at a gaging station, knowing the time an image is acquired is important, but such metadata often is not available. The sundial method is a simple means of inferring image acquisition time from shadow orientation. Images with known acquisition times are used to test the approach. The file SundialDataReleaseNAIP.csv contains image metadata, shadow measurements, and inferred image acquisition times based on the sundial method. The difference between the known acquisition times of the aerial images and those inferred via the sundial technique is used to assess the accuracy of the method. Please refer to the entity and attribute section of the metadata for further detail regarding this file. To facilitate plotting, this information is also provided in a shapefile that contains the same attributes as the file SundialDataReleaseNAIP.csv but represents the digitized shadows as line features. The shapefile is named ShadowLinesNAIP.shp and is packaged in a zip file named ShadowLinesNAIP.zip. The zip file also contains a .prj file that defines the coordinate reference system of the shapefile as geographic coordinates (latitude and longitude) in the NAD83 datum. The file SundialImagesNAIP.zip contains 6 NAIP aerial images with known acquisition times that were used to test the sundial method. Each image is provided in a GeoTIFF format that includes embedded spatial referencing information. Users are advised to thoroughly read the metadata file associated with this data release to understand the appropriate use and limitations of the data and code provided herein. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.

A Cessna 182 fixed-wing aircraft equipped with a multispectral camera was used to collect aerial imagery of selected river reaches within the Willamette River Integrated Water Science basin in Oregon. On April 16-18, 2024, image acquisition was focused on four reaches of the Clackamas River. Photogrammetry techniques were applied to the images consisting of visible or red, green, and blue (RGB) spectral bands, a near-infrared (NIR) spectral band, and a long-wave infrared (LWIR) spectral band to produce orthomosaic maps of each study reach along the Clackamas River. The resulting orthomosaic maps are provided as cloud optimized GeoTIFF files. The spatial resolution, pixel size, of the visible (RGB) and the color infrared (abbreviated CIR and including NIR, red, and green bands), orthomosaic maps is 0.09 meters for all study reaches. The pixel size of the long-wave infrared (LWIR) orthomosaic maps varied between 0.54 and 0.61 meters among the four study reaches. The long-wave infrared camera was not calibrated for absolute temperature so the raster values of these images are expressed as digital counts.

A series of field measurements of surface water velocity derived from video and Doppler velocity radar collected by small unoccupied aircraft systems (sUAS) and portable sensors were collected at seven locations in Colorado, USA, during the summer of 2023. The measurements were utilized to compute surface velocity and discharge using the Probability Concept, Large-Scale Particle Image Velocimetry (LSPIV), and Space-Time Image Velocimetry (STIV) methods. This data release includes the original videos, radar spectra, and ancillary data necessary to produce the surface water velocity and streamflow results. Data are grouped into sections (child items) based on the data type and purpose:Ancillary Scripts: this child item contains Microsoft Windows batch and Python script files that reproduce the processing steps used for specific files associated with image calibration, collating video metadata, and extraction of velocity data from associated hydroacoustic discharge measurements.Calibration Images: this child item contains images with labeled ground control points and associated pixel coordinate locations for each dataset. The images are used to calibrate image velocimetry results into real-world units (meters, for example). The images also indicate the pixel positions corresponding to the location of the streamflow measurement cross-section used for each dataset.Cross Section Geometry: this child item contains the bathymetry cross-sectional survey information for each dataset.Discharge Measurements: this child item contains the raw acoustic Doppler velocity profiler (ADCP) and acoustic Doppler velocimeter (ADV) measurements collected by U.S. Geological Survey hydrographers at each site to validate image and Doppler radar velocimetry results.Ground Control: this child item contains point correspondence information for each field site. The point real-world coordinates and their respective pixel locations are included.Radar Spectra: this child item contains Doppler velocity radar spectra values for selected field sites.Videos: this child item contains the raw videos captured by sUAS for selected field sites.Each Field Site is abbreviated in various files in this data release. File and folder names quickly identify which site a particular file or dataset represents. The following abbreviations are used:ACS: Anthracite Creek at Somerset, Colorado, USABRA: Blue River below Dillon, Colorado, USA (collected in August 2023)BRJ: Blue River below Dillon, Colorado, USA (collected in June 2023)CRG: Colorado River below Glenwood Springs, Colorado, USACRR: Colorado River above Roaring Fork River at Glenwood Springs, Colorado, USAERW: Eagle River below Milk Creek near Wolcott, Colorado, USAMCA: Maroon Creek near Aspen, Colorado, USARFG: Roaring Fork at Glenwood Springs, Colorado, USAThe ERW and RFG sites contain radar spectra but not associated image velocimetry data, and the CRG site contains image velocimetry data but no associated radar spectra.

