Members’ Publication

Transport mode choice is a crucial determinant of urban mobility patterns, influencing infrastructure planning, environmental sustainability, and social equity. Although it is important, there is still an unfulfilled gap in the use of socio-demographic, behavioral and perception-based factors to accurately predict choice of transport mode especially in the developing countries. The proposed study shall fill this gap by applying a deep learning model to make predictions of transport mode choice using a multidimensional survey data. The primary objective of this research was to investigate the potential of a Gated Recurrent Unit (GRU) neural network for classifying transport mode choice using a variety of socio-demographic, economic, and travel behavior features. The dataset includes 348 respondents, capturing responses related to seven transport modes: Bike, Bus, CNG, Car, Cycle, Easy bike, and Rickshaw. Key attributes in the dataset include gender, age, occupation, income, travel objectives, and safety perceptions related to different transport modes. The preprocessing of the data included the following: one-hot encoding of features of character type, normalization of numeric data, and label encoding of target variable. The GRU-based model was trained and tested based on stratified 80:20 train-test split and tested with reference to confusion matrices, ROC, and precision-recall. The accuracy of the model has a value of 79%, ensuring very good results on modes such as CNG (precision = 1.00, recall = 1.00) and Easy bike (precision = 0.73, recall = 0.88). This class-wise analysis raised the issue of less frequent mode prediction such as Cycle and Car modes which were having a lower recall. The AUC scores had micro- and macro-averages of 0.943 and 0.918 respectively. These findings reveal the ability of deep learning models, especially GRUs to be used reliably to predict transport mode preferences using a diversified group of socio-demographic and behavioral variables. This predictive modeling would provide urban designers and policymakers with the information needed to design more specifically focused interventions to promote sustainable transport networks, increase modal share, and reduce congestion in urban areas.

Tropical cyclones rank among the most destructive natural hazards globally, posing significant threats to coastal ecosystems and communities. Mangrove forests, renowned for their ecological importance and coastal protection services, are vulnerable to these disturbances, suffering structural damage, habitat loss, and disruption of vital ecosystem functions. Conventional field-based assessment methods often fall short in capturing the rapid and widespread impacts of cyclones, particularly in remote or cloud-obscured regions. This review aims to provide a comprehensive synthesis of remote sensing applications for monitoring cyclone-induced impacts on mangrove and coastal ecosystems worldwide. Through a systematic literature review of 74 peer-reviewed articles from 1990 to 2025, the study evaluates the utility of optical sensors, radar systems, and multi-sensor platforms in assessing inundation, vegetation damage, and ecosystem service loss. Key methodological advances such as time-series analysis, machine learning, and UAV-based validation are highlighted, alongside critical gaps including limited geographic coverage, weak validation practices, and minimal socio-economic integration. Notably, 75.4% of reviewed studies are concentrated in Asia, with Bangladesh and India alone accounting for 44.6% of the total literature, underscoring a pronounced geographic bias. The findings underscore the need for robust, near-real-time monitoring frameworks that combine satellite technologies with ground data and community engagement. Ultimately, the review advocates for an integrated, multi-sensor, and participatory approach to cyclone resilience, offering valuable insights for future research, disaster response planning, and sustainable mangrove management.

Bangladesh and other developing nations face road traffic accidents (RTAs) as a major public safety issue. Accidents have grown due to growing motor vehicle use, obsolete infrastructure, and lax traffic law enforcement. The Khulna–Rajshahi Highway experiences frequent and severe road crashes, resulting in high fatalities, injuries, and economic losses. The study aims to identify crash hotspots, assess land-use influences on road safety across varying road environments, and propose infrastructure and policy measures to enhance safety along the Khulna–Rajshahi corridor, with particular emphasis on VRU risks due to their disproportionate burden in Bangladesh's mixed-traffic environment. The research relied on a combination of Geographic Information System (GIS) tools, police-reported accident data from 2023 to 2024 integrated with VRU survey data (n = 208), and high-resolution satellite imagery. Advanced spatial techniques such as Kernel Density Estimation (KDE), Getis-Ord Gi∗ hotspot analysis, and Geographically Weighted Regression (GWR) were used to uncover meaningful patterns, yielding a model fit of R2 = 0.27. The results indicate a notable clustering of accidents (Moran's I = 0.065, p < 0.05), with urban stretches along the corridor reporting the highest concentrations, reaching up to 30–35 accidents per square kilometer. Severity mapping revealed critical danger zones in places like Puthia (Rajshahi), Boraigram Upazila (Natore), among others. Due to poor infrastructure and traffic management, motorcyclists (77% of VRUs) and pedestrians were especially susceptible in mixed-use zones near lively markets and junctions, where approximately 45% of vulnerable road user (VRU) incidents occurred. This study suggests immediate, focused safety measures to decrease accidents. Building pedestrian overpasses and placing traffic lights in high-risk areas are key. A replicable GIS-based, corridor-level evidence framework that uniquely integrates VRU behavioral data with spatial statistics allows planners and transport authorities to prioritize location-specific interventions to reduce road traffic accidents in developing-country highway contexts.

