Civil & Environmental Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/2221
Browse
3 results
Search Results
Item A BIG-DATA-DRIVEN FRAMEWORK FOR SPATIOTEMPORAL TRAVEL DEMAND ESTIMATION AND PREDICTION(2023) Hu, Songhua; Schonfeld, Paul; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Traditional travel demand models heavily rely on travel surveys, simplify future demand forecasting, and show low sensitivity in response to spatiotemporal dynamics. This study proposes a deep-learning-driven framework based on mobile device location data (MDLD) for estimating and predicting large-scale travel demand at both individual and aggregated levels. This study first introduces how raw MDLD should be parsed to distill trip rosters and estimate population flow. Based on derived information, this study reexamines relations between average population flow and its determinants such as built environment, socioeconomics, and demographics, via a set of explainable machine learning (EML) models. Different interpretation approaches are employed and compared to understand nonlinear and interactive relations learned by EML models. Next, this study proposes a Multi-graph Multi-head Adaptive Temporal Graph Convolutional Network (Multi-ATGCN), a general deep learning framework that fuses multi-view spatial structures, multi-head temporal patterns, and various external effects, for multi-step citywide population flow forecasting. Multi-ATGCN is designed to comprehensively address challenges such as complex spatial dependency, diverse temporal patterns, and heterogeneous external effects in spatiotemporal population flow forecasting. Last, at an individual level, this study proposes a Hierarchical Activity-based Framework (HABF) for simultaneously predicting the activity, departure time, and location of the origin and destination of the next trip, incorporating both internal (individual characteristics) and external (calendar, point-of-interests (POIs)) information. For each individual, HABF first predicts activities via an Interpretable Hierarchical Transformer (IHTF). IHTF can efficiently handle big data benefiting from its transformer-based design to avoid recursion. Meanwhile, loss functions used in semantic segmentation are introduced into IHTF to address imbalanced distributions of activity types. Then, a local plus global probabilistic generator is designed to generate locations based on predicted activities and historical places, allowing individuals to visit new or historically-sparse places. Analyses are performed on several real-world datasets to demonstrate the model's capability in forecasting large-scale high-resolution human mobility in a timely and credible manner. Altogether, this study provides sound evidence, practically and theoretically, of the feasibility and reliability of realizing data-driven travel demand estimation and prediction at different spatiotemporal resolutions and scales.Item MODELING URBAN FLOODING IN THE TIBER BRANCH WATERSHED, ELLICOTT CITY, MARYLAND, USING PCSWMM(2020) Walcott, Cadijah; Brubaker, Kaye; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Urban flooding — due to land cover change, inadequate drainage networks, and increased precipitation — exacerbates communities’ economic and social vul¬nerabilities. A detailed watershed model can help communities identify weak portions of the drainage network and design resolutions. This research details the development of a comprehensive model of the Tiber Branch Watershed in Ellicott City, Maryland, to reproduce observed depth in the Hudson Branch tributary using PCSWMM (a commercial version of the U.S. Environmental Protection Agency’s Storm Water Management Model). The 2,434.8-acre watershed comprises 8,821 PCSWMM objects, which were estimated from various raster and vector datasets. Without calibration, the model generally captures the timing and shape of the stage hydrographs but is less successful in simulating event magnitude and receives a R2 of 0.65 and SE/SY of 0.67 for the 43 selected events, collectively. Ultimately, model evaluation was not completed due to a lack of representative rainfall within the watershed.Item Soil Slope Failure Investigation Management Systems(2012) Ramanathan, Raghav Sarathy; Aydilek, Ahmet H; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Highway slopes are exposed to environmental and climatic conditions, such as deforestation, cycles of freezing and thawing weather, heavy storms etc. Over time these climatic conditions can influence slope stability in combination with other factors such as geological formations, slope angle and groundwater conditions. These factors contribute towards causing slope failures that are hazards to highway structures and the traveling public. Consequently, it is crucial to have a soil slope failure investigation management system to track, record, evaluate, analyze and review the soil slope failure data and soil slope remediation data so that cost effective and statistically efficient remedial plans may be developed. This paper presents the framework for developing such a system for The State of Maryland, using a GIS database and a collective overlay of maps to indicate potentially unstable highway slopes through spatial and statistical analysis.