Open Access. Powered by Scholars. Published by Universities.®
- Discipline
-
- Anthropology (194)
- Remote Sensing (28)
- Physical Sciences and Mathematics (19)
- Forest Sciences (13)
- Life Sciences (13)
-
- Geographic Information Sciences (12)
- Architecture (11)
- Human Geography (11)
- Spatial Science (10)
- Arts and Humanities (9)
- Urban, Community and Regional Planning (9)
- Computer Sciences (7)
- History (7)
- Archaeological Anthropology (6)
- Education (6)
- Environmental Sciences (6)
- Higher Education (6)
- Landscape Architecture (6)
- Educational Methods (5)
- Electrical and Computer Engineering (5)
- Engineering (5)
- Oceanography and Atmospheric Sciences and Meteorology (5)
- Physical and Environmental Geography (5)
- Atmospheric Sciences (4)
- Signal Processing (4)
- Urban Studies and Planning (4)
- Earth Sciences (3)
- Environmental Studies (3)
- Institution
- Keyword
-
- Remote sensing (22)
- GIS (14)
- Climate change (8)
- Deep learning (8)
- Geography (8)
-
- Twitter (8)
- Environmental Sciences (7)
- LiDAR (7)
- Limnology (7)
- Water Resources (7)
- Spatial science (6)
- Archaeology (5)
- Classification (5)
- Coastal (5)
- Machine learning (5)
- Remote Sensing (5)
- Tropical cyclones (5)
- Big data (4)
- CNN (4)
- COVID-19 (4)
- Flood (4)
- Gulf of Mexico (4)
- Latin America (4)
- Pelvis (4)
- Peru (4)
- SUAS (4)
- Underwater archaeology (4)
- Variability (4)
- Vegetation index (4)
- Accuracy (3)
- Publication Year
Articles 31 - 60 of 371
Full-Text Articles in Geography
Advances In Tropical Climatology–A Review, Flávia D.S. Moraes, Craig Ramseyer, Paul W. Miller, Jill C. Trepanier
Advances In Tropical Climatology–A Review, Flávia D.S. Moraes, Craig Ramseyer, Paul W. Miller, Jill C. Trepanier
Faculty Publications
Understanding tropical climatology is essential to comprehending the atmospheric connections between the tropics and extratropical latitudes weather and climate events. In this review paper, we emphasize the advances in key areas of tropical climatology knowledge since the end of the 20th century and offer a summary, assessment, and discussion of previously published literature. Among the key areas analyzed here, we explore the advances in tropical oceanic and atmospheric variability, such as El Niño–Southern Oscillation and the Madden-Julian Oscillation, and how those teleconnection events have helped us to better understand variabilities in tropical monsoons, tropical cyclones, and drought events. We also …
Family Roots And Research Journal Unm Emeritus Professor José A. Rivera, José A. Rivera Ph.D
Family Roots And Research Journal Unm Emeritus Professor José A. Rivera, José A. Rivera Ph.D
Faculty Publications
This article is an abbreviated life narrative of UNM Emeritus Professor of Community and Regional Planning, José A. Rivera. It begins with highlights of his family ancestry and continues with an account of his educational experiences K-12 and into a decade of university life as a student while earning a bachelor’s, two master’s and a doctorate. He taught at UNM for 35 years while also conducting research in his areas of interest, mostly in community irrigation studies, mutual aid societies, and rural development. The main body in the article focuses on positions he held at UNM and on publications that …
Cgbi_Yolo: Lightweight Land Target Detection Network, Ruiyang Wang, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Xiaobing Chen, Wenfeng Zheng
Cgbi_Yolo: Lightweight Land Target Detection Network, Ruiyang Wang, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Xiaobing Chen, Wenfeng Zheng
Faculty Publications
Object detection algorithms for optical remote sensing images often face challenges in computational efficiency, particularly when detecting small and densely packed targets. This paper introduces CGBi_YOLO, a novel lightweight land target detection network designed to optimize computational resource utilization while maintaining detection capabilities for small-scale targets. Our approach incorporates an innovative lightweight optimization strategy featuring a new lightweight backbone feature extraction network: CSPGhostNet. This model significantly enhances the detection ability of small objects within optical remote sensing images without increasing computational demands. The efficacy of the proposed model is validated through rigorous experimentation on the DOTA dataset. Compared to the …
Research Overview On Urban Heat Islands Driven By Computational Intelligence, Chao Liu, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Wenfeng Zheng
Research Overview On Urban Heat Islands Driven By Computational Intelligence, Chao Liu, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Wenfeng Zheng
