Construction activities typically create large amounts of ground disturbance, which can lead to increased rates of soil erosion. Construction stormwater practices are used on active jobsites to protect downstream waterbodies from offsite sediment transport. Federal and state regulations require routine pollution prevention inspections to ensure that temporary stormwater practices are in place and performing as intended. This study addresses the existing challenges and limitations in the construction stormwater inspections and presents a unique approach for performing unmanned aerial system (UAS)-based inspections. Deep learning-based object detection principles were applied to identify and locate practices installed on active construction sites. The system integrates a post-processing stage by clustering results. The developed framework consists of data preparation with aerial inspections, model training, validation of the model, and testing for accuracy. The developed model was created from 800 aerial images and was used to detect four different types of construction stormwater practices at 100% accuracy on the Mean Average Precision (MAP) with minimal false positive detections. Results indicate that object detection could be implemented on UAS-acquired imagery as a novel approach to construction stormwater inspections and provide accurate results for site plan comparisons by rapidly detecting the quantity and location of field-installed stormwater practices.

Construction site erosion and resulting sedimentation constitutes one of the greatest non-point source pollution threats to our nation’s waterways. Erosion control practices are important aspects of any construction project due to their ability to limit the process of erosion. Testing erosion control practices under simulated rainfall representative of conditions experienced on construction sites is important to better understand their erosion reduction capabilities. Full-scale testing using simulated rainfall has been shown to provide controllable and repeatable results, in comparison to field-testing under natural conditions. Therefore, the focus of this study was to design, construct, and calibrate a pressurized rainfall simulator testing apparatus capable of accurately and repeatedly simulating rainfall intensities of 50.8, 101.6, and 152.4 mm/hr (2.0, 4.0, and 6.0 in/hr) for 20-min intervals. The developed testing apparatus consisted of a 12 m (40 ft) long by 2.4 m (8.0 ft) earthen slope at a 3H:1V slope. Ten sprinkler risers at a height of 4.27 m (14 ft) were installed around the perimeter of the slope to create a uniform distribution of rainfall. Data collection procedures consisted of collecting and analyzing rainfall depth, drop size distributions, and sediment concentrations. The optimum location for each sprinkler riser, as well as the most accurate nozzle configuration, were determined through test procedures developed for this study. Through calibration testing, the simulator was found to produce accurate rainfall intensities with relative errors of 1.17–4.00% of the target intensities. Uniformity of rainfall distribution ranged from 85.7 to 87.5%. Average drop sizes were determined to be between 2.35 and 2.58 mm (0.093 to 0.102 in.).

Erosion and sediment controls on construction sites minimize environmental impacts from sediment-laden stormwater runoff. Silt fence, a widely specified perimeter control practice on construction projects used to retain sediment on-site, has limited performance-based testing data. Silt fence failures and resultant sediment losses are often the result of structural failure. To better understand silt fence performance, researchers at the Auburn University-Erosion and Sediment Control Testing Facility (AU-ESCTF) have evaluated three silt fence options to determine possible shortcomings using standardized full-scale testing methods. These methods subject silt fence practices to simulated, in-field conditions typically experienced on-site without the variability of field testing or the limited application of small-scale testing. Three different silt fence practices were tested to evaluate performance, which included: (1) Alabama Department of Transportation (ALDOT) Trenched Silt Fence, (2) ALDOT Sliced Silt Fence, and (3) Alabama Soil and Water Conservation Committee (AL-SWCC) Trenched Silt Fence. This study indicates that the structural performance of a silt fence perimeter control is the most important performance factor in retaining sediment. The sediment retention performance of these silt fence practices was 82.7%, 66.9% and 90.5%, respectively. When exposed to large impoundment conditions, both ALDOT Trench and Sliced Silt Fence practices failed structurally, while the AL-SWCC Trenched Silt Fence did not experience structural failure.

As climate change impacts intensify, communities in rural Alaska are undergoing and adapting to changes to infrastructure from increased permafrost thawing, flooding, and erosion. Climate change adaptation is needed to address structural failures and safety concerns. Despite recognizing the need for support from stakeholders and adaptation of infrastructure, the level of adaptation activity remains limited and inconsistent across regions and communities in rural Alaska. We address this need by identifying barriers to community-wide adaptation of infrastructure based on stakeholder perspectives who make adaptation decisions for government agencies, nonprofits, engineering firms, or academic institutions in rural Alaska. Barriers were identified qualitatively through interviews (N = 25) and validated quantitatively through surveys (N = 30). Qualitative and quantitative results identified and validated 17 barriers to adaptation of infrastructure – spanning sociocultural, institutional, economic, physical, and environmental dimensions based on the Sustainable Livelihoods Framework (SLF). Results demonstrate the need for national adaptation funding and policy that is specific to the diverse cultural landscapes, extreme weather, rural locations, limited transportation, and high costs in rural Alaska. Adaptation funding and policy is needed that supports the collaboration of Alaska-based institutions, such as nonprofit organizations and engineering firms, Tribal entities, and rural Alaska community representatives in adaptation.

Construction activities increase the erosion potential of a site through earth-disturbing processes of vegetative grubbing, topsoil stripping, and grading. Receiving waters become susceptible and vulnerable to the process of sedimentation, which degrades the overall water quality. Federal, state, and local regulations require the use of erosion and sediment controls to help manage stormwater discharge from construction sites. Regulations further require regular inspections, monitoring, and maintenance of employed erosion and sediment control practices. Unmanned aerial vehicles (UAVs) are an emerging remote sensing tool capable of acquiring high resolution spatial and sensing data. Remote sensing with UAVs has the potential to provide high-quality aerial imagery and data that can assist in site inspections of erosion and sediment control practices and monitoring project progression. UAVs are economical and flexible in acquiring aerial data and can be preprogrammed with flight paths to capture data over construction sites objectively. UAV-based remote sensing enables user-controlled image acquisition and bridges the gap in scale and resolution between ground observations and imagery acquired from conventional manned aircraft and satellites. This research describes the application of UAV technologies for construction site inspections of erosion and sediment control practices and tracking project progression. A case study was performed on an active residential construction site with a commercially available UAV to showcase its application and capabilities of enhancing the site inspection process and construction monitoring.

Perimeter controls [i.e., sediment barriers (SBs) or sediment retention devices] are typically used on construction sites to retain sediment and prevent polluted stormwater runoff from adversely affecting aquatic habitats and clogging storm sewers. Often, parameters based on rule-of-thumb are applied to the design of SBs without knowing their expected performance capabilities. This issue is further complicated by the difficulty in devising a scientifically sound, repeatable testing methodology, replicating field conditions to assess performance. To resolve this issue, a test apparatus was designed and constructed at the Auburn University—Erosion and Sediment Control Test Facility to replicate in-field rainfall runoff rates for purposes of conducting full-scale experiments on various SBs. This apparatus allows for performance testing and direct comparisons between various SB products, practices, and installations. The overall intent of conducting full-scale testing is to improve design criteria and enhance the in-field performance of SB practices. Initial test results for a woven polypropylene silt fence reinforced with a polypropylene grid and supported by wooden posts performed well structurally with an average sediment retention rate of 90.5% by volume.