Bangladesh and other developing nations face road traffic accidents (RTAs) as a major public safety issue. Accidents have grown due to growing motor vehicle use, obsolete infrastructure, and lax traffic law enforcement. The Khulna–Rajshahi Highway experiences frequent and severe road crashes, resulting in high fatalities, injuries, and economic losses. The study aims to identify crash hotspots, assess land-use influences on road safety across varying road environments, and propose infrastructure and policy measures to enhance safety along the Khulna–Rajshahi corridor, with particular emphasis on VRU risks due to their disproportionate burden in Bangladesh's mixed-traffic environment. The research relied on a combination of Geographic Information System (GIS) tools, police-reported accident data from 2023 to 2024 integrated with VRU survey data (n = 208), and high-resolution satellite imagery. Advanced spatial techniques such as Kernel Density Estimation (KDE), Getis-Ord Gi∗ hotspot analysis, and Geographically Weighted Regression (GWR) were used to uncover meaningful patterns, yielding a model fit of R2 = 0.27. The results indicate a notable clustering of accidents (Moran's I = 0.065, p < 0.05), with urban stretches along the corridor reporting the highest concentrations, reaching up to 30–35 accidents per square kilometer. Severity mapping revealed critical danger zones in places like Puthia (Rajshahi), Boraigram Upazila (Natore), among others. Due to poor infrastructure and traffic management, motorcyclists (77% of VRUs) and pedestrians were especially susceptible in mixed-use zones near lively markets and junctions, where approximately 45% of vulnerable road user (VRU) incidents occurred. This study suggests immediate, focused safety measures to decrease accidents. Building pedestrian overpasses and placing traffic lights in high-risk areas are key. A replicable GIS-based, corridor-level evidence framework that uniquely integrates VRU behavioral data with spatial statistics allows planners and transport authorities to prioritize location-specific interventions to reduce road traffic accidents in developing-country highway contexts.

Open spaces function as the lungs of a city, providing environmental and social benefits. In a densely populated city like Dhaka, community-based open spaces play a crucial role in enhancing urban livability. The sustainability of such spaces largely depends on effective management. However, these spaces face multiple barriers in this regard. Therefore, this study aimed to explore the transformation of a community-based open space named Road No. 17 Park, understand the connection with other organizations and identify challenges faced. Employing Participatory Rural Appraisal (PRA) tools and Key Informant Interviews (KIIs), the research identifies that the committee’s strong relationships with the Ward Councillor and the local parliamentary member facilitated management activities, while unity among members remains its core strength. However, inadequate financial resources pose significant challenges. Hence, the study recommended future guidelines on the management of community-based open spaces, highlighting effective Public-Private Partnership and funding from NGOs and the local government.

This data article introduces a detailed and structured dataset derived from a survey exploring the psychological factors that influence transport mode choices in Pabna Municipality, northwest of Bangladesh. This dataset covers a wide range of socio-demographic factors, i.e., income, occupation level, and age, as well as the factors related to the choice of the mode of transportation, money expenditure, and a set of psychological determinants, i.e., the perceived safety, financial constraint, and environmental consciousness. These aspects are often under-represented in existing research. The data were collected using a carefully structured questionnaire survey of 348 samples conducted over a three weeks survey of urban residents on different points. The dataset is an important resource to researchers working on urban planning, transportation behaviour analysis, environmental psychology and public health as it provides a more detailed understanding of how psychological factors interact with mode choice in transportation. This will help in policy-making, to contribute to the broader field of urban transport planning. To validate the reliability and predictive capability of the dataset, several supervised machine learning models were applied, demonstrating strong classification performance for transport mode choice. The dataset can be used in future research on inclusion-based, user-friendly transport systems especially in Bangladesh as well as other rapidly urbanising regions, as it is in line with global sustainability.