Faculty Publications
In recent years, the intensification of the urban heat island (UHI) effect has become a significant concern as urbanization accelerates. This survey comprehensively explores the current status of surface UHI research, emphasizing the role of land use and land cover changes (LULC) in urban environments. We conducted a systematic review of 8260 journal articles from the Web of Science database, employing bibliometric analysis and keyword co-occurrence analysis using CiteSpace to identify research hotspots and trends. Our investigation reveals that vegetation cover and land use types are the two most critical factors influencing UHI intensity. We analyze various computational intelligence techniques, …
Current Situation And Prospect Of Geospatial Ai In Air Pollution Prediction, Chunlai Wu, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Wenfeng Zheng
Current Situation And Prospect Of Geospatial Ai In Air Pollution Prediction, Chunlai Wu, Siyu Lu, Jiawei Tian, Lirong Yin, Lei Wang, Wenfeng Zheng
Faculty Publications
Faced with increasingly serious environmental problems, scientists have conducted extensive research, among which the importance of air quality prediction is becoming increasingly prominent. This article briefly reviews the utilization of geographic artificial intelligence (AI) in air pollution. Firstly, this paper conducts a literature metrology analysis on the research of geographical AI used in air pollution. That is, 607 documents are retrieved from the Web of Science (WOS) using appropriate keywords, and literature metrology analysis is conducted using Citespace to summarize research hotspots and frontier countries in this field. Among them, China plays a constructive role in the fields of geographic …
Storm-Driven Tree Exposure And Geomorphic Change: Predicting The Distribution Of Preserved Late Pleistocene Tree Stumps On The Outer Alabama Continental Shelf, Kelli L. Moran, Kehui Xu, Jeffrey Obelcz, Kristine L. Delong, Kendall Fontenot, Carl A. Reese, Grant L. Harley, Douglas Jones, Alicia Caporaso
Storm-Driven Tree Exposure And Geomorphic Change: Predicting The Distribution Of Preserved Late Pleistocene Tree Stumps On The Outer Alabama Continental Shelf, Kelli L. Moran, Kehui Xu, Jeffrey Obelcz, Kristine L. Delong, Kendall Fontenot, Carl A. Reese, Grant L. Harley, Douglas Jones, Alicia Caporaso
Faculty Publications
The Alabama Underwater or Drowned Forest is a well-preserved Late Pleistocene (dated to 72–56 ± 8 ka, 2σ) terrestrial landform on the northern Gulf of Mexico continental shelf that provides geomorphic and ecosystem information rarely preserved during the glacial intervals. Stumps of bald cypress (Taxodium distichum (L.) Rich.) trees were exposed in ∼18 m of water following Hurricane Ivan in 2004. This research investigates geomorphic changes to the Mississippi-Alabama-Florida (MAFLA) sand sheet, which presents as shore-oblique Holocene sand ridges, and the exposure and burial of tree stumps following the passage of Hurricane Sally in 2020 using repeat sidescan and bathymetric …
Spatiotemporal Climatology Of Georgia Tropical Cyclones And Associated Rainfall, Reilly Corkran, Jill Trepanier, Vincent Brown
Spatiotemporal Climatology Of Georgia Tropical Cyclones And Associated Rainfall, Reilly Corkran, Jill Trepanier, Vincent Brown
Faculty Publications
Tropical cyclones (TCs), often characterized by high wind speeds and heavy rainfall, cause widespread devastation, affecting millions of people and leading to economic losses worldwide. TC-specific research in Georgia is scarce, likely due to the minimal geographical extent of its coast and the infrequency of direct landfalls. Research on Georgia TCs does not account for storms that make landfall in other southeastern states (e.g., Florida) and continue north, northeast, or northwest into Georgia. This study used the North Atlantic Basin hurricane database (HURDAT2) to quantify the spatiotemporal patterns of direct and indirect landfalling of Georgia tropical cyclones (>16 ms−1) …
Scene Classification Of Remote Sensing Image Based On Multi-Path Reconfigurable Neural Network, Wenyi Hu, Chunjie Lan, Tian Chen, Shan Liu, Lirong Yin, Lei Wang
Scene Classification Of Remote Sensing Image Based On Multi-Path Reconfigurable Neural Network, Wenyi Hu, Chunjie Lan, Tian Chen, Shan Liu, Lirong Yin, Lei Wang
Faculty Publications
