Department of Civil Engineering

Now showing 1 - 2 of 2

Embargo
Relationships amongst water and sediment qualities, discharge, and allochthonous inputs of intermittent streams in tropical dry climates: Implications on stream management
(Elsevier, 2023-07-19) Gomes, P.I.A; Perera, M.D.D
The interrelationships amongst water and sediment physicochemistry, catchment hydrology, and allochthonous inputs are not well established for intermittent streams, especially in tropical climates. This remains a major concern in water resources management, and understanding these streams is vital in forming targeted frameworks for protection. A two-year comprehensive study showed spatially independent water quality variations, where similar temporal patterns were observed in different streams in close catchments for many variables (such as for electrical conductivity, pH, nitrogen species, and dissolved oxygen). This was not the case for sediment quality variables; in addition, in-stream variation was high. This gave an indication of the regulatory potential of intermittent stream sediment. Redundancy analysis models showed that stream water quality was significantly correlated to, and could be explained by discharge, rainfall parameters, litter, and sediment quality. Sediment quality was not influenced by litter inputs but by discharge and rainfall-related parameters. The study reported new insights into the unique physicochemistry of intermittent streams and proposes the fact that sediment quality needs comprehensive monitoring and management both spatially and temporally.
Open Access
Evaluating expressway traffic crash severity by using logistic regression and explainable & supervised machine learning classifiers
(Elsevier, 2023-07-09) Shashiprabha, M.J.P.S; Kelum, S.R.M; Meddage, D.P.P; Pasindu, H.R; Gomes, P.I.A
The number of expressway road accidents in Sri Lanka has significantly increased (by 20%) due to the expansion of the transport network and high traffic volume. It is crucial to identify the causes of these crashes for effective road safety management. However, traditional statistical methods may be insufficient due to their inherent assumptions. This study utilized explainable machine learning to investigate the factors that affect the severity of traffic crashes on expressways. The study evaluated two groups of traffic crashes: fatal or severe crashes, and other crashes that included non-severe injuries or only property damage. Five factors that contribute to crashes were analyzed: road surface condition, road alignment, location, weather condition, and lighting effect. Four machine learning models (Random Forest (RF), Decision Tree (DT), extreme gradient boosting (XGB), K-Nearest Neighbor (KNN)) were developed and compared with Logistic Regression (LR) using 223 training and 56 testing data instances. The study revealed that the machine learning algorithms provided more accurate predictions than the LR model. To explain the machine learning models, Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were used. These methods revealed that all five features decreased the possibility of occurrence of fatal accidents. SHAP and LIME explanations confirmed the known interactions between factors influencing crash severity in expressway operational conditions. These explanations increase the trust of end-users and domain experts on machine learning models. Furthermore, the study concluded that using explainable machine learning methods is more effective than traditional regression analysis in evaluating safety performance. Additionally, the results of the study can be utilized to improve road safety by providing accurate explanations for decision-making processes for black-box models. © 2023

Department of Civil Engineering

Browse

Filters

Advanced Search

Filter by

Settings

Sort By

Results per page

Search Results