The availability of nighttime satellite imagery provides unique opportunities for monitoring fishing activity in data-sparse ocean regions. This study leverages Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band monthly composite imagery to identify and classify recurring spatial patterns of fishing activity in the Korean Exclusive Economic Zone from 2014 to 2024. While prior research has primarily produced static hotspot maps, our approach advances geospatial fishing activity identification by employing machine learning techniques to group similar spatiotemporal configurations, thereby capturing recurring fishing patterns and their temporal variability. A convolutional autoencoder and a Gaussian Mixture Model (GMM) were used to cluster the VIIRS imagery. Results revealed seven major nighttime light hotspots. Results also identified four cluster patterns: Cluster 0 dominated in December, January, and February, Cluster 1 in March, April, and May, Cluster 2 in July, August, and September, and Cluster 3 in October and November. Interannual variability was also identified. In particular, Clusters 0 and 3 expanded into later months in recent years (2022–2024), whereas Cluster 1 contracted. These findings align with environmental changes in the region, including ocean temperature rise and declining primary productivity. By integrating autoencoders with probabilistic clustering, this research demonstrates a framework for uncovering recurrent fishing activity patterns and highlights the utility of satellite imagery with GeoAI in advancing marine fisheries monitoring.

Highway interchanges are vulnerable components of transport networks, often prone to congestion and crashes. Traditional monitoring methods like loop detectors or travel time queries often fail to capture the granular spatiotemporal distribution of bottlenecks in detail. To address this gap, this study introduces a new approach to quantify congestion and analyze bottleneck dynamics at Atlanta’s Tom Moreland Interchange, one of the nation’s most congested sites. A percent Traffic Congestion (pTC) metric was developed from the Google Maps Traffic Layer for twelve directional routes and validated against observed travel times obtained independently through the Google Maps Routes API. Traffic imagery collected every ten minutes for four months and 746 crash records were analyzed. Findings reveal distinct spatial patterns and temporal dynamics of congestion, with northbound I-85 and eastbound I-285 most affected during afternoon peaks. A quadratic model provided the best fit between pTC and travel times (R² = 0.85), confirming pTC as a reliable congestion indicator. An LSTM model using pTC time series also accurately predicted mobility trends at the I-285 west to I-85 north bottleneck. Additionally, Seasonal-Trend decomposition using LOESS (STL) identified congestion anomalies, and their association was analyzed with crashes. The proposed methodology offers transportation agencies a cost-effective framework for monitoring, measuring, and understanding congestion in complex interchanges.

Satellite-based nighttime light imagery offers a powerful means of monitoring fishing activity across data-sparse ocean regions, yet the influence of image standardization on machine-learning-based pattern classification has received little attention. This study analyzed Visible Infrared Imaging Radiometer Suite Day/Night Band (VIIRS DNB) monthly composite imagery of the Korean Exclusive Economic Zone (EEZ) from 2014 to 2024, applying an identical Convolutional Autoencoder and Gaussian Mixture Model (CAE-GMM) framework under both local and global standardization. Global standardization produced three or four major spatiotemporal clusters that broadly corresponded to seasonal fishing cycles: a high-intensity autumn–winter pattern, an expanded summer–autumn pattern, and a low-intensity winter–spring pattern. In the four-cluster solution, the fourth cluster represented the transition periods among the three seasonal patterns. Particularly, the strong autumn-winter pattern weakened after 2019 and was increasingly replaced by winter-spring clusters. Comparison of the two standardization methods showed that local standardization categorizes images primarily by their internal spatial light distribution, whereas global standardization additionally reflects brightness differences across the time series. As a result, images with similar spatial patterns but lower intensity, such as January through March in recent years, were assigned to a different cluster. These findings demonstrate that standardization is not just a preprocessing step but a decisive methodological choice that depends on the research objective in fisheries monitoring with nighttime lights.

This study investigates the temporal shifts in seasonal vegetation coloration, focusing on changes in greenness levels (measured by NDVI) from 1982 to 2023, using multiple satellite sources including AVHRR, Landsat, MODIS, and VIIRS. The primary objectives of this research are twofold: (1) to determine whether greenness levels have significantly changed during spring and fall, and (2) to assess whether there are notable differences in NDVI values among the various imaging sensors used. Given the context of global warming, it is plausible that greenness levels would show an increase on the same date in early spring or late fall across multiple years. Our study area consists of the Great Smoky Mountains National Park, where we analyze the timing of seasonal changes, revealing a trend toward earlier springs and longer falls. Our findings indicate significant increases in NDVI values during spring across all datasets, notably from AVHRR and Landsat, while fall data shows less consistent trends, with MODIS and VIIRS revealing minimal changes. The research highlights the importance of sensor selection in NDVI measurements, with non-parametric test results confirming significant variances among the sensors analyzed. This study contributes to understanding the implications of climate change on vegetation dynamics, underscoring the need for continued monitoring as seasonal patterns evolve.