Members’ Publication

In developing countries, rapid and unregulated population growth, along with economic and industrial growth and development have accelerated the rate of changes in land use and land cover (LULC) during the early twenty-first century. One of the most effective ways to assess and manage the land transformation is through quantitative assessment of LULC changes. To find the best classifier for further uses of earth observation data, it is necessary to compare the accuracy of several LULC modelling algorithms. In this paper, four machine learning (ML) algorithms/classifier namely support vector machine (SVM), k-nearest neighbor (KNN), random forest (RF) and decision tree (DT) have been examined using Landsat 8 Operational Land Imager (OLI) sensor data. All the algorithms performed almost in a similar accuracy level, where SVM scores 84.00% of Cohen kappa and 90.74% of overall accuracy. These figures are 82.99% and 90.05% respectively for KNN. For RF, Cohen kappa and overall accuracy recorded 78.24% and 87.62% respectively. DT gained 74.46% for Cohen kappa and 85.51% for overall accuracy. Clearly SVM outperformed other algorithms in low spatial-resolution satellite data. The outcome of the study would help in different stages of LULC modelling. Moreover, it would help the planners and policy makers in formulation and preparation of land-based policy and planning to ensure sustainable living environment.

Major cities of Bangladesh have been experiencing rapid urbanization and industrialization. These are incurring positive externalities to national economy at the expense of environmental degradation and deterioration of living environment. The ambivalent sequel of industrialization has made it necessary to study urban areas and monitor spatiotemporal changes to facilitate decision-making process regarding land use planning, resource distribution, priority setting for planning interventions. Thus, this study aims to classify land use land cover(LULC) of Narayanganj Sadar Upazila and detect spatiotemporal changes within the period of 2015 to 2020using MLC algorithm based supervised classification method. To serve this purpose, sentinel-2 satellite imagery are used. The results derived from the study elicit an increase (24.14 acre) in industrial land in 2020compared to 2015. Approximately 1,538-acres land transformed into built-up area in 2020. Decrease in vegetation (15.85%) and water body (7.65%) are also evident from the findings. The results of the study will be conducive to have an initial glimpse of the LULC changing trend in the study area due to rapid urbanization and thus, will be instrumental for performing further research.

Assessing fish habitat suitability in a data-scarce tidal river is often challenging due to the absence of continuous water quantity and quality records. This study comprises an intensive field study on a 42 km reach which recorded bathymetry and physical water quality parameters(pH, electroconductivity, dissolved oxygen, and total dissolved solids) testing and corresponding water levels and velocity. Frequent water sampling was conducted on 17 out of 90 locations for laboratory water quality tests. Based on this, an interpolation technique, i.e., Inverse DistanceWeighted (IDW), generates a map in a Geographic Information System (GIS) environment using ArcGIS software to determine the river water quality parameters. Additionally, a hydrodynamic model study was conducted to simulate hydraulic parameters using Delft3D software followed by water quality distribution. During validation, the Delft3D-simulated water quality could reasonably mimic most field data, and GIS featured dissolved oxygen. The overall water quality distribution showed a lower dissolved oxygen level (~3 mg/l) in the industrial zone compared to the other two zones during the study period. On the other hand, these validated hydraulic properties were applied in the Physical Habitat Simulation Model (PHABSIM) set up to conduct the hydraulic habitat suitability for Labeo rohita (Rohu fish). Thus, the validated model could represent the details of habitat suitability in the studied river for future decision support systems, and this study envisaged applying it to other similar rivers (4) (PDF) Suitability Assessment of Fish Habitat in a Data-Scarce River. Available from: https://www.researchgate.net/publication/364279688_Suitability_Assessment_of_Fish_Habitat_in_a_Data-Scarce_River [accessed Sep 11 2023].

Buildings are the most striking artificial features, and extracting buildings becomes critical for many service-providing agencies. Although improvements have been achieved, building detection from remotely sensed images is still challenging. In the past few years, many building extraction methods have been put forward by researchers, such as line- or edge-based, template matching, knowledge- and auxiliary data-based, machine learning, morphological operations-based, and GEographic Object-Based Image Analysis (GEOBIA) -based. GEOBIA is a paradigm for analyzing high-resolution images; however, GEOBIA-based building extraction methods encounter problems in the segmentation and classification stage. Thus, the accuracy of those methods is lesser than other building detection approaches. This research introduced several modifications to the previously proposed hybrid segmentation methods, such as using the reference polygon to identify optimal parameters, a donut filling technique to reduce over-segmentation caused by roof elements, and illumination differences to restrict merging with shadow. The proposed methodology was tested on a UAV image with visible bands only. Better results were achieved using this approach when compared to the multiresolution proposed by Baatz and Schäpe (2000) and the other two-hybrid methods proposed by Wang et al. (2018a) and Yang et al. (2017). This hybrid segmentation method was also applied to subsets of the Wuhan University buildings dataset and produced similar results. One of the great strengths of the proposed method was that there were no parameter tuning and user interaction at running time. In addition, it was able to segment both small and large buildings without using any scale or object size parameters.

Rajshahi City Corporation (RCC) has been marked as a geologically vulnerable in terms of earthquake. However, no scientific method has been determined to figure out the influencing factors. This is the first approach to detect the vulnerability of RCC area. In this point of view, the liquefaction hazard map has the innate power to evaluate the potentiality of earthquake-prone areas. The liquefaction map was prepared using sixty borehole profiles data among 30 wards of RCC. The most widely popular Seed’s method (1971) is employed to calculate liquefaction potential index (LPI) using an earthquake scenario of magnitude M7.0 with peak ground acceleration of 0.12 g (BNBC 2010 draft version). Based on LPI value, Rajshahi city area has been divided into four different liquefaction severity categories (i.e., very low, low, high, and very high) and finally mapped through ArcGIS for the complete visualization. This initial study might be helpful for engineers and planners to plan and execute different structural scheme in this region. This paper also summarizes the calculation procedure of determining LPI from available literature to build up a single framework.

The literature on low-cost housing has paid considerable attention to the economic factors influencing the residential stability of the urban poor. However, tenants' perceptions of residential stability in poor neighbourhoods still represent major gaps within the existing knowledge. This paper investigates migration, length of residency and perceived risk of eviction among urban poor, with the aim of understanding residential stability within the context of Least Developed Countries (LDCs). We frame this study within the literature on ‘social capital’, and analyse the aspects of residential stability while focusing on tenants' perceptions of eviction risk as the key outcome of interest. We used data from 1800 households, obtained from 18 poor neighbourhoods across three cities in Bangladesh. The findings suggest that social capital has a potential role to play in increasing residential stability among the urban poor. These are critical in the upgrading and redevelopment of housing, and in promoting the residential stability of the urban poor in Bangladesh and other LDCs. The potential engagement of social capital in housing the poor could make a valuable contribution to the literature on international housing policy. We discuss the implications at length, and draw links with international housing policy discourse.