Coasts are critical ecological, economic and social interfaces between terrestrial and marine systems. The current upsurge in the acquisition and availability of remote sensing datasets, such as Landsat remote sensing data series, provides new opportunities for analyzing multi-decadal coastal changes and other components of coastal risk. The emergence of machine learning-based techniques represents a new trend that can support large-scale coastal monitoring and modeling using remote sensing big data. This study presents a comprehensive multi-decadal analysis of coastal changes for the period from 1990 to 2024 using Landsat remote sensing data series along the eastern and southern coasts of Peninsular Malaysia. These coastal regions include the states of Kelantan, Terengganu, Pahang, and Johor. An innovative approach combining deep learning-based shoreline extraction with the Digital Shoreline Analysis System (DSAS) was meticulously applied to the Landsat datasets. Two semantic segmentation models, U-Net and DeepLabV3+, were evaluated for automated shoreline delineation from the Landsat imagery, with U-Net demonstrating superior boundary precision and generalizability. The DSAS framework quantified shoreline change metrics—including Net Shoreline Movement (NSM), Shoreline Change Envelope (SCE), and Linear Regression Rate (LRR)—across the states of Kelantan, Terengganu, Pahang, and Johor. The results reveal distinct spatial–temporal patterns: Kelantan exhibited the highest rates of shoreline change with erosion of −64.9 m/year and accretion of up to +47.6 m/year; Terengganu showed a moderated change partly due to recent coastal protection structures; Pahang displayed both significant erosion, particularly south of the Pahang River with rates of over −50 m/year, and accretion near river mouths; Johor’s coastline predominantly exhibited accretion, with NSM values of over +1900 m, linked to extensive land reclamation activities and natural sediment deposition, although local erosion was observed along the west coast. This research highlights emerging erosion hotspots and, in some regions, the impact of engineered coastal interventions, providing critical insights for sustainable coastal zone management in Malaysia’s monsoon-influenced tropical coastal environment. The integrated deep learning and DSAS approach applied to Landsat remote sensing data series provides a scalable and reproducible framework for long-term coastal monitoring and climate adaptation planning around the world.
Accurate identification of alteration minerals in remote polar regions remains a significant challenge because field access is limited, environmental conditions are extreme, and exposed lithologies commonly show mixed spectral responses. Satellite-based multispectral remote sensing, particularly using the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), provides an efficient means of investigating surface mineralogy in ice-free Antarctic terrains. This study applies a sequential dimensionality reduction and spectral classification workflow integrating Principal Component Analysis (PCA), Independent Component Analysis (ICA), Minimum Noise Fraction (MNF), and Mixture-Tuned Matched Filtering (MTMF) to ASTER imagery from the Dry Valleys of South Victoria Land, Antarctica. The workflow identified major mineral groups including iron oxides and hydroxides, Al–OH and Mg–OH phyllosilicates, carbonates, silica phases, and mafic–ultramafic indicator minerals. These mapped mineral groups are spatially associated with granitoid and metasedimentary basement rocks, Beacon Supergroup sedimentary units, Jurassic diabase intrusions, and Ferrar volcanic rocks. Accuracy assessment against lithological reference classes indicated an overall accuracy of about 78% and a kappa coefficient of approximately 0.72. The results show that the integrated ASTER workflow can support regional mineral group mapping in exposed polar bedrock terrains, while individual mineral interpretations remain limited by ASTER spectral resolution, mixed pixels, and restricted field validation.
31 August 2026 in Journal of Sustainability Science and Management
The current study aims to analyse long-term coastal processes along the coast of Terengganu and Johor in Peninsular Malaysia over a 34-year period (1990–2024) with the aim of comparing two quite different coastal systems that vary in geomorphological characteristics and level of anthropogenic alteration. The eight years (1990, 1993, 1998, 2002, 2008, 2014, 2018, and 2024) were selected based on cloud-free satellite image availability and spatial consistency. DSAS is used to represent long-term shoreline change. Annual Landsat satellite remote sensing composites were examined and the shoreline was drawn using the U-Net deep learning segmentation model, with an overall accuracy of 98.7%, which provided the most robust shoreline delineations. Digital Shoreline Analysis System (DSAS) was used to measure the shoreline changes by use of Linear Regression Rate (LRR) and Net Shoreline Movement (NSM) measures. The results show that the Terengganu coast is relatively stable and shows a medium erosion and accretion due to the dynamics of the monsoonal waves in combination with the recent introduction of coastal protection structures. Johor coast, on the other hand, shows high rates of accretion due to large-scale land reclamation, estuarine sedimentation, as well as urban development, and erosion persists along the coast facing the Malacca, which experiences high wave energy.