A Temporal Attention-Based SARIMA-BiLSTM Residual Learning Model Tuned by Grey Wolf Optimizer for Parallel Urban Traffic Forecasting by Manas Kamal Das, Christopher Columbus Chinnappan, E. Elakiya

“…The SARIMA component captures underlying seasonal and linear patterns in traffic flow, while the residuals—representing unmodeled nonlinear dynamics—are learned by the BiLSTM module. …”
Get full text

Runoff Simulation Study of Ganjiang River Basin Based on Distributed Time-varying Gain Hydrological Model and CN05.1 Precipitation Data by ZHONG Qi, FU Xiaolei, JIANG Xiaolei, ZHANG Yuchen, HU Leyi, ZHANG Liping

“…Additionally,the paper evaluates the applicability of the distributed time-variant gain hydrological model (DTVGM) and CN05.1 precipitation data in simulating runoff in the Ganjiang River Basin.The results show that:① CN05.1 precipitation and station interpolated precipitation exhibit similar variation patterns over multiple years,with a high spatial distribution correlation and a mean correlation coefficient (R) of 0.90.The correlation between CN05.1 daily precipitation and interpolated daily precipitation is also high,with a root mean square error (RMSE) of less than or equal to 7.52 mm and an R value greater than or equal to 0.81.② Using CN05.1 precipitation and station interpolated precipitation data,the flow of six hydrological stations,including Xintian,in the Ganjiang River Basin is simulated from 1961 to 2009.The simulated flow generally exceeds the measured flow during high flow periods,indicating that the model overestimates the simulation of large flows.③ The accuracy of runoff simulation based on CN05.1 precipitation is high, whether for daily or monthly runoff, with better performance in simulating monthly runoff compared to daily runoff.Therefore,the DTVGM model and CN05.1 precipitation data are highly applicable for runoff simulation in the Ganjiang River Basin.…”
Get full text

Assessment of suitability evaluation for Ficus altissima blume ancient trees in different climatic environments in Guangxi, China by Hongliang Gu, Yuxia Chen, Qinqin Zhang

“…The spatial distribution of these trees is highly discrete, influenced by topographical constraints and intraspecific competition. …”
Get full text

Regional-scale assessment of groundwater recharge and the water balance for Austria by Hanna Zeitfogel, Mathew Herrnegger, Karsten Schulz

“…Study Focus: Knowledge of regional groundwater recharge patterns is essential for sustainable water resource management. …”
Get full text

Bridging the gap in flood risk communication: a comparative study of community and organizational social media posts using natural language processing by Christin Salley, Nathan Fox, Alyssa Schubert

“….), with escalating risks due to climate change-induced factors like rising sea levels and erratic rainfall patterns. While organizational efforts to mitigate the social and economic impacts of floods exist, there is a continued need for innovative approaches to flood management, particularly in flood risk communication. …”
Get full text

Multivariate Segment Expandable Encoder-Decoder Model for Time Series Forecasting by Yanhong Li, David C. Anastasiu

“…By capturing quantile distributions across segmented subsequences at multiple scales, the model is able to detect complex patterns, enhancing both the accuracy and robustness of forecasts. …”
Get full text

On the use of adversarial validation for quantifying dissimilarity in geospatial machine learning prediction by Yanwen Wang, Mahdi Khodadadzadeh, Raúl Zurita-Milla

“…Next to this, we studied how dissimilarity affects CV methods’ evaluations by comparing the results of random CV method (RDM-CV) and of two geospatial CV methods, namely, block and spatial+ CV (BLK-CV and SP-CV). Our results showed the evaluations follow similar patterns in all datasets and predictions: when dissimilarity is low (usually lower than 30%), RDM-CV provides the most accurate evaluation results. …”
Get full text

Investigation of damage characteristics in freeze-thawed grey-white sandstone using AE multifractal analysis by Xinlei Zhang, Xiaoli Liu, Jiaxu Jin, Haibo Wang, Zhiqiang Lv, Yong Xiao

“…A close correlation was observed between the spatial distribution of AE localization points and the macroscopic cracking patterns. …”
Get full text

Spatiotemporal, demographic, and climatic drivers of malaria transmission in the endemic setting of Jazan, Saudi Arabia: A retrospective study by Ahmad Y Alqassim