Information on water depth in river channels is important for a number of applications in water resource management but can be difficult to obtain via conventional field methods, particularly over large spatial extents and with the kind of frequency and regularity required to support monitoring programs. Remote sensing methods could provide a viable alternative means of mapping river bathymetry (i.e., water depth). The purpose of this study was to develop and test new, spectrally based techniques for estimating water depth from satellite image data. More specifically, a neural network-based temporal ensembling approach was evaluated in comparison to several other neural network depth retrieval (NNDR) algorithms. These methods are described in a manuscript titled "Neural Network-Based Temporal Ensembling of Water Depth Estimates Derived from SuperDove Images" and the purpose of this data release is to make available the depth maps produced using these techniques. The images used as input were acquired by the SuperDove cubesats comprising the PlanetScope constellation, but the original images cannot be redistributed due to licensing restrictions; the end products derived from these images are provided instead. The large number of cubesats in the PlanetScope constellation allows for frequent temporal coverage and the neural network-based approach takes advantage of this high density time series of information by estimating depth via one of four NNDR methods described in the manuscript:Mean-spec: the images are averaged over time and the resulting mean image is used as input to the NNDR.Mean-depth: a separate NNDR is applied independently to each image in the time series and the resulting time series of depth estimates is averaged to obtain the final depth map.NN-depth: a separate NNDR is applied independently to each image in the time series and the resulting time series of depth estimates is then used as input to a second, ensembling neural network that essentially weights the depth estimates from the individual images so as to optimize the agreement between the image-derived depth estimates and field measurements of water depth used for training; the output from the ensembling neural network serves as the final depth map.Optimal single image: a separate NNDR is applied independently to each image in the time series and only the image that yields the strongest agreement between the image-derived depth estimates and the field measurements of water depth used for training is used as the final depth map.MATLAB (Version 24.1, including the Deep Learning Toolbox) source code for performing this analysis is provided in the function NN_depth_ensembling.m and the figure included on this landing page provides a flow chart illustrating the four different neural network-based depth retrieval methods.To develop and test this new NNDR approach, the method was applied to satellite images from three rivers across the U.S.: the American, Colorado, and Potomac. For each site, field measurements of water depth available through other data releases were used for training and validation. The depth maps produced via each of the four methods described above are provided as GeoTIFF files, with file name suffixes that indicate the method employed: X_mean-spec.tif, X_mean-depth.tif, X_NN-depth.tif, and X-single-image.tif, where X denotes the site name. The spatial resolution of the depth maps is 3 meters and the pixel values within each map are water depth estimates in units of meters.

