Parallel Session 1B

Traditional land use and land cover (LULC) classification approaches using spectral bands display persistent limitations in distinguishing similar landcover types, particularly within heterogeneous urban–rural transition zones. This research examines the effectiveness of multi-feature fusion for improving classification accuracy by systematically evaluating combinations of spectral indices with machine learning classifiers. Sentinel-2 imagery of Kaduwela, Sri Lanka, was utilized, focusing on six LULC categories: water, forest, vegetation, roads, buildings, and rock exposure. The methodology involved an initial evaluation of baseline RGB performance using Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT) classifiers. Subsequently, 27 spectral indices were generated and integrated with RGB to form a 30-dimensional feature set, followed by Principal Component Analysis (PCA) to reduce dimensionality, retaining five components that explained over 95% of the variance for subsequent classification. The RGB feature set yielded accuracies of 39.22% (SVM), 44.19% (DT), and 50.45% (RF); integration of RGB with 27 indices improved accuracies to 53.22% (SVM), 52.01% (DT), and 52.94% (RF); while the PCA-reduced feature set provided 54.70% (SVM), 46.18% (DT), and 49.34% (RF). The findings highlight that in heterogeneous and urban–rural interfaces, PCA-based reduction of spectral indices has improved SVM classification and reduced computational load. For future studies, further hyperparameter tuning could enhance accuracy.

Landslides are among the most destructive natural hazards, causing significant damage to infrastructure, ecosystems, and human settlements. Monitoring vegetation recovery after such events is critical for ecological restoration and effective hazard management. Given the challenges of conducting field surveys and UAV-based monitoring in inaccessible terrain, remote sensing approaches can be an efficient alternative. Sentinel-2 optical imagery, with a native spatial resolution of 10 meters and minimal cloud interference, provides a valuable resource for monitoring vegetation dynamics. However, to obtain more detailed and accurate spatial information, alternative approaches such as downscaling are required. In this study, the Sentinel-2 Deep Resolution 3.0 model (S2DR3) is used to downscale imagery from 10m to 1m resolution. Leveraging this enhanced resolution, the Normalized Difference Vegetation Index (NDVI) is applied to monitor vegetation disturbance and regrowth over time following a rainfall-induced landslide that occurred on 4 June 2021 in Dumbarawatta, Sri Lanka. The analysis is conducted using the Google Earth Engine platform, offering a scalable and cost-effective methodology for post-landslide environmental monitoring. This approach supports informed decision-making in landscape recovery and land management, particularly in complex and mountainous terrains. The S2DR3 downscaled product detected up to 5% more vegetation cover than Sentinel-2, enhancing accuracy in post-landslide recovery assessments.

Developing countries like Sri Lanka face severe transportation challenges that arise due to increased demand driven by rapid urbanization and population growth. This highlights the necessity of long-term efficient, environmentally friendly, and viable transport solutions like Light Rail Transit (LRT). Thus, this study proposes an integrated Remote-Sensing and Geographic Information Systems (GIS) with Analytical Hierarchy Process (AHP)-based Multi-Criteria Decision Analysis (MCDA) approach to identify optimal LRT station locations within the Colombo Metropolitan Area (CMA). Eight important factors such as slope, land use, proximity to buildings, environmentally sensitive areas, socially sensitive locations, existing transportation nodes, main roads, population density were systematically weighted, analysed, and used to produce suitability maps. Station locations were carefully selected based on suitability values across 31 zones and validated through Google imagery to assess land feasibility and availability. The demand estimation and accessibility analysis were done within the 1 km buffer zones surrounding each proposed station. This confirms that the majority of selected stations have better ridership potential and good road accessibility. Despite certain limitations in datasets, this structure can be used to design sustainable urban transport planning and long-term mobility policies applicable to Colombo, especially with the integration of precise field measurements and high-resolution imagery.

