In times of an increasingly uncertain climate and growing demand for water resources, there is a need for assessing how aquatic systems worldwide are responding to co-occurring human and climatic disturbances. Over the past half century, remote sensing technology, high performance and cloud computing infrastructure, machine learning techniques, open data practices, and widened training in computer programming have created extraordinary opportunities to expand aquatic science research across spatial and temporal scales. Remote sensing of chlorophyll concentrations has enabled near-global monitoring of algal blooms. Data science and machine learning methods have empowered the prediction of water quality dynamics, while also informing management actions. Process-based models have improved our understanding of environmental fluid dynamics, which can be consequential for ecosystem regime shifts. Open data practices have increased the amount of publicly available data that many calibration and validation techniques ultimately demand. The nexus of data science, remote sensing, modeling, and open science in the aquatic sciences is a dynamic, rapidly progressing space, where novel aquatic science questions can be answered at unprecedented scales.
Given these developments, there can be a lingering question of “What’s next?” To date, many aquatic remote sensing, modeling, and data science efforts have focused on measuring or predicting individual parameters or variables. While these individual efforts are herculean initiatives, a ripe frontier for this nexus is linking limnological, hydrological, oceanographic, and ecological processes and principles with remote sensing, data science, and modeling techniques to understand fundamental emergent properties of aquatic systems and inform monitoring at local-to-global and subdaily-to-decadal scales. Additionally, the increase of open science and data democratization brings the potential for a more diverse, inclusive, and accessible scientific community and more holistic research.
To build a conversation around multifaceted developments in remote sensing, data science, modeling, and the aquatic sciences, this session invites contributors to share how they use one or a combination of remote sensing, data science, modeling, or open science practices to expand the fields of limnology, oceanography, hydrology, or ecology. We envision this session will host a range of presentation topics, including but not limited to novel methods for atmospheric corrections, scaling of cloud and other high-volume computing environments, assessing water quantity and quality across spatial and temporal scales, quantifying long-term changes in stratification dynamics, merging process-based modeling and deep learning, and applying data-intensive techniques for basic and applied research questions.
While submissions may stem from methodological and technical hurdles encountered in remote sensing and data science fields, we challenge submissions to focus on how their efforts de-silo the aquatic sciences from the remote sensing and data science arenas.
We enthusiastically encourage submissions by early career researchers as well as by researchers from BIPOC, LGBTQIA+, and other marginalized identities. An intentional focus on research that breaks down barriers to entry for underrepresented scientists in the fields of remote sensing and aquatic data science, through open science, will yield insight into the power and potential of the next frontier in emergent properties of aquatic systems.
Lead Organizer: Michael Meyer, U.S. Geological Survey (mfmeyer@usgs.gov)
Co-organizers:
Elisa Calamita, Eawag (elisa.calamita@eawag.ch)
Kate Fickas, Esri (kfickas@esri.com)
Robert Ladwig, University of Wisconsin - Madison (rladwig2@wisc.edu)
Rachel Pilla, Oak Ridge National Laboratory (pillarm1@ornl.gov)
Presentations
09:00 AM
Multi-model analysis of lake chlorophyll-a predictions enabled by open, automated data and modeling workflows (8060)
Primary Presenter: Mary Lofton, Virginia Tech (melofton@vt.edu)
Chlorophyll-a is a key indicator of lake water quality and phytoplankton blooms, motivating the need for predictions of future chlorophyll-a concentrations for management. Advance notice of blooms could enable preemptive actions to mitigate water quality impacts. Despite decades of research, however, accurate prediction of future lake chlorophyll-a remains difficult. Moreover, the application of various predictive modeling approaches across different datasets, waterbodies, and prediction windows (e.g., one-week-ahead vs. seasonal predictions) makes model inter-comparison challenging and hampers identification of the most accurate modeling methods. Here, we compared 25 models predicting chlorophyll-a from 1 to 35 days ahead at a drinking water reservoir, using exactly the same data for each model. Models were fit using 3.5 years of data and validated by generating predictions for an additional year. We found that regardless of model type (e.g., machine learning, process-based), models with an autoregressive component performed best, indicating that real-time chlorophyll-a measurements, which are quickly assimilated into models, may be important for accurate lake chlorophyll-a predictions. Notably, this work was enabled by our team’s implementation of automated data quality assurance and access workflows, which permit easy ingestion of new data into models and ongoing analysis of model performance. Our analysis exemplifies how integration of data science and open science into aquatic research can lead to insight regarding the predictability of lake chlorophyll-a.
09:15 AM
Optimizing HAB Management in Lake Mattamuskeet: Insights from Baseline Monitoring and Multi-Dimensional Data Integration (8435)
Primary Presenter: Gabriel Rozman, BlueGreen Water Technologies (grozman@bluegreenwatertech.com)
Lake Mattamuskeet is the largest natural lake in North Carolina at 40,000 acres. It plays a vital role in serving as habitat for various migratory bird species. The lake is currently facing challenges related to high turbidity, which is exacerbated by HABs, and adversely impacts sub-aquatic vegetation. BlueGreen Water Technologies collaborated with the University of North Carolina Institute of Marine Sciences to conduct a yearlong monitoring study ahead of gaging the efficacy of a mitigation treatment. Goals were: (1) Establish effective scientific based management practices drawn from multi-dimensional data integration, (2) Understand function and limitations of: Water Sensors, S3 satellite analysis, and pigment extraction, and (3) Gain insight into algal bloom dynamics. Results revealed seasonal succession of algal populations with three distinct blooming periods in Spring, Summer, and Autumn. While Cyanobacteria are present throughout the year, the extent varies depending on seasonal driving forces such as temperature and competition. Spring blooms showed higher diversity, while summer blooms showed a significant dominance of Cyanobacteria. These results are critical for understanding and managing HABs, especially in determining when and when not to treat. Targeting the right bloom at the right time may increase the effectiveness of a mitigation treatment and improve diversity and overall health, while treating at the wrong time may have deleterious effects and long-term consequences.
09:30 AM
CyanoSCOPE: an open-source, deep-learning approach to automate cyanobacteria identification and enumeration from microscopy imaging (7820)
Primary Presenter: Tyler Harman, CSS, Inc (Contracted to NOAA NCCOS) (tyler.harman@noaa.gov)
Citizen scientists are crucial in monitoring cyanobacteria harmful algal blooms (cHABs); however, the success of these programs hinges on certain requirements. To ensure user satisfaction and maintain interest, the process of identifying these blooms needs to be rapid, reliable and easy to use. To address this issue, CyanoSCOPE, a deep-learning imaging tool has been developed in the R programming language using Keras and UNet neural network modeling. This tool can identify single-cell and filamentous cyanobacteria from light microscopy images. Automated quantification tools are built from the cellcount library, using tools and functions from EBImage. The current version of CyanoSCOPE can identify Microcystis, Dolichospermum, Anabaena, and Sphaerospermopsis genera. This tool also has built-in identifiers for common freshwater diatoms, chlorophytes, chrysophytes, and cryptophytes; these additional features help demonstrate overall accuracy, precision, and efficiency. An interactive user interface enables users to upload images and apply models seamlessly, and generates identifier data and bloom density metrics. The applications of this tool range from cyanobacteria culture maintenance to endless possibilities within the citizen-science sector where citizens can easily locate, identify and monitor cHABs as they progress. It also eliminates the time-consuming bottleneck of cell identification by microscopy, which can further delay a cHAB response and reduces potential identification discrepancies between taxonomers.
