Urban transport decarbonization in Indonesia requires strategies that address the persistent dominance of private motorized mobility, particularly motorcycles, while strengthening the competitiveness of public transport. This study examines travel activity patterns, the current role of public transport, and potential mode-shift responses to improved public transport services across 11 Indonesian urban areas. Primary data were collected through a structured face-to-face interview survey involving 5,532 respondents. A mixed logit model was estimated to examine how travel cost, public transport fare, access cost, travel time, waiting time, and electric propulsion influence mode choice. The descriptive results show that public transport currently performs two roles in urban mobility. Among current public transport users, 82.69% had previously made the same trip using another mode, indicating a substitution role, while 17.31% reported that the trip had not been made before public transport became available, indicating a mobility-enabling role. Motorcycles were the dominant previous mode for several public transport services, reflecting their strong position in Indonesian urban travel. For public transport alternatives, travel time produced the largest direct elasticities in absolute terms, followed by access cost. Access-cost elasticities consistently exceeded fare elasticities in absolute terms, while waiting-time elasticities were not statistically significant. Interactions with gender, age, income, and urban context further revealed systematic differences in modal preferences, with women and older respondents more oriented toward buses and minibuses relative to motorcycles, higher-income respondents more oriented toward cars, and rail utility consistently lower outside the Jakarta Metropolitan Area. These findings suggest that public transport strategies in Indonesian cities should prioritize reductions in door-to-door journey time and first- and last-mile burdens, complement these measures with fare integration, and adapt interventions to local urban contexts and user-group needs.
Automatic crack detection on concrete surfaces is important for infrastructure inspection because manual assessment is time-consuming, subject to observer variability, and difficult to apply consistently across large and heterogeneous inspection areas. This study evaluated an integrated deep learning workflow for practical concrete surface crack detection under realistic inspection conditions. The objective was to examine whether a patch-based classification workflow using a pretrained ResNet-50 model could support crack presence detection and approximate spatial localization on full-resolution concrete surface images. The dataset combined field-acquired images and four public datasets, totaling 135,711 images, including 55,559 cracked and 80,152 non-cracked samples. Image pre-processing, data augmentation, transfer learning, batch normalization, dropout regularization, and class balancing were applied during model de- velopment. Model performance was evaluated on 41,119 independent test images using accuracy, precision, recall, and F1-score. The workflow achieved an accuracy of 81.98%, with a macro precision of 0.8176, a macro recall of 0.8275, and a macro F1-score of 0.8179. In addition to patch-level classification, the workflow generated spatially interpretable outputs through sliding-window aggregation, suppression of overlapping detections, confidence heatmaps, and overlay visualization. The visual inference results showed that crack-prone regions could still be localized under both ideal and non-ideal image conditions, including varying illumination and surface blemishes. These findings indicate that the evaluated workflow is useful for practical crack-presence detection and approximate spatial localization on concrete surfaces. The study contributes a structured evaluation of an integrated inspection workflow that may support more consistent and interpretable visual assessment in civil engineering applications under diverse field conditions and realistic infrastructure inspection scenarios.
Accurate prediction of concrete strength is essential for effective mix proportioning, performance optimisation, and sustainable construction. Conventional empirical and regression–based approaches often have limited capability to capture the complex and nonlinear interactions among constituent materials, particularly in blended and geopolymer concrete systems. This study develops an Artificial Neural Network (ANN)–based machine learning framework for predicting the compressive and flexural strengths of GGBS–based concrete. A dataset comprising 150 concrete mixtures with varying binder compositions, material proportions, and curing periods was employed to develop and evaluate the predictive models. The modelling framework was assessed using k–fold cross–validation, statistical error indicators, \ and residual diagnostics to examine prediction accuracy, robustness, and generalisation capability. The ANN model demonstrated excellent predictive performance for compressive strength, achieving high coefficients of determination and low prediction errors across the training, validation, and testing datasets. In comparison, the prediction of flexural strength showed relatively lower generalisation performance, which may be attributed to greater experimental variability and the sensitivity of flexural behaviour to crack initiation, propagation, aggregate–matrix interaction, and material heterogeneity. To improve model interpretability, SHAP (SHapley Additive exPlanations) analysis was employed to quantify the contribution of individual input variables. The results identified GGBS content and the alkali–to–binder ratio as the dominant factors influencing predicted strength, demonstrating consistency with the underlying chemical and mechanical behaviour of GGBS–based concrete. The integrated ANN–SHAP framework provides both accurate prediction and meaningful interpretation of strength development. Overall, the findings demonstrate that ANN based machine learning can serve as a reliable and efficient tool for strength prediction and performance–based optimisation of GGBS–based concrete, potentially reducing the need for extensive experimental trials while saving time, material consumption, and associated costs.
Assessing seismic site conditions through the time-averaged shear-wave velocity of the upper 30 meters (Vs₃₀) is fundamental for understanding local geological response and supporting seismic microzonation. This study investigates the subsurface characteristics of the Ketahun region, North Bengkulu, by integrating the Horizontal-to-Vertical Spectral Ratio (HVSR) method with Monte Carlo inversion to obtain a robust estimation of Vs₃₀. A total of 29 microtremor measurement stations were deployed using a three-component seismometer, and ambient vibration data were processed with Geopsy to derive dominant frequency (f₀) and site amplification (A₀). These parameters served as key constraints in the inversion procedure to construct shear-wave velocity profiles. The inversion results yield Vs₃₀ values ranging from 257 to 1220 m/s, indicating substantial lateral heterogeneity driven by variations in sediment thickness and bedrock depth. Lower Vs₃₀ values characterize coastal alluvial deposits, whereas higher values are found in the eastern–northern hilly terrain dominated by shallow bedrock. A comparative assessment with the global USGS topographic-slope-based Vs₃₀ model reveals systematic discrepancies, with the USGS proxy consistently underestimating Vs₃₀ in hard-rock domains. Statistical evaluation confirms that the differences between both datasets are significant, underscoring the superior representativeness of HVSR-based inversion for local-scale site characterization, particularly in geologically complex environments. Overall, the findings demonstrate the effectiveness of the HVSR Monte Carlo approach in resolving near-surface velocity structures and highlight its importance for seismic hazard assessment, microzonation efforts, and regional planning in North Bengkulu. The resulting Vs₃₀ distribution provides a valuable foundation for future geotechnical validation and for the integration of complementary subsurface investigation methods.
The increasing environmental burden associated with cement production and freshwater consumption has created a need for sustainable alternatives in concrete production. This study investigates the combined utilization of Sugarcane Bagasse Ash (SCBA) as a partial cement replacement and Distilled SewageWater (DSW) as an alternative mixing-water source in M25–grade concrete. Seven concrete mixtures (M0–M6) were prepared by incorporating 0–30% SCBA and 0–40% DSW while maintaining a constant binder content of 400 kg/m3 and water-to-binder ratio of 0.50. Compressive strength was experimentally evaluated after 7, 14, and 28 days of curing. The results demonstrated that moderate replacement levels improved strength, with the mixture containing 10% SCBA and 20% DSW achieving the highest compressive strengths of 20.8, 26.1, and 34.2 MPa at 7, 14, and 28 days, respectively. The improvement was attributed to the pozzolanic activity and micro-filler effect of SCBA, together with adequate water availability. Higher replacement levels resulted in strength reduction because of cement dilution and reduced calcium hydroxide availability. Furthermore, Artificial Neural Network (ANN) and Physics-Informed Neural Network (PINN) models were developed to predict compressive strength using key mix–design parameters and curing age. Both models exhibited excellent predictive performance, with R2 values exceeding 0.999 during the evaluated stages. ANN provided slightly higher numerical accuracy, whereas PINN demonstrated more consistent validation and testing behaviour, indicating improved generalisation and physical consistency. The findings demonstrate that the integrated experimental, physics-informed modelling, and explainable–AI framework can support the development and optimization of sustainable SCBA–DSW concrete while reducing dependence on conventional cement and freshwater resources.
