Floods are one of the most devastating and costly natural disasters, posing a significant threat to human life and property, and necessitating systematic and timely response to flood risks. While most floods cannot be prevented, they can be detected, and a quick response can greatly reduce the consequences. Recent advancements in artificial intelligence, computing power, and earth observation data availability has enabled researchers to use computer vision and satellite/aerial imagery to help assess ground conditions and decision-makers’ prioritization of response efforts. This paper investigates different algorithmic design decisions to determine best flood line detection performance. We also investigated the value of adding non-imagery proxy data used for flood prediction into a computer vision pipeline, which includes the combination of Height Above Nearest Drainage (HAND)-based inundation map data and aerial imagery to train a semantic segmentation convolutional neural network. In our experiments, we trained several U-Net shaped fully convolutional neural networks using aerial imagery of hurricane Harvey retrieved from the National Oceanic and Atmospheric Administration (NOAA) repositories, and rasterized HAND map data retrieved from The Texas Advanced Computing Center (TACC). The paper contributes by showcasing the results of combining both a hydrologic and computer vision method for flood detection.

We have developed a framework for crisis response and management that incorporates the latest technologies in computer vision (CV), inland flood prediction, damage assessment and data visualization. The framework uses data collected before, during, and after the crisis to enable rapid and informed decision making during all phases of disaster response. Our computer-vision model analyzes spaceborne and airborne imagery to detect relevant features during and after a natural disaster and creates metadata that is transformed into actionable information through web-accessible mapping tools. In particular, we have designed an ensemble of models to identify features including water, roads, buildings, and vegetation from the imagery. We have investigated techniques to bootstrap and reduce dependency on large data annotation efforts by adding use of open source labels including OpenStreetMaps and adding complementary data sources including Height Above Nearest Drainage (HAND) as a side channel to the network's input to encourage it to learn other features orthogonal to visual characteristics. Modeling efforts include modification of connected U-Nets for (1) semantic segmentation, (2) flood line detection, and (3) for damage assessment. In particular for the case of damage assessment, we added a second encoder to U-Net so that it could learn pre-event and post-event image features simultaneously. Through this method, the network is able to learn the difference between the pre- and post-disaster images, and therefore more effectively classify the level of damage. We have validated our approaches using publicly available data from the National Oceanic and Atmospheric Administration (NOAA)'s Remote Sensing Division, which displays the city and street-level details as mosaic tile images as well as data released as part of the Xview2 challenge.

New crisis response and management approaches that incorporate the latest information technologies are essential in all phases of emergency preparedness and response, including the planning, response, recovery, and assessment phases. Accurate and timely information is as crucial as is rapid and coherent coordination among the responding organizations. We are working towards a multipronged emergency response tool that provide stakeholders timely access to comprehensive, relevant, and reliable information. The faster emergency personnel are able to analyze, disseminate and act on key information, the more effective and timelier their response will be and the greater the benefit to affected populations. Our tool consists of encoding multiple layers of open source geospatial data including flood risk location, road network strength, inundation maps that proxy inland flooding and computer vision semantic segmentation for estimating flooded areas and damaged infrastructure. These data layers are combined and used as input data for machine learning algorithms such as finding the best evacuation routes before, during and after an emergency or providing a list of available lodging for first responders in an impacted area for first. Even though our system could be used in a number of use cases where people are forced from one location to another, we demonstrate the feasibility of our system for the use case of Hurricane Florence in Lumberton, North Carolina.

Winds are a dominant source of energy for driving motions at the ocean surface. Currents form in the upper layers of the ocean driven by the wind and earth's rotation and generally follow the large-scale wind patterns. The combination of currents in the ocean basins form subtropical gyres that are characterized by intense western boundary currents and eastern boundary currents that are important upwelling zones.

As standards in best practices in data quality assurance and quality control evolve, methods for discovery and transport of information relating to these practices must also be developed. An observation’s history, from sensor descriptions, processing methods, parameters and quality control tests to data quality flags and sensor alert flags, must be accessible through standards-based web services to enable machine-to-machine interoperability. This capability enables a common understanding and thus an underlying trust in the expanding world of ocean observing systems. For example, a coastal observatory conducts several tests to evaluate and improve the quality of in situ time series data (e.g. velocity) and then generate an oceanic property (e.g. wave height). Using content-rich webenabled services, a data aggregation center will be able to determine which tests were conducted, interpret data quality flags and provide value added services, such as comparing the parameter with those from near-by observations. These additional processing steps may also be documented and sent along with the data to other participating ocean observing systems throughout the world. By utilizing standards-based protocol (Open Geospatial Consortium (OGC) frameworks) and welldefined community adopted QA/QC (Quality Assurance/Quality Control) tests and best-practices (Quality Assurance in Real-Time Oceanographic Data QARTOD), information about the system provenance, sensor and data processing history needn’t be lost. Are data providers ready, willing and able to describe sensors and processing history? And can we transport the information using a framework that offers semantic and syntactic interoperability? The group developing this community white paper has demonstrated that it can be and is being done. A project called Q2O, QARTOD to OGC (Open Geospatial Consortium), bridges the QARTOD community with the OGC community to demonstrate and document best practices in the implementation of QA/QC within the OGC Sensor Web Enablement (SWE) framework. This paper describes this demonstration project and documents the existence of parallel related efforts. With adequate funding to enable the strengthening and broadening of these communities, a solid foundation for ocean observing systems will be built with the assurance that best-practices of data quality are communicated in a meaningful way.

Extreme tides and large, battering waves have the potential to cause hazardous conditions along the sandy southwest coasts of Maine and New Hampshire. Increasing storm tides inundate low lying areas, while building waves lead to beach erosion and structural damage. The combined effects of these dynamical forces are complex and not fully understood. According to a recent Northern New England coastal flood climatology (Cannon 2007), damage often occurred during Nor'easters despite tide levels significantly below the Portland Harbor flood stage of 12.0 ft. The empirical relationship between storm tides and large, battering waves demonstrated the need to create a forecast prediction scheme based on impact and not solely on water level. Hourly forecasts of water level and near-shore waves were plotted simultaneously to visually display oceanographic conditions on a single diagram. The East Atlantic Water Level Forecast (ADCIRC) and Wave Watch III models were used to produce the output. The result is a web-based coastal flood nomogram, which is produced twice daily at www.gomoos.org. When animated, users can monitor for critical splash-over and coastal flood benchmarks as thresholds are exceeded. The tool assists meteorologists and emergency managers in the forecast and hazard mitigation process.

Key to the appropriate use of data is the knowledge of data quality. This knowledge is critical for products and decision-support tools that utilize real-time data, and it is also essential for the longer term application of data as well. Guidance by the National Archives and Records Administration (NARA) for appraising observational data for archive states that factors favoring long-term or permanent retention include the uniqueness, completeness, and quality of observational data and the quality and completeness of metadata [1]. The National Oceanographic Data Center (NODC), the designated archive center for oceanographic data in the U.S., requires that data submitted be documented to enable secondary use and ensure data posterity. Such metadata should include not only geospatial characteristics and time periods of observations, but also the collection methods, instrumentation used, units of measure, acceptable values, error tolerance, processing history, quality assessments and explanations of quality flags, data aggregation methods, and other pertinent information [2]. Providing this information in a consistent manner can be a challenge. However, an approach to capturing and conveying this metadata using community-developed practices for ocean observing system data and metadata is well underway.This paper presents methods of capturing data and provenance of data quality using the Open Geospatial Consortium (OGC) Sensor Web Enablement (SWE) framework. It describes the types of metadata content captured and demonstrates the utility and significance of defining and registering terms to enable semantic, as well as syntactic, interoperability. The SWE framework provides an avenue for conveying quality flags and methods used to make assurances about the integrity of oceanographic data for real-time consumption and for potential submittal to permanent archives such as NODC.

Communities that want to share information often do not know enough about the available standards or how to choose the best one. One is example is marine communities that want to share observation data. Even selecting a standards body, such as the Open Geospatial Consortium (OGC), is not enough. For example, OGC has more than one standard that could potentially be used to publish time series data: sensor observation service (SOS), Web feature service (WFS) and Web coverage service (WCS). To better assess these standards requires testing and evaluation in end-to-end demonstrations. An end-to end prototype spans from publishing sensor deployment information to visualizing in a Web client data from a remote Web service. OOSTethys is a community initiative that has been advancing standardized components in end-to-end prototypes for marine observations. OOSTethys participants initiated an OGC Ocean Science Interoperability Experiment (Oceans IE) in 2007, to advance the interoperability of ocean observing systems by using OGC standards. The Oceans IE Phase I investigated the use of WFS and SOS for representing and exchanging point data records from fixed in-situ marine platforms. The study found that 1) SOS contains the necessary components to represent observations, not only from sensors, but also from sensor systems; 2) communities that adopt SOS instead of WFS will not be required to create and maintain their own specifications, which specify the rules of encoding, such as XML schemas; and, 3) the SOS model and weak typing approach provides a sufficient balance to allow general structure and community semantics to co-exist; however, this requires an effort in creating and maintaining controlled vocabularies by marine communities. The result is not only relevant to the marine community but to any community that is sharing geo-spatial observations.