A reach of the Sacramento River near Glenn, California, was selected as a field site to test a sensor payload developed by the U.S. Geological Survey and the National Aeronautics and Space Administration for estimating surface flow velocities in rivers. The payload, called the River Observing System (RiOS), can be deployed from an uncrewed aircraft system (UAS). RiOS includes visible and thermal cameras, a laser range finder, an inertial navigation system, an embedded computer for storing and processing data, and a wireless link for transmitting data to a ground station. This data release includes thermal imagery acquired by RiOS and stored in Robot Operating System (ROS) *.bag files. The bag files are organized into two separate zip archives, one for each date of data collection. Foxglove Studio, an open-source data visualization tool, can be used to view the thermal images contained within the bag files (see link in Related External Sources). Once the thermal bag file is loaded in Foxglove Studio, open the settings and set the color mode to gradient and the minimum and maximum values to 12,000 and 15,000, respectively (see Foxglove.jpg in Attached files). The minimum and maximum values can be adjusted from these default values to enhance image contrast.The thermal images were used as input to an image velocimetry algorithm to estimate the surface flow velocities along the river. To assess the accuracy of these image-derived velocity estimates, field measurements of flow velocity were obtained using a SonTek M9 acoustic Doppler current profiler (ADCP) using the RiverSurveyor Live software package. ADCP measurements were collected along multiple pre-planned cross section lines oriented perpendicular to the primary downstream flow direction. At each transect, multiple ADCP passes were made and the data was then processed using the Velocity Mapping Toolbox (VMT) to produce mean cross sections (Parsons et al., 2013). The output from VMT consisted of a single comma delimited text file with the following seven column headers: 1) xs: the river transect stationing in meters; 2) x_meters: easting (x) spatial coordinate in meters; 3) y_meters: northing (y) spatial coordinate in meters; 4) depth_meters: depth in meters; 5) vmag_meters_per_second: the depth-averaged velocity magnitude in meters per second; 6) u_meters_per_second: east (u) component of the depth-averaged velocity vector in meters per second; and 7) v_meters_per_second: northing (v) component of the depth-averaged velocity vector in meters per second. The spatial coordinates are projected in Universal Transverse Mercator (UTM) Zone 10, World Geodetic System 1984 (WGS-84) datum.

A reach of the North Santiam River, Oregon, was used as a case study in an ongoing effort to develop and test uncrewed aircraft system (UAS)-based salmon habitat mapping techniques using: (1) particle image velocimetry (PIV) for estimating surface flow velocities from remotely sensed data; and (2) two-dimensional (2D) flow modeling based on remotely sensed topography and bathymetry (topo-bathymetry). Direct measurements of flow velocity were obtained using an acoustic Doppler current profiler (ADCP) and used to assess the accuracy of the image-derived velocity estimates and modeled flow fields. Water depth was measured using a single beam echosounder and was used to calibrate and validate image-derived depth estimates and to test the accuracy of the flow model. The topography of dry land and water surface elevations were measured using UAS-based near-infrared (NIR) light detection and ranging (lidar) data. River bathymetry was mapped by applying a spectrally based depth retreival algorithm to multispectral image data. Video was acquired from a small UAS and used as input to a PIV algorithm. The in situ velocity measurements were collected using a SonTek M9 RiverSurveyor ADCP deployed from a cataraft. The SonTek RiverSurveyor Live software package was used to set up the ADCP prior to data collection, control the instrument, view the data in real-time, and save the raw data in MATLAB .mat data files. A total of four passes back and forth across the channel were completed at seven cross sections located within the field of view of the UAS-based videos. These files were then read into the USGS Velocity Mapping Toolbox (VMT) and further processed to combine the four passes into a single mean cross section and compute depth-averaged velocities (Parsons et al., 2013). The VMT output was summarized by creating a single csv file consisting of a header row with variable names and five columns: 1) East_meters: easting (x) spatial coordinate in meters; 2) North_meters: northing (y) spatial coordinate in meters; 3) velU_meters_per_second: east (u) component of the depth averaged velocity vector in meters per second; 4) velV_meters_per_second: north (v) component of the depth averaged velocity vector in meters per second; and 5) velMag_meters_per_second: velocity magnitude in meters per second. The spatial coordinates are in the UTM Zone 10 projection, WGS84 datum. The depth measurements in this data release were obtained using a single beam echosounder and are provided in a comma-delimited (.csv) text file with three columns: East_meters, North_meters, Depth_meters; the units of the spatial coordinates and the depths are meters. The spatial coordinates of the depth data are in the UTM Zone 10 projection, WGS84 datum. NIR lidar data on the North Santiam River were acquired on July 25, 2022, to measure elevations on dry land and the water surface, and to support the development of a 2D flow model. These data were collected using a Qube240 lidar scanner. The Qube240 uses a YellowScan UltraSurveyor lidar scanner integrated with an Applanix 15 inertial navigation system (INS).  