09:45 AM
QUANTIFYING ERROR INTRODUCED BY SPATIOTEMPORAL MISMATCHES IN SATELLITE AND IN-SITU DATA ACQUISITION IN OCEAN COLOR ALGORITHM DEVELOPMENT. (8055)
Primary Presenter: Olivia Cronin-Golomb, ORISE - Environmental Protection Agency RTP (croningolomb.olivia@epa.gov)
In-situ measurements of optically active indicators of water quality are used to develop and validate spatiotemporally robust and cost-effective satellite remote sensing algorithms. Outputs from water quality algorithms routinely inform policymaker decisions that impact environmental well-being, and, consequently, human health and economic stability. Therefore, understanding sources of error in these algorithms and communicating them to managers is crucial for their proper interpretation. Currently, algorithm error is largely attributed to the assumptions inherent in the algorithms themselves. However, the error introduced by temporal mismatch between field and satellite data acquisition is often cited but poorly constrained. In the time between field and satellite data collection, the in-situ surface water parcel that represented the optical conditions of a location at time of sample collection could have traveled outside the bounds of the associated satellite pixel. Here, we assess the possible contributions of this spatiotemporal error by modeling the movement of a surface water parcel over six hours under a variety of wind speeds and directions. We compare the distance and direction traveled to the pixel size of Planet, Sentinel 2, and Sentinel 3 imagery, generating an error estimate for high to coarse resolution imagery under a range of potential sampling conditions. The results of this simulation will clarify a source of disconnect between in-situ and algorithm-derived measurements of water quality, improving stakeholder understanding, communication, and engagement.
10:00 AM
LAKEVIEW: NEW UNDERSTANDING OF LAKE WATER QUALITY THROUGH INTEGRATED EARTH OBSERVING SYSTEMS (8390)
Primary Presenter: Sophia Skoglund, University of Wisconsin–Madison, Center for Limnology (skskoglund@wisc.edu)
Hyperspectral imagery availability is increasing with new and upcoming satellite missions such as NASA’s Plankton, Aerosol, Cloud Ocean Ecosystem (PACE) and Surface Biology and Geology (SBG) missions. Application to lakes could provide valuable insight on water quality, but there are significant challenges interpreting spectral data in terms of biogeochemical parameters and microbial community composition. The LakeView campaign entails simultaneous airborne hyperspectral imaging and comprehensive in situ sampling of Lake Mendota in Madison, WI. With LakeView, we address the questions: Can remotely sensed hyperspectral data provide quantitative retrievals that correlate with in situ observations? Does remotely sensed hyperspectral imagery resolve the spatial and temporal variability in water quality? Biogeochemical data from October 2023 sampling show clear spatial variability, with the two northernmost sites near the mouth of the Yahara River exhibiting the highest levels of inorganic carbon (~1.25x), total nitrogen (~2x), total phosphorus (~1.75x), and chlorophyll (~2x) across the transect. In situ optical characteristics correspond with that transect gradient. We anticipate this gradient to be evident in the microbial community and hyperspectral data currently being processed. Biweekly (weather-dependent) sampling in 2024 will capture the limnological conditions of Lake Mendota as it passes through seasonal phases that have distinct water optical characteristics. The workflow developed here is intended to inform future agency applications of hyperspectral data.
10:15 AM
THE CYANOBACTERIA ASSESSMENT NETWORK'S SUCCESSFUL DELIVERY OF A REMOTE SENSING MONITORING TOOL FOR CYANOBACTERIA BLOOMS. (8420)
Primary Presenter: Bridget Seegers, NASA Ocean Ecology Lab (bridgetseegers@gmail.com)
Satellite remote sensing provides the ability to assess water quality at a broad regional scale and significantly increases the monitoring tools available for water resource managers and researchers. The Cyanobacteria Assessment Network (CyAN) project is an interagency (US-EPA, NASA, NOAA, USGS) that uses satellite remote sensing to support the management and public use of U.S. inland bodies of water by providing a capability to detect and quantify cyanobacteria algal blooms using the Cyanobacteria Index algorithm. The standard CyAN product utilizes data from the Ocean and Land Color Instrument (OLCI) on Sentinel-3 A and -B and is delivered daily and as a weekly composite for over 2,300 lakes across the contiguous United States. This presentation will give details about the algorithm and highlight the ways the CyAN product is delivered to create a user friendly experience from phone and web applications. Additionally, the talk will highlight selected ways states have incorporated the data into their monitoring efforts from action plans to state monitoring criteria. The utility of remote sensing will be demonstrated through CyAN success stories.
SS01A - The Next Frontier in Aquatic Sciences: Linking Remote Sensing, Data Science, Modeling, and Open Science to Understand Ecosystems’ Emergent Properties
Description
Time: 9:00 AM
Date: 5/6/2024
Room: Hall of Ideas G