Civil & Environmental Engineering
Permanent URI for this communityhttp://hdl.handle.net/1903/2221
Browse
2 results
Search Results
Item Prediction of Marine Timber Pile Damage Ratings Using a Gradient Boosted Regression Model(2023) Willmott, Carly; Attoh-Okine, Nii O.; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Marine pilings are critical structural elements exposed to harsh environmental conditions. Specialized routine inspection and regular maintenance are essential to keep marine facilities in good working condition. These activities generate data that can be exploited for knowledge gain with machine learning tools. A gradient boosted random forest regressor machine learning algorithm, XGBoost, was applied to datasets that contain timber pile underwater inspection and repair data over a period of 23 years. First, the data was visualized to show the longevity of different timber pile repair types. An XGBoost model was then tuned and trained on a dataset for timber piles at one pier. Variables in the dataset were evaluated for feature importance in predicting damage ratings assigned during routine underwater inspections. Next, an ensemble of XGBoost models was trained and applied to a second dataset containing the same features for an adjacent pier. This dataset was reserved for testing to demonstrate whether the ensemble trained on one pier’s data could be generalized to predict timber pile damage ratings at a nearby but separate pier. Finally, the ensemble was used to predict damage ratings on piles that had earlier data but were not rated in the two most recent inspection events. Results suggest that the ensemble is capable of predicting timber pile damage ratings to approximately +/- one damage rating on both the training and test datasets. Feature importances revealed that half of the variables (time since the first event, repair type, exposed pile length, and time since the last repair) contributed to two thirds of the relative importance in predicting damage ratings. Data visualization showed that a few repair types, such as pile replacements and encapsulations, appeared to be most successful over the long term compared with shorter-lived repairs like wraps and encasements. These results are promising indications of the advantages machine learning algorithms can offer in processing and gleaning new insights from structural repair and inspection data. Economic benefits to marine facility owners can potentially be realized through earlier anticipation of repairs and more targeted inspection and rehabilitation efforts. There are also opportunities for better understanding of deterioration rates if more data is gathered over the lifespans of structures, as well as more detailed data that can be introduced as new features.Item SEA LEVEL RISE AND ITS ECONOMIC EFFECTS ON NAVAL INSTALLATIONS(2015) Schedel, Angela Luzier; Baecher, Gregory B; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Global sea level is rising. Coastal lands are at risk from eventual inundation, property loss and economic devaluation. The threat is impending but not rapidly approaching. With sea level rise projections ranging from 0.1 meters to 2 meters by the year 2100, there are concerns but little action being taken to adapt and prepare. Given the potential economic impact of future flood events, it appears that many government agencies and municipalities are not taking enough action to prevent the threat of sea level rise. Due to its large footprint of real estate within the coastal zone worldwide, one of the largest organizations threatened directly by sea level rise is the U.S. Navy. Adapting to sea level rise will require strategic planning and policy changes in order to prevent the encroaching sea from limiting naval operations and threatening national security. This study provides a tool to aid Navy decision makers in Implementing Sea Level Adaptation (ISLA). The ISLA tool applies the methodology of decision trees and Expected Monetary Value (EMV), using probability to estimate the cost of potential flood damage and compare this cost to adaptation measures. The goal of this research is for ISLA to empower decision makers to evaluate various adaptation investments related to sea level rise. A case study is used to illustrate the practical application of ISLA. The case study focuses on when to implement a variety of adaptation measures to one asset at the naval base at Norfolk, Virginia. However, its method can be applied to any asset in any location. It is not limited to only military bases. ISLA incorporates a unique method for analyzing the implementation of adaptation measures to combat future coastal flooding which will be worsened by sea level rise. It is unique in its use of decision tree theory to combine the probability of future flood events with the estimated cost of flood damage. This economic valuation using Expected Monetary Value allows for comparison of a variety of adaptation measures over time. The projections of future flood damage costs linked to adaptation allows the decision maker to determine which adaptation measures are economically advantageous to implement and when to implement them.