Accurate representation of Earth's diverse terrains is fundamental for geospatial applications, from urban planning to environmental modeling. This research explores the challenge of selecting an appropriate Digital Elevation Model (DEM) for diverse terrain types, focusing on the vertical accuracies in different topographical settings. The study uses various elevation data sources, including the Shuttle Radar Topography Mission (SRTM), Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), high-precision Light Detection and Ranging (LiDAR), data from Unmanned Aerial Vehicles (UAVs), and fine-grained 1:10000 digital vector data. The research aims to identify the suitability of DEMs for diverse topographical natures, revealing the complex interplay between terrain diversity and DEM accuracy. The findings show that the 1:10000 digital vector data layer is the best DEM for three distinct terrain types: highly hilly, moderately hilly, and flat. ASTER, 1:10000 digital vector data, and SRTM provide roughly identical DEM accuracy for flat terrain. The study emphasizes the need for a tailored approach in selecting DEMs to represent Earth's diverse terrains accurately.

The Kelani River, a major freshwater resource in Sri Lanka, has experienced significant water quality degradation over the past two decades due to land use and land cover (LULC) changes and climate variability. This study investigates the spatial and temporal impacts of these factors on key water quality parameters from 2003 to 2023 across the upstream, midstream, and downstream segments of the river. Using remote sensing, GIS (ArcGIS Pro), and statistical analysis in Python, the study evaluates relationships between LULC categories and water quality parameters, as well as between climate factors and water quality parameters such as pH, dissolved oxygen (DO), biological oxygen demand (BOD), chemical oxygen demand (COD), nitrate, phosphate, turbidity, electrical conductivity (EC), and temperature. Findings reveal a substantial increase in developed land, particularly downstream, alongside a decline in vegetation, which contributes to elevated organic pollution and reduced oxygen levels. Strong positive correlations (r=0.86) were observed between rainfall and turbidity, as well as temperature and BOD (r=0.61), highlighting the influence of seasonal climate variability on water quality of midstream and downstream. These results underscore the need for integrated watershed management that accounts for both spatial and temporal variations in land use and climate, to safeguard the Kelani River’s water quality and support sustainable resource planning.

Rapid urbanization in Colombo, Sri Lanka, has intensified the Urban Heat Island (UHI) effect, raising local temperatures, increasing energy use, and stressing urban infrastructure. This study assesses spatial and temporal UHI dynamics in Colombo from 2001 to 2024 using multi-temporal satellite data, remote sensing, and GIS-based analysis. Land Surface Temperature (LST), land cover, and ecological indices (NDVI, NDBI, NBUI, UTFVI) were analyzed to identify trends and hotspots. Results show a rise in built-up areas, a decline in vegetation, and increased LST, with 39% of the city experiencing extreme heat stress, especially in dense urban cores. The study recommends increasing urban green cover, using high-albedo materials, and implementing climate-sensitive planning to align with SDGs 11 and 13. These findings provide a replicable framework for UHI mitigation and support sustainable, climate-resilient urban development in Colombo.

Waste generation and energy scarcity are major problems in the world nowadays. To address both these problems, as the best solutions, waste to energy technologies (WTE) are introduced and are now drastically spreading around the world. Due to the various waste generation according to different countries, there are suitable WTE technologies for each waste type. The developed countries generate high energetic waste with less moisture, while developing countries produce high moist, low energy waste. WTE technologies are further divided into thermochemical and biochemical conversion by the process and optimized using newer techniques to achieve a greater waste conversion and energy recovery while reducing the negative impact on the environment, society and economy.

This study introduces a novel scientific approach that integrates hyperspectral imaging and artificial intelligence to enhance rock type classification. A core contribution of this work is the development of an original segmentation algorithm capable of identifying subtle mineralogical variations in core samples. This algorithm enables the automated classification of diverse rock types with high accuracy and interpretability. The original algorithms were implemented into a user-friendly application that streamlines the image analysis process, thereby reducing dependency on expert geological interpretation. This enables rapid and reliable evaluation, even by non-specialist users. To validate the application's performance, a case study was conducted. Comparing the segmentation-based rock type classification with conventional visual inspection and Python-based scripts, confirming comparable accuracy. The findings demonstrate that the proposed system offers both scientific novelty and practical value, contributing to the advancement of non-contact, efficient, and accurate geotechnical analysis in both research and field environments.

This final segment invites reflections from presenters and attendees, synthesizing key insights from the session. The session chair will formally conclude the discussion by summarizing thematic threads, highlighting interdisciplinary contributions, and outlining potential collaborative directions.