Flooding is one of the most frequent and severe natural hazards in the coastal region of Bangladesh, where low-lying terrain, tidal incursion, and frequency of tropical storms enhance the degree of susceptibility. Mongla and Sharankhola Upazilas in Bagerhat district experience recurrent inundation driven by tidal surges, river overflow, and intense monsoonal rainfall, with exposure amplified by fragile geomorphology, inadequate drainage, and limited infrastructural resilience. An integrated Analytic Hierarchy Process (AHP) and Geographic Information System (GIS) approach has been developed to comparatively assess the flood risk of these two upazilas, which is presented in this paper. The study integrates flood hazard and vulnerability to produce composite risk maps that are intended to aid local disaster management and planning. This was carried out by relative weight assignment of flood-controlling parameters through expert assessment and generating spatially explicit hazard, vulnerability and composite risk maps using GIS overlay analysis. Hazard factors were distance from rivers, slope, drainage density, average annual rainfall, elevation and Topographic Wetness Index (TWI). On the other hand vulnerability parameters were Land Use Land Cover (LULC), distance from roads, road-river intersections, population density and literacy rate.The results show different flood risk dynamics in these two study areas. In Mongla the two major factors that drive vulnerability are distance from roads (38%) and literacy rate (31%) which suggest that accessibility and educational awareness increase flood susceptibility but hazard is mainly determined by rainfall with average annual rainfall (37%) and drainage density (25%) being the most significant variables. In Mongla, about 59 % of area comes under moderate to high flood risk, and almost all of the unions are flood prone. However the unions of Chandpi and Sonailtala have been identified as most at risk. On the other hand, Sharankhola’s vulnerability is dominated by literacy rate (37%) and population density (24%), indicating the significance of social preparedness and population concentration, whereas distance from rivers (32%) and drainage density (25%) controlled the hazard in the area. While moderate-risk zones occupy the majority of Sharankhola (31 %), Southkhali and Royenda unions are identified as high-priority zones concerning flood risk. The consistent influence of drainage density across both upazilas underscores a hydrological vulnerability in the southern coastal plain. Overall, the integrated AHP–GIS approach outlines spatially explicit flood risk zones, which may identify regions of resilience and adaptation both directly and indirectly. This comparative analysis emphasizes the significance of local disaster management policies to handle physical variables and socio-economic causes underlying flood risk. Such essential information helps policy makers, developers, and local people to prioritize measures, increase flood preparation and make infrastructure more robust in exploitable coastal regions of Bangladesh.

Transport systems are an important aspect of social and economic growth of cities and especially those cities that rapidly grow such as Khulna City. This paper assesses operational performance of three unsignalized intersections; Shibbari, Zero Point and Moylapota in the heterogeneous traffic scenario taking into account diverse types of vehicles, such as non-motorized vehicles, semi-motorized vehicles, and motorized vehicles. The surveys on traffic volume were performed during the times of maximum traffic, and the data was used to calculate the approach capacities and to estimate the volume-to-capacity (V/C) ratios of the Level of Service (LOS) analysis. The results demonstrated that some methods, including the Khulna City Bypass and Khulna-Satkhira Road, work at LOS E-F, which implies that the methods are overloaded and the flow situation is unstable. Other methods, on the other hand, sustain LOS C, which is an indicator of moderate congestion. Another result of the study was the movement in modal share with an increasing use of motorized mode at peak hours. Its findings highlight the urgent need of capacity, adaptive traffic and web-enhanced public transportation and non-motorized transport infrastructure. This study not only addresses good insights on traffic management planning in Khulna but other mid cities in Bangladesh where the same is being experienced and thereby aiding in improved transportation planning and development of the city.