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-related ground-disturbing activities leave exposed land susceptible to soil loss and increase the risk of polluting adjacent waterbodies with sediment-laden discharge. State and federal regulations require stormwater pollution prevention plans to be implemented during construction to mitigate the impact of stormwater runoff. Areas prone to soil loss can be identified early in site planning using soil loss modeling. Identification of these critical areas could influence the design and placement of erosion and sediment control practices. The Revised Universal Soil Loss Equation (RUSLE) can be applied to estimate the soil loss on construction sites in tonnes per Ha per year (tons/acre/year) by considering factors of rainfall erosivity, soil erodibility, length of slope, erosion control, and sediment control. This study integrates geographic information system (GIS) with RUSLE to create soil loss models for residential, commercial, and highway construction scenarios in the contiguous U.S.A. These three construction types were modeled in various locations throughout the country to assess erosive risk. Soil loss outputs were categorized into five risk tiers ranging from very low to very high. Southeastern states had the highest estimated soil loss during residential, commercial, and highway construction, reaching rates of 1,464, 706, and 1,302 tonnes per Ha per year (653, 315, and 581 tons/acre/year), respectively. This study provides a customizable model for any site-specific slope-length factor outside of the three construction scenarios modeled. Integration of GIS provides a unique opportunity to apply RUSLE across a larger landscape. The presented macro-scale data can be used for the design of erosion and sediment control practices.

Implementing proper methods and techniques for construction stormwater management brings numerous benefits in protecting the environment, maintaining social justice, and enhancing sustainability within the construction industry. Flocculants improve construction stormwater management on active job sites by enhancing the function of temporary sediment control practices by facilitating the capture of fine-sized soil particles that are otherwise difficult to settle. The performance of flocculants is dependent on specific soil properties, dosage, and application techniques. Proper product selection and identification of adequate dosage rates is an arduous task for practitioners given the soil variability across job sites and a lack of implementation guidance. This study investigated the performance of various commercially available flocculant products on 15 soil samples collected from construction sites across Alabama through bench-scale testing methods. Experiments focused on providing guidance on product selection and identifying optimum dosage rates through soil assessment, match tests, and dosage experiment phases. The performance of polyacrylamide, sodium montmorillonite, chitosan, agricultural gypsum, and alum-based products was investigated across all soil samples for product selection. Dosage of selected products was evaluated by ranging manufacturers’ dosage recommendations from 0% to 200% to evaluate settling performance across a range of dosing conditions. Results indicated that increasing recommended dosage rates negatively affected the turbidity reduction performance of tested products. In general, dosages lower than 40% manufacturer recommended rates showed a statistically significant improvement in turbidity reduction at a 95% confidence level. The study provides insight for practitioners and future research agendas on the proper usage of flocculants in the construction industry.

Flocculants provide an innovative solution for managing construction stormwater runoff with their efficiency in reducing turbidity in the effluent. With proper application and dosage, these chemicals improve the performance of sediment control practices in capturing fine-sized soil particles. Flocculants function by providing electromagnetic charges to attract soil particles into large molecular bridges of flocs. Following this process, suspended particle removal can be achieved through gravitational forces. Despite the benefits of using flocculants, their implementation may create a potential risk of polluting downstream waterbodies and harming aquatic life in case of a high residual concentration in discharge. Determining residual concentrations is challenging for practitioners because of a lack of field applicable testing methods that work across a variety of flocculant types. This study developed a field applicable methodology for detecting residual flocculant concentrations by using settling velocity as an identifier of flocculant concentration. In total, 14 products comprised of polyacrylamide, sodium montmorillonite, chitosan, agricultural gypsum, and alum-based products were evaluated. Known flocculant concentrations ranging from 0% to 30% of the manufacturer’s recommended dosage, were mixed with a fine soil passing through No. 200 sieve and allowed to settle in a graduated cylinder to record the settling velocity. Regression analysis was conducted on the experimental data to develop concentration versus settling velocity relationships which indicated that more than 90% of known concentration values are dependent on the settling velocity. The study provides a framework for practitioners to identify residual flocculant concentrations in field conditions by relating settling velocity with chemical concentrations.