“…Descriptive statistics characterized cases across demographic factors and spatial and temporal distributions. Correlations and linear regression modeling identified associations between monthly cases and weather parameters mapping visualized geographic patterns. …”
Get full text

War and mobility: Using Yandex web searches to characterize intentions to leave Russia after its invasion of Ukraine by Athina Anastasiadou, Artem Volgin, Douglas R. Leasure

“…CONTRIBUTION: This work combines spatial data on sociodemographic characteristics with search engine data to understand the mobility patterns of Russian nationals from Russia after the invasion of Ukraine. …”
Get full text

Morphological Variation of the Fiddler Crab Tubuca paradussumieri (Decapoda: Ocypodidae) Among Provinces in the Vietnamese Mekong Delta and a Classification Key for Genus Tubuca by Anh Ngoc Tran, Vuong Van Ly, Phuc Le Hoang Nguyen, Thuan Thanh Tran, Vinh Quoc Nguyen, Quang Minh Dinh

“…Clarifying local adaptations, resource partitioning, and biodiversity patterns in vulnerable coastal ecosystems requires understanding these variances. …”
Get full text

A novel explainable deep learning framework for reconstructing South Asian palaeomonsoons by K. M. R. Hunt, K. M. R. Hunt, S. P. Harrison

“…The CNNs, designed to account for spatial relationships in both the predictor and target, demonstrate higher skill in reconstructing rainfall patterns and produce robust spatiotemporal reconstructions. …”
Get full text

Breast cancer classification based on hybrid CNN with LSTM model by Mourad Kaddes, Yasser M. Ayid, Ahmed M. Elshewey, Yasser Fouad

“…CNNs extract mammographic features, including spatial hierarchies and malignancy patterns, whereas LSTM networks characterize sequential dependencies and temporal interactions. …”
Get full text

The Impact of Offshore Wind Farm Construction on Maritime Traffic Complexity: An Empirical Analysis of the Yangtze River Estuary by Jian Liu, Wenbo Yu, Zhongyi Sui, Chunhui Zhou

“…Existing research has explored local traffic patterns and collision risks but lacks comprehensive frameworks for evaluating traffic complexity at both micro and macro levels. …”
Get full text

Machine Learning for Resilient and Sustainable Cities: A Bibliometric Analysis of Smart Urban Technologies by Bin Luan, Xinqun Feng

“…This study aims to conduct a bibliometric analysis of the published research in the fields of smart cities and machine learning, using visualization techniques to reveal the spatiotemporal distribution patterns, research hotspots, and collaborative network structures. …”
Get full text

Dynamic Impact of the Southern Annular Mode on the Antarctic Ozone Hole Area by Jae N. Lee, Dong L. Wu

“…We employ empirical orthogonal function (EOF) analysis to decompose the GPH variability into distinct spatial patterns. EOF analysis reveals a strong relationship between the first EOF (representing the SAM) and the Antarctic ozone hole area (<i>γ</i> = 0.91). …”
Get full text

Assessment of soil erosion and sediment transport index in the Awash River Basin, Ethiopia: an application of the USLE model and GIS techniques by Abayneh Gebremichael, Ephrem Gebremariam, Hayal Desta

“…Furthermore, this study emphasizes how important land use patterns, erodibility of soil, and erosivity of rainfall are associate in exacerbating of erosion. …”
Get full text

A novel multidimensional framework for bridging conservation gaps and optimizing the system of natural reserves for biodiversity: A case study of Dongying, China by Yifei Xu, Chi Li

“…Using this framework, we quantitatively explored the spatial and temporal dynamics of species dispersal and habitat quality for migratory birds in Dongying, China. …”
Get full text

Comparative Analysis of MaxEnt and Deep Learning Approaches for Modeling Humpback Whale Distribution in North Iceland by Nils Barthel, Charla J. Basran, Marianne H. Rasmussen, Benjamin Burkhard

“…The deep learning model is more likely to overfit, but the larger weight network increases the model's capability to capture complex relationships and patterns. Ultimately, the results show that the deep learning model had a higher predictive performance in modeling both current and future humpback whale distributions. …”
Get full text

Spatio-temporal assessment of aerosol-induced atmospheric heating rates in Nigeria by Tertsea Igbawua, Alexander Aondongu Tyonvenda, Terver Sombo, Idugba Mathias Echi

“…This study investigates the spatial and temporal patterns of AHR across Nigeria from 2000 to 2022, using a radiative transfer model. …”
Get full text