http://repository.ou.ac.lk/handle/94ousl/3432 2026-08-31T02:04:31Z 2026-08-31T02:04:31Z Shameeha, M.S.M.F. Siyad, N.M. http://repository.ou.ac.lk/handle/94ousl/3476 2026-08-21T06:44:56Z 2025-01-01T00:00:00Z

Detecting Underwater Macroplastic Pollution: A Review on AI-Based Computer Vision Methods and their Relevance to Sri Lanka’s Marine Ecosystem Shameeha, M.S.M.F.; Siyad, N.M. The escalating crisis of marine plastic pollution, particularly macroplastic debris, poses severe threats to marine biodiversity, coastal ecosystems, and human livelihoods. Sri Lanka, ranked among the top global contributors to marine plastic waste, suffers from a lack of systematic and scalable monitoring mechanism, especially for underwater macroplastic detection. Traditional survey methods are often manual, labour-intensive, and limited in coverage. Recent advancements in artificial intelligence, specifically computer vision, present promising alternatives for automating detection and analysis of marine debris. This review paper critically examines the current landscape of AI-based approaches for underwater macroplastic detection, highlighting their methodologies, datasets, performance metrics, and limitations. While global efforts have largely emphasized surface litter and microplastic detection, underwater macroplastic monitoring remains underexplored. Moreover, Sri Lanka lacks context-specific studies and affordable, software-based AI tools that can leverage existing underwater imagery to detect macroplastic waste. By synthesizing global literature and identifying region-specific research gaps, this paper advocates for the development of lightweight, AI-powered systems tailored to the Sri Lankan coastline. Such innovations could enable continuous monitoring, inform policy decisions, and strengthen marine conservation efforts in data-scarce and resource-constrained settings.

2025-01-01T00:00:00Z Wazny, H.S. Siyad, N.M. http://repository.ou.ac.lk/handle/94ousl/3475 2026-08-25T03:11:53Z 2025-01-01T00:00:00Z

AI and IoT-Driven Framework for Monitoring and Restoring of Mangrove Ecosystem Health in Coastal Sri Lanka Wazny, H.S.; Siyad, N.M. Mangrove ecosystems in Sri Lanka are critical for coastal protection, biodiversity, and carbon sequestration, but face increasing threats from anthropogenic activities and climate change. Traditional monitoring methods often lack the precision and speed required to detect early stage degradation. This study proposes an AI- and IoT-driven framework for monitoring and restoring mangrove ecosystem health in Sri Lanka, based on the global applications of AI, IoT, and Unmanned Aerial Vehicles (UAVs) in mangrove conservation. Findings show that AI techniques such as deep learning, IoT sensors, and UAVs have shown global success in species classification, degradation detection, and high-resolution monitoring. However, Sri Lanka still lacks an integrated AI- and IoT-based system for its mangrove ecosystems. Key gaps include limited localized AI models, poor technological integration, and a lack of real-time monitoring frameworks. To address these gaps, this study proposes a Sri Lanka-specific smart monitoring framework that integrates UAVs for canopy imaging, IoT sensors for root-level data, and AI analytics for real-time anomaly detection and informed decision-making. The four-layered architecture emphasizes data acquisition, secure transmission, machine learning, and an interactive dashboard for real-time monitoring. A phased implementation strategy and recommendations for community engagement, cross-sector partnerships, and policy integration are also provided. With careful piloting and stakeholder collaboration, this framework can transform mangrove conservation efforts in Sri Lanka from reactive to predictive, data-driven ecosystem management.

