Coastal erosion is a critical environmental challenge in the Upper Gulf of Thailand, driven by both natural processes and human activities. This study analyzes 35 years (1988–2023) of shoreline changes using geoinformatics, machine learning algorithms (Random Forest, Support Vector Machine, Maximum Likelihood, Minimum Distance), and the Digital Shoreline Analysis System (DSAS). The results show that the Random Forest algorithm, utilizing spectral bands and indices (NDVI, NDWI, MNDWI, SAVI), achieved the highest classification accuracy (98.17%) and a Kappa coefficient of 0.9432, enabling reliable delineation of land and water boundaries. The extracted annual shorelines were validated with high accuracy, yielding RMSE values of 13.59 m (2018) and 8.90 m (2023). The DSAS analysis identified significant spatial and temporal variations in shoreline erosion and accretion. Between 1988 and 2006, the most intense erosion occurred in regions 4 and 5, influenced by sea-level rise, strong monsoonal currents, and human activities. However, from 2006 to 2018, erosion rates declined significantly, attributed to coastal protection structures and mangrove restoration. The period 2018–2023 exhibited a combination of erosion and accretion, reflecting dynamic sediment transport processes and the impact of coastal management measures. Over time, erosion rates declined due to the implementation of protective structures (e.g., bamboo fences, rock revetments) and the natural expansion of mangrove forests. However, localized erosion remains persistent in low-lying, vulnerable areas, exacerbated by tidal forces, rising sea levels, and seasonal monsoons. Anthropogenic activities, including urban development, mangrove deforestation, and aquaculture expansion, continue to destabilize shorelines. The findings underscore the importance of sustainable coastal management strategies, such as mangrove restoration, soft engineering coastal protection, and integrated land-use planning. This study demonstrates the effectiveness of combining machine learning and geoinformatics for shoreline monitoring and provides valuable insights for coastal erosion mitigation and enhancing coastal resilience in the Upper Gulf of Thailand.

In this study, a recovery assessment of the permanent housing and living conditions in the aftermath of the 2004 Tsunami in Phang-nga Province, Thailand, was conducted using geoinformatics technologies, field observations, and living-related parameters from basic minimum need (BMN) data retrieved from the Ministry of Interior. In the results, 29 permanent housing projects were mapped, classified into five sizes (very small, small, medium, large, and very large), and overlaid with the tsunami-inundated zone visually interpreted from satellite images. Thirteen out of twenty-nine projects were reconstructed in the inundation zone (in situ), while the rest were relocated to higher ground. Permanent houses were rebuilt in 18 communities in three patterns: single-story or one-story houses (511 houses), single-story and raised-basement houses (58 houses), and two-story houses (712 houses). The selected BMN’s living-related parameters, such as sufficient water for household consumption (dimension: dwelling), employment of people between 15 and 60 years old (dimension: economy), and participation in communities’ activities (dimension: participation), which covered 2002–2015 at the community-based level, were compared annually to its criterion and indicated as passing or not passing the standard. The reconstructed communities recovered (passing the requirements) within four years of transferring to the reconstructed houses.

This research looks at how Geographical Indication (GI)-certified agricultural products are managed in Thailand. It focuses on the sales and production cycles, the income they bring in, and the main problems they face. Using a mixed-methods approach, surveys and interviews were conducted with representatives of 77 GI-certified products categorized into rice (10), foods (15), and plant fruits and vegetables (52). Four management patterns emerged: one production and one selling season (25 products), one production with multiple selling seasons (15), two production and selling cycles (19), and multiple cycles (18). Contributions to household income were classified into four levels: Low (19), Medium (18), High (13), and Maximum (27). A Chi-Square test revealed no significant association between management patterns and income levels. Producers identified critical barriers, including limited market access and climate variability, which affected product quantity and quality. Many expressed low confidence in product reputation, citing the inability to secure price premiums over non-GI products. The study underscores the need for targeted policies to address market access, climate resilience, and product reputation. These findings provide valuable insights for GI authorities, policymakers, and stakeholders to sustain GI management, enhance rural incomes, and align with Sustainable Development Goals. The results are broadly applicable to other developing countries reliant on agricultural GIs.

All-sky cameras provide continuous hemispherical observations essential for atmospheric monitoring and observatory operations; however, automated classification of sky conditions in tropical environments remains challenging due to strong illumination variability, atmospheric scattering, and overlapping thin-cloud structures. This study proposes EfficientNet-Attention-SPP Multi-scale Network (EASMNet), a physics-aware deep learning framework for robust all-sky scene classification using hemispherical imagery acquired at the Thai National Observatory. The proposed architecture integrates Squeeze-and-Excitation (SE) blocks for radiometric channel stabilization, the Convolutional Block Attention Module (CBAM) for spatial–semantic refinement, and Spatial Pyramid Pooling (SPP) for hemispherical multi-scale context aggregation within a fully fine-tuned EfficientNetB7 backbone, forming a domain-aware atmospheric representation framework. A large-scale dataset comprising 122,660 RGB images across 13 day–night sky-scene categories was curated, capturing diverse tropical atmospheric conditions including humidity, haze, illumination transitions, and sensor noise. Extensive experimental evaluations demonstrate that the EASMNet achieves 93% overall accuracy, outperforming representative convolutional (VGG16, ResNet50, DenseNet121) and transformer-based architectures (Swin Transformer, Vision Transformer). Ablation analyses confirm the complementary contributions of hierarchical attention and multi-scale aggregation, while class-wise evaluation yields F1-scores exceeding 0.95 for visually distinctive categories such as Day Humid, Night Clear Sky, and Night Noise. Residual errors are primarily confined to physically transitional and low-contrast atmospheric regimes. These results validate the EASMNet as a reliable, interpretable, and computationally feasible framework for real-time observatory dome automation, astronomical scheduling, and continuous atmospheric monitoring, and provide a scalable foundation for autonomous sky-observation systems deployable across diverse climatic regions.