Members’ Publication

sdfsdf

Extracting building information from remotely sensed images is essential in various geographic and environmental applications. Specifically, there is a growing demand for distinguishing buildings based on roof colors from low-cost but high-resolution RGB images. However, this task presents significant challenges due to the variability in building color, size, and style, as well as their resemblance to nonbuilding objects. The existing GEographic Object-Based Image Analysis (GEOBIA) approaches often struggle with misclassification, mainly because they do not effectively leverage spatial information during the classification stage. Tabular Deep Learning (DL) models have emerged as promising alternatives to shallow classifiers, demonstrating improved performance in recent years. However, their effectiveness in extracting buildings based on roof color has not been thoroughly examined. To address these challenges and improve the accuracy of building extraction, this study proposed a target-based model that incorporates a sequential extraction process using tabular DL models such as Gated Additive Tree Ensemble (GATE), Neural Oblivious Decision Ensemble (NODE). The proposed method adopted a hybrid segmentation approach to effectively segment the image and extract each segment's spectral, textural, geometrical, and contextual features. Non-building objects were systematically eliminated based on their representation within the image. Subsequently, buildings with varying roof colors—brown, black, and white—were extracted. Spatial information was then meticulously integrated into the classification process. The proposed methodology was tested on a UAV image with a spatial resolution of 0.20 m and three visible bands—red, green, and blue—captured in Kingston, Ontario, Canada. This enhanced approach significantly improved precision and overall classification accuracy, demonstrating the effectiveness of incorporating spatial data into the extraction process. This research introduced a framework for incorporating spatial information into tabular models that would serve as a foundation for further improving building extraction accuracy in future studies.

Sentinel-2 satellites are one of the major instruments in remote sensing (RS) technology that has revolutionized Earth observation research, as its main goal is to offer high-resolution satellite data for dynamic monitoring of Earth’s surface and climate change detection amongst others. However, visual observation of Sentinel-2 satellite data has revealed that most images obtained during the winter season contain snow noise, posing a major challenge and impediment to satellite RS analysis of land surface. This singular effect hampers satellite signals from capturing important surface features within the geographical area of interest. Consequently, it leads to information loss, image processing problems due to contamination, and masking effects, all of which can reduce the accuracy of image analysis. In this study, we developed a snow-cover removal (SCR) model based on the Cycle-Consistent Adversarial Networks (CycleGANs) architecture. Data augmentation procedures were carried out to salvage the effect of the limited availability of Sentinel-2 image data. Sentinel-2 satellite images were used for model training and the development of a novel SCR model. The SCR model captures snow and other prominent features in the Sentinel-2 satellite image and then generates a new snow-free synthetic optical image that shares the same characteristics as the source satellite image. The snow-free synthetic images generated are evaluated to quantify their visual and semantic similarity with original snow-free Sentinel-2 satellite images by using different image qualitative metrics (IQMs) such as Structural Similarity Index Measure (SSIM), Universal image quality index (Q), and peak signal-to-noise ratio (PSNR). The estimated metric data shows that Q delivers more metric values, nearly 95%, than SSIM and PRSN. The methodology presented in this study could be beneficial for RS research in DL model development for environmental mapping and time series modeling. The results also confirm the DL technique’s applicability in RS studies.

Landslides significantly threaten human life, infrastructure, and environmental balance. In the hilly regions of Bangladesh, including Sylhet and Rangamati, landslides are frequent, causing 727 deaths and 1017 injuries between 2000 and 2018. The northeastern section of Bangladesh is projected to receive over 500–600 mm of precipitation in 2023, breaking records over the past 122 years, according to the European Centre for Medium-Range Weather Forecasts (ECMWF). With an elevation range of 0 to 195 m above sea level and 18% of its total land area covered by water bodies, Rangamati is particularly vulnerable to landslides. Despite the devastating impact of landslides, susceptibility assessment and risk management strategies are lacking. This research aims to address this gap by developing a comprehensive framework for sustainable landslide risk mitigation using geostatistical and geospatial modeling techniques. Factors such as land use and land cover (LULC), elevation, slope, topographic wetness index (TWI), precipitation, lithology, soil type, normalized difference vegetation index (NDVI), and distance from roads are used to create a frequency ratio (FR) model and identify landslide susceptibility and risk zones. The resulting high-resolution landslide susceptibility map (LSM) and risk assessment models provide valuable insights for policymakers, land-use planners, and stakeholders involved in disaster risk reduction and sustainable development. By applying geostatistical and geospatial modeling techniques to assess landslide susceptibility, manage risk, and promote sustainability, this research enhances resilience to landslides and highlights the importance of proactive planning and informed decision-making in mitigating the impact of landslides for promoting sustainable development in hilly regions.

This professional report investigates the drivers, processes, and consequences of sand-filling in developing housing real estate in Dhaka, Bangladesh. It examines its implications for the city's environmental sustainability and urban governance. Through a qualitative research approach relying on documentary analysis and case study methods, the study reveals a complex interplay of colonial legacies, political-economic interests, and institutional weaknesses shaping Dhaka's unsustainable and inequitable sand-filling and housing development patterns. The report highlights these practices' significant environmental and socio-economic impacts on the city's hydrology, ecology, and marginalized communities. It analyzes the gaps and challenges in the existing institutional and regulatory frameworks governing these processes. The report identifies potential strategies for addressing the challenges of sand-filling and promoting sustainable housing development in Dhaka, emphasizing the need for officially delineating watershed boundaries, developing government databases, providing accessible information through geo-portals, and adopting innovative planning approaches such as the "Dhaka Nexus" and "terraqueous planning." It also underscores the importance of considering the broader context of Dhaka's rapid population growth and geographical constraints in addressing these issues, discussing the need for increased housing density, polycentric regional development, and context-specific strategies that prioritize hydrological infrastructure and social equity. The study contributes to advancing the knowledge of urban transformation, environmental sustainability, and social justice in the context of rapid urbanization and colonial legacies in the Global South.