The data were acquired from a Quantum-Systems Trinity F90+ UAS platform and were used to produce an interpolated topographic raster Digital Elevation Model (DEM's) with a 1 m cell size in GeoTiff format. The map projection and datum for the lidar contained in this data release is UTM Zone 10 N and NAD83. Multispectral imagery data on the North Santiam River were acquired on July 25, 2022, to map river bathymetry, which is a required input for flow modeling. These data were collected using a MicaSense RedEdge-MX camera, which is integrated with the Trinity F90+ UAS platform. The RedEdge-MX is a radiometrically-calibrated spectral imager with ten bands between 400 and 900 nm. The redEdge-MX multispectral imagery had pixel sizes of 0.085 m at a flying height of 120 m, and an orthoimage is provided in GeoTiff format.  The multispectral image was used to map water depth using the Optimal Band Ratio Analysis spectrally based depth retrieval algorithm (Legleiter and Harrison, 2019). The map projection and datum for the multispectral image contained in this data release is UTM Zone 10 N and NAD83. Following completion of the depth mapping, we subtracted the image-based depth estimates from the lidar water surface to convert depths to bed elevations using the approach implemented in the ORByT software package (Legleiter, 2021). We fused the bathymetry data with the lidar elevations on dry land to make a continuous DEM, with a resolution of 1 m. The hybrid topographic DEM is provided in this data release as a csv file, file with three columns: East_meters, North_meters, Elevation_meters; the units of the spatial coordinates and the elevation are meters. The map projection and datum for the DEM contained in this data release is UTM Zone 10 N and NAD83. The DEM contained in this data release was used as input to develop a two-dimensional (2D) hydrodynamic model using the Delft3D-Flexible Mesh (Delft3D-FM, 2023.02 release) model developed by Deltares (2024). We used a curvilinear grid with a cell size of 1 m and included a spiral flow parameter, which accounts for the effects of secondary flow induced by streamline curvature. We set the time step to ensure a Courant number less than 0.7, and specified a minimum depth for wetting/drying calculations of 0.05 m. We prescribed an upstream discharge of 25 m3/s and ran steady flow simulations. To account for turbulence in the model, we used a uniform eddy viscosity value of 0.15 m2/s. The flow resistance was defined using a uniform roughness height (ks) which was converted to spatially explicit Chezy C coefficients via the Colebrook-White equation. Additional Delft3D-FM model input values are provided as a supplemental (*.csv) text file. Seven UAS-based videos were acquired from a DJI Matrice 210 quadcopter equipped with a Zenmuse X4S optical camera on July 25, 2022. The videos were acquired from a nominal flying height of 120 meters above ground level and are provided in their native form, with a frame rate of 30 Hertz and an *.mov file format. The videos were used to estimate surface flow velocities via PIV, as implemented in the TRiVIA software package (Legleiter and Kinzel, 2023). References cited:Deltares. 2024. Delft3D Flexible Mesh Suite User Manual. Delft, Netherlands: Deltares. Available from: https://www.deltares.nl/en/software/delft3d-flexible-mesh-suite/. Legleiter, C. J., and Harrison, L. R. (2019). Remote Sensing of River Bathymetry: Evaluating a Range of Sensors, Platforms, and Algorithms on the Upper Sacramento River, California, USA. Water Resources Research, 55(3), 2142–2169. https://doi.org/10.1029/2018WR023586 Legleiter, C. J. (2021). The optical river bathymetry toolkit. River Research and Applications, 37(4), 555–568. https://doi.org/10.1002/rra.3773 Legleiter, C. J., and Kinzel, P. J. (2023). The Toolbox for River Velocimetry using Images from Aircraft (TRiVIA). River Research and Applications, 39(8), 1457–1468. https://doi.org/10.1002/rra.4147 Parsons, D. R., Jackson, P. R., Czuba, J. A., Engel, F. L., Rhoads, B. L., Oberg, K. A., Best, J. L., Mueller, D. S., Johnson, K. K., and Riley, J. D. 2013. Velocity Mapping Toolbox, VMT: a processing and visualization suite for moving-vessel ADCP measurements. Earth Surface Processes and Landforms, 38(11), 1244–1260. https://doi.org/10.1002/esp.3367

This dataset is a collection of hyperspectral imagery profiles of algae, many associated with Harmful Algae Blooms (HABs). Data were collected using a microscope-based hyperspectral imaging system with the cooperation of the National Institute of Standards and Technology. Samples were collected from U.S. Geological Survey (USGS) water quality sampling efforts, to include water quality parameters and algal biomass. Data are shown in basic hyperspectral imagery form, normalized to 1.