The utility and cost-effectiveness of instrument networks are enhanced by instrument interoperability. Today's oceanographic instruments are characterized by very diverse non-standard software protocols and data formats. This diversity of protocols poses serious challenges to integration of large-scale sensor networks. Standard instrument protocols are now being developed to address these challenges. Some of these standards apply at the IP-network level and enable integration of existing "lower level" proprietary instrument protocols and software components. Other approaches are intended to be implemented by the instrument device itself. These native instrument protocol standards offer the possibility of more uniform and simpler system architectures. We compare these various approaches, describe how they can be combined with one another, and describe some prototypes that implement them.

Fundamental to sustaining the financial support of a coastal ocean observing system is an intimate knowledge of users and their decision-making processes in order to maximize the worth of ocean observations to them. This article explores the evolving mission of GoMOOS (the Gulf of Maine Ocean Observing System), its costs of providing near real-time observations and observing products, possible methods to assess the benefits of an ocean observing system, and a method for indexing the importance - and thus, potentially, the economic value - that users attach to these observations and products.

The SURA Coastal Ocean Observing and Prediction (SCOOP) program is using geographical information system (GIS) technologies to visualize and integrate distributed data sources from across the United States and Canada. Hydrodynamic models are run at different sites on a developing multi-institutional computational Grid. Some of these predictive simulations of storm surge and wind waves are triggered by tropical and subtropical cyclones in the Atlantic and the Gulf of Mexico. Model predictions and observational data need to be merged and visualized in a geospatial context for a variety of analyses and applications. A data archive at LSU aggregates the model outputs from multiple sources, and a data-driven workflow triggers remotely performed conversion of a subset of model predictions to georeferenced data sets, which are then delivered to a Web Map Service located at Texas A&M University. Other nodes in the distributed system aggregate the observational data. This paper describes the use of GIS within the SCOOP program for the 2005 hurricane season, along with details of the data-driven distributed dataflow and workflow, which results in geospatial products. We also focus on future plans related to the complimentary use of GIS and Grid technologies in the SCOOP program, through which we hope to provide a wider range of tools that can enhance the tools and capabilities of earth science research and hazard planning. Copyright © 2008 John Wiley & Sons, Ltd.

The Southeastern Universities Research Association (SURA) has advanced the SURA Coastal Ocean Observing and Prediction (SCOOP) program as a multi-institution collaboration to design and prototype a modular, distributed system for real-time prediction and visualization of the coastal impacts from extreme atmospheric events, including hurricane inundation and waves. The SCOOP program vision is a community “cyberinfrastructure” that enables advances in the science of environmental prediction and coastal hazard planning. The system architecture is a coordinated and distributed network of interoperable, modularized components that include numerical models, information catalogs, distributed archives, computing resources, and network infrastructure. The components are linked over the Internet by standardized web-service interfaces in a service-oriented architecture (SOA). The design philosophy allows geographically disparate partnering institutions to provide complementary data-provider and integration services. The overall system enables coordinated sharing of resources, tools, and ideas among a virtual community of coastal and computer scientists. The distributed design builds on the notion that standards enable innovation, and seeks to leverage successes of the World Wide Web by creating an environment that nurtures interaction between the research community, the private sector, and government agencies working together on behalf of the nation.

The economically important Louisiana Coastal Area (LCA) is susceptible to hurricane activity which is increasingly aggravated by the continuing erosion of wetlands. Various programs are aimed at building sophisticated models of meteorological, coastal, and ecological processes. The emerging paradigm of Dynamic Data Driven Application Systems (DDDAS) can be applied to these models leading to new scenarios for integrated, real-time simulations that include feedback control with sensors and simulations. This paper describes the motivation and components for a comprehensive DDDAS for coastal and environmental modeling and the implications this has for scientific libraries and high performance computing.

1 Center for Computation & Technology, Louisiana State University, Baton Rouge, LA 70803, USA, 2 Department of Computer Science, Louisiana State University, Baton Rouge, LA 70803, USA, 3 Southeastern Universities Research Association, 1201 New York Avenue, Washington, D.C 20005, USA 4 GoMOOS, 350 Commercial Street, Portland, ME 04101, USA 5 Academy for Advanced Telecommunications, 3139 TAMU, Texas A&M University, College Station, TX 77843-3139, USA 6 Wetland Biogeochemistry Institute, Department of Oceanography and Coastal Science, Louisiana State University, Baton Rouge, LA 70803, USA 7 Fisheries and Oceans, Canada, Bedford Institute of Oceanography, Dartmouth, Nova Scotia, Canada 8 Coastal Studies Institute, Louisiana State University, Baton Rouge, LA 70803, USA