An official website of the United States government
Rising waters and land subsidence are increasing relative sea levels in western and northern Alaska, forcing communities to relocate or armor in place. To appropriately plan and make equitable decisions, there is a need to forecast the risk of flood exposure in coastal Alaskan communities and to evaluate methods to mitigate that risk. This paper conducts use-inspired science to evaluate the current and future flood exposure of roads in Hooper Bay, Alaska, proposes a unit cost of flood exposure to estimate the cost of flooding, and compares various mitigation efforts including elevating roads and building dikes. Nine historic storms and their associated flood depths were subject to return-period analysis and modeled for several sea level rise scenarios. Based on the simulated road flood exposure (km hours/storm), and the storm-return period, an annual flood exposure (km hours/year) was computed. Then, the unit cost of flood exposure (USD/km hours) was determined as the ratio of the cost of flood mitigation (USD/year) to the annual flood exposure mitigated by the project. The analysis found that the unit cost of flood exposure, in conjunction with flood exposure calculations, does provide an approximate flood risk calculation, though a unitized cost of flood exposure needs to be divided into lump sum costs and materials costs. The analysis also found that dikes may be a more cost-effective alternative than road elevation. The flood risk calculation, based on the unit cost of flood exposure, could be made for all of the communities in a given region to identify those communities that face a high flood risk. Furthermore, if one divides the unit cost of flood exposure by the population, one obtains a cost/benefit ratio that potentially could be used to prioritize flood mitigation work.
more »
« less
This content will become publicly available on March 17, 2026
AquaCam: An ML-Enhanced Low-Cost, Deploy-Anywhere Water Level Detection Sensor
Flood detection is difficult in rural areas with little or no monitoring infrastructure. Smaller streams and flood-prone regions often remain unmonitored, which leaves communities vulnerable. Commercial systems cost much and use proprietary designs, so many communities cannot use them. This work presents AquaCam, a low-cost and open-source flood detection system that uses a Raspberry Pi and a camera to measure stream water levels automatically. AquaCam captures images and trains a lightweight convolutional neural network (YOLOv8) with the collected data. The model learns to recognize water in natural backgrounds and measure water height. To test whether AquaCam can adapt to new environments, we evaluated the trained model at a different site with no retraining. The system still identified water levels accurately. This shows that the approach is practical and generalizable. AquaCam moves flood detection toward being affordable, accessible, and adaptable for the communities that need it.
more »
« less
- PAR ID:
- 10647722
- Publisher / Repository:
- IEEE
- Date Published:
- Page Range / eLocation ID:
- 628 to 632
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In this paper, we use a procedural generation system to design urban layouts that passively reduce water depth during urban floods. The tool enables designing cities that passively lower flood depth everywhere or in chosen key areas. Our approach integrates a porosity-based hydraulic model and a parameterized urban generation system with an optimization engine so as to find the least cost modification to an initial urban layout. In order to investigate the relationship between urban layout design parameters and flood inundation depth, correlation coefficient method is used. This paper concludes that the most influential urban layout parameters are average road length and the mean parcel area.more » « less
-
Abstract Tide gauge water levels are commonly used as a proxy for flood incidence on land. These proxies are useful for projecting how sea‐level rise (SLR) will increase the frequency of coastal flooding. However, tide gauges do not account for land‐based sources of coastal flooding and therefore flood thresholds and the proxies derived from them likely underestimate the current and future frequency of coastal flooding. Here we present a new sensor framework for measuring the incidence of coastal floods that captures both subterranean and land‐based contributions to flooding. The low‐cost, open‐source sensor framework consists of a storm drain water level sensor, roadway camera, and wireless gateway that transmit data in real‐time. During 5 months of deployment in the Town of Beaufort, North Carolina, 24 flood events were recorded. Twenty‐five percent of those events were driven by land‐based sources—rainfall, combined with moderate high tides and reduced capacity in storm drains. Consequently, we find that flood frequency is higher than that suggested by proxies that rely exclusively on tide gauge water levels for determining flood incidence. This finding likely extends to other locations where stormwater networks are at a reduced drainage capacity due to SLR. Our results highlight the benefits of instrumenting stormwater networks directly to capture multiple drivers of coastal flooding. More accurate estimates of the frequency and drivers of floods in low‐lying coastal communities can enable the development of more effective long‐term adaptation strategies.more » « less
-
This study originated with the objective of parameterizing riparian evapotranspiration (ET) in the water budget of the middle Rio Grande of New Mexico. We hypothesized that flooding and invasions of non-native species would impact the ecosystem's use of water. Our objectives were to measure and compare the ET of native (Rio Grande cottonwood, Populus deltoides ssp. wizleni) and non-native (saltcedar, Tamarix chinensis, Russian olive, Eleagnus angustifolia) bosque (woodland) communities and to evaluate how water use is affected by climatic variability resulting in high river flows and flooding as well as drought conditions and deep water tables. This data set contains water table levels monitored at nine sites along the Rio Grande riparian corridor between Albuquerque and Bosque del Apache National Wildlife Refuge. Data date to 1999. Two sites remain active and are well into their second decade of monitoring. One is in a xero-riparian, non-flooding, saltcedar woodland within the Sevilleta National Wildlife Refuge. The other is in a dense, monotypic saltcedar thicket at the Bosque del Apache NWR that is subject to flood pulses associated with high river flows.more » « less
-
Abstract A changing climate and growing coastal populations exacerbate the outcomes of environmental hazards. Large‐scale flooding and acute disasters have been extensively studied through historic and current data. Chronic coastal flooding is less well understood and poses a substantial threat to future coastal populations. This paper presents a novel technique to record chronic coastal flooding using inexpensive accelerometers. This technique was tested in Key West, FL, USA using storm drains to deploy HOBO pendant G data loggers. The accuracy and feasibility of the method was tested through four deployments performed by a team of local stakeholders and researchers between July 2019–November 2021 resulting in 22 sensors successfully recording data, with 15 of these sensors recording flooding. Sensors captured an average of 13.58 inundation events, an average of 12.07% of the deployment time. Measured flooding events coincided with local National Oceanic and Atmospheric Administration (NOAA) water level measurements of high tides. Multiple efforts to predict coastal flooding were compared. Sensors recorded flooding even when NOAA water levels did not exceed the elevation or flooding thresholds set by the National Weather Service (NWS), indicating that NOAA water levels alone were not sufficient in predicting flooding. Access to an effective and inexpensive sensor, such as the one tested here, for measuring flood events can increase opportunities to measure chronic flood hazards and assess local vulnerabilities with stakeholder participation. The ease of use and successful recording of loggers can give communities an increased capacity to make data‐informed decisions surrounding sea level rise adaptation.more » « less