2025-01-01T00:00:00Z Danushiya, K. Siyad, N.M. http://repository.ou.ac.lk/handle/94ousl/3474 2026-08-21T06:47:09Z 2025-01-01T00:00:00Z

Early Detection and Diagnosis of Coconut Leaf Diseases in Sri Lanka’s Coconut Triangle: A Systematic Review Danushiya, K.; Siyad, N.M. This study presents a Systematic Literature Review (SLR) on the early detection and diagnosis of coconut leaf diseases in Sri Lanka’s Coconut Triangle, a region critical to the nation’s agricultural economy. The review systematically evaluates published research on deep learning-based models, image classification techniques, and hybrid approaches that integrate environmental data for more reliable diagnosis. To ensure methodological rigor, the study followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) framework. Relevant studies were retrieved from scholarly databases including IEEE Xplore, ScienceDirect, Springer, Scopus, and Google Scholar using predefined search strings. Strict inclusion and exclusion criteria were applied to filter peer-reviewed articles published between 2016 and 2025, ensuring relevance and reproducibility. A total of 20 papers met the criteria for final review, covering a diverse range of approaches such as Convolutional Neural Networks (CNNs), transfer learning models (VGG16, ResNet, EfficientNet), ensemble methods (CNN–SVM), and IoT-assisted systems. The synthesis of findings highlights several insights: transfer learning-based CNNs achieved over 90% accuracy, even for subtle early-stage symptoms. Hybrid approaches combining CNNs with classifiers like SVMs improved precision, reducing false positives and enhancing robustness across coconut varieties. Integrating environmental data (humidity, rainfall, temperature) increased accuracy by 6– 10%, stressing the need for region-specific models in Sri Lanka’s diverse agro-climatic zones. However, most systems lack large-scale field validation, mobile deployment, and consideration of smallholder farmer resource constraints. Key research gaps include limited Sri Lanka-specific datasets, inadequate focus on multi-disease co-infections, and the absence of farmer-oriented mobile and IoT tools for real-time disease monitoring. Finally, the study highlights future directions such as building larger and varietal-specific datasets, experimenting with advanced architecture (EfficientNet, Vision Transformers), and developing lightweight, offline-capable mobile applications to ensure accessibility for rural farmers. The integration of IoT sensors and climate forecasting models is also recommended to move from disease detection towards predictive and preventive farming strategies. This review contributes to the body of knowledge by not only consolidating existing research but also providing actionable insights for researchers, policymakers, and agricultural technology developers to ensure sustainable disease management and resilience in Sri Lanka’s coconut sector.

2025-01-01T00:00:00Z Aratthanage, K.D.B. Premachandra, N.G.P.R. Kirushika, J. Madhushika, T.D.T. Subasighe, H.P.I. Wanigasuriya, N.C. http://repository.ou.ac.lk/handle/94ousl/3473 2026-08-21T06:48:07Z 2025-01-01T00:00:00Z

Plastic Waste Leakage in Urban River Basins of Sri Lanka: A Geospatial and Machine Learning Perspective Aratthanage, K.D.B.; Premachandra, N.G.P.R.; Kirushika, J.; Madhushika, T.D.T.; Subasighe, H.P.I.; Wanigasuriya, N.C. Plastic waste leakage into the urban river basins has emerged as a critical environmental challenge in Sri Lanka, threatening aquatic ecosystems, public health, and urban resilience. Rapid urbanization, inadequate waste management, and poor drainage infrastructure have accelerated the accumulation and transport of plastic debris into waterways. This study presents a geospatial and machine learning approach to identify and model the key drivers of plastic waste leakage in selected urban river basins. High-resolution geospatial datasets, including land use, population density, slope, rainfall patterns, and proximity to waste disposal sites, were integrated with field-based leakage observations. A Random Forest classifier was employed to predict leakage hotspots, achieving a moderate level of accuracy. Feature importance analysis highlighted waste site proximity, urban density, and hydrological factors as the dominant predictors. The confusion matrix further illustrates the model's strengths in identifying high-risk zones; however, misclassification in low-risk areas suggests potential improvement through the inclusion of additional environmental and socio-economic variables. The findings offer actionable insights for urban planners, waste management authorities, and policymakers to develop targeted interventions for mitigating plastic waste in riverine environments.

2025-01-01T00:00:00Z