Land image recognition and classification and land environment detection are important research fields in remote sensing applications. Because of the diversity and complexity of different tasks of land environment recognition and classification, it is difficult for researchers to use a single model to achieve the best performance in scene classification of multiple remote sensing land images. Therefore, to determine which model is the best for the current recognition classification tasks, it is often necessary to select and experiment with many different models. However, finding the optimal model is accompanied by an increase in trial-and-error costs and is a waste of …
Conducting Structure-From-Motion (Sfm) Modeling Of Freshwater Environments Using Unpiloted Aerial Systems (Uas): Challenges And Lessons Learned, Benjamin T. Fraser, Christine L. Bunyon, Russell G. Congalton
Conducting Structure-From-Motion (Sfm) Modeling Of Freshwater Environments Using Unpiloted Aerial Systems (Uas): Challenges And Lessons Learned, Benjamin T. Fraser, Christine L. Bunyon, Russell G. Congalton
Faculty Publications
The pairing of Unpiloted Aerial Systems (UAS) and Structure from Motion (SfM) has provided new capabilities for modeling freshwater environments. Applications of UAS-SfM range from water quality monitoring to the mapping of aquatic vegetation. The models produced provide users with the ability to analyze features at ultra-high-resolutions and across scales not easily achieved through in situ sampling. Despite the demonstrated benefits of UAS-SfM in freshwater and other natural resource disciplines, there remain fundamental technical challenges in the modeling of environments with homogenous surfaces (e.g., water). In this research, the effectiveness of several image collection and processing approaches for the modelling …
Shifting Baselines: Visualizing Climate Change In America’S National Parks, Lee Lines
Shifting Baselines: Visualizing Climate Change In America’S National Parks, Lee Lines
Faculty Publications
No abstract provided.
Snapshots Of Coastal Ecology Using Multiproxy Analysis Reveals Insights Into The Preservation Of Swamp And Marsh Environments Since The Late Pleistocene, Kendall Fontenot, Kristine L. Delong, Brian A. Schubert, Sophie Warny, Davin J. Wallace, Carrie M. Miller, Erin Culver-Miller, Michael J. Polito, Carl A. Reese, Kathryn Garretson, Kehui Xu, Grant L. Harley, Jeffrey Obelcz, Kelli L. Moran, Julian Traphagan, Douglas Jones, Alicia Caporaso
Snapshots Of Coastal Ecology Using Multiproxy Analysis Reveals Insights Into The Preservation Of Swamp And Marsh Environments Since The Late Pleistocene, Kendall Fontenot, Kristine L. Delong, Brian A. Schubert, Sophie Warny, Davin J. Wallace, Carrie M. Miller, Erin Culver-Miller, Michael J. Polito, Carl A. Reese, Kathryn Garretson, Kehui Xu, Grant L. Harley, Jeffrey Obelcz, Kelli L. Moran, Julian Traphagan, Douglas Jones, Alicia Caporaso
Faculty Publications
The southeastern United States Coastal Plain ecosystem contains baldcypress (Taxodium distichum) swamps and grass-dominated marshes. These ecosystems also occurred on the exposed continental shelf during lower sea levels but are rarely preserved due to the mechanically erosive nature of transgression and regression. Two presently marine sites on the northeastern Gulf of Mexico's continental shelf contain well-preserved woody terrestrial sediments that were the subject of previous studies. This study continues the investigation using geochemical (δ13C, δ15N, δ34S) and palynological characteristics of these formerly terrestrial sediments to determine if swamps and/or marshes existed at the time of deposition. The first site is …
Spatiotemporal Analysis Of Nighttime Crimes In Vienna, Austria, Jiyoung Lee, Michael Leitner, Gernot Paulus
Spatiotemporal Analysis Of Nighttime Crimes In Vienna, Austria, Jiyoung Lee, Michael Leitner, Gernot Paulus
Faculty Publications
Studying the spatiotemporal dynamics of crime is crucial for accurate crime geography research. While studies have examined crime patterns related to weekdays, seasons, and specific events, there is a noticeable gap in research on nighttime crimes. This study focuses on crimes occurring during the nighttime, investigating the temporal definition of nighttime crime and the correlation between nighttime lights and criminal activities. The study concentrates on four types of nighttime crimes, assault, theft, burglary, and robbery, conducting univariate and multivariate analyses. In the univariate analysis, correlations between nighttime crimes and nighttime light (NTL) values detected in satellite images and between streetlight …
Elevating The Rre Framework For Geospatial Analysis With Visual Programming Platforms: An Exploration With Geospatial Analytics Extension For Knime, Lingbo Liu, Fahui Wang, Xiaokang Fu, Tobias Kötter, Kevin Sturm, Weihe Wendy Guan, Shuming Bao
Elevating The Rre Framework For Geospatial Analysis With Visual Programming Platforms: An Exploration With Geospatial Analytics Extension For Knime, Lingbo Liu, Fahui Wang, Xiaokang Fu, Tobias Kötter, Kevin Sturm, Weihe Wendy Guan, Shuming Bao
Faculty Publications
Reproducibility, replicability, and expandability (RRE) have emerged as fundamental concerns in the realm of scientific research and development. Wherein, devising effective solutions for RRE within geospatial analysis stands out as a particularly critical challenge that demands immediate attention. Although there has been an evolution from basic reproducibility of code and data to a more comprehensive cyberinfrastructure, this integrated solution is still grappling with issues of limited user accessibility, steep learning curves particularly in coding skills, and difficulties in achieving collaboration with other data science platforms This study proposes a framework that combines open-source GIS with visual programming platforms, grounded in …
Stacked Noise Reduction Auto Encoder–Ocean: A Novel Personalized Recommendation Model Enhanced, Bixi Wang, Wenfeng Zheng, Ruiyang Wang, Siyu Lu, Lirong Yin, Lei Wang, Zhengtong Yin, Xinbing Chen
Stacked Noise Reduction Auto Encoder–Ocean: A Novel Personalized Recommendation Model Enhanced, Bixi Wang, Wenfeng Zheng, Ruiyang Wang, Siyu Lu, Lirong Yin, Lei Wang, Zhengtong Yin, Xinbing Chen
Faculty Publications
With the continuous development of information technology and the rapid increase in new users of social networking sites, recommendation technology is becoming more and more important. After research, it was found that the behavior of users on social networking sites has a great correlation with their personalities. The five characteristics of the OCEAN personality model can cover all aspects of a user’s personality. In this research, a micro-directional propagation model based on the OCEAN personality model and a Stacked Denoising Auto Encoder (SDAE) was built through the application of deep learning to a collaborative filtering technique. Firstly, the dimension of …
Aerial, Surface, And Subsurface Multimodal Mapping In Coastal Peru: Insights From Cerro San Isidro, Moro Region, Nepeña Valley, Kayla Golay Lausanne, David Chicoine, Jeisen Navarro Vega, George F. Lau
Aerial, Surface, And Subsurface Multimodal Mapping In Coastal Peru: Insights From Cerro San Isidro, Moro Region, Nepeña Valley, Kayla Golay Lausanne, David Chicoine, Jeisen Navarro Vega, George F. Lau
Faculty Publications
This article describes a series of steps to integrate multiple modes of archaeological mapping in arid and agricultural settings. We use the coastal region of Peru as a case study and share our recent field experience at Cerro San Isidro, a multicomponent hill site located in the agriculture-intensive and mid-elevation (about 500 m asl) Moro region of the Nepeña Valley. In June and July 2022, we spent eight weeks deploying a combination of drone aerial imagery, pedestrian GPS reconnaissance, and GPR survey to map the surface and subsurface features at the site and in the adjacent agricultural fields. Our efforts …
Deterministic Global 3d Fractal Cloud Model For Synthetic Scene Generation, Aaron M. Schinder, Shannon R. Young, Bryan J. Steward, Michael L. Dexter, Andrew Kondrath, Stephen Hinton, Ricardo Davila
Deterministic Global 3d Fractal Cloud Model For Synthetic Scene Generation, Aaron M. Schinder, Shannon R. Young, Bryan J. Steward, Michael L. Dexter, Andrew Kondrath, Stephen Hinton, Ricardo Davila
Faculty Publications
This paper describes the creation of a fast, deterministic, 3D fractal cloud renderer for the AFIT Sensor and Scene Emulation Tool (ASSET). The renderer generates 3D clouds by ray marching through a volume and sampling the level-set of a fractal function. The fractal function is distorted by a displacement map, which is generated using horizontal wind data from a Global Forecast System (GFS) weather file. The vertical windspeed and relative humidity are used to mask the creation of clouds to match realistic large-scale weather patterns over the Earth. Small-scale detail is provided by the fractal functions which are tuned to …
A Sensor-Based Simulation Method For Spatiotemporal Event Detection, Yuqin Jiang, Andrey A. Popov, Zhenlong Li, Michael E. Hodgson, Binghu Huang
A Sensor-Based Simulation Method For Spatiotemporal Event Detection, Yuqin Jiang, Andrey A. Popov, Zhenlong Li, Michael E. Hodgson, Binghu Huang
Faculty Publications
Human movements in urban areas are essential to understand human–environment interactions. However, activities and associated movements are full of uncertainties due to the complexity of a city. In this paper, we propose a novel sensor-based approach for spatiotemporal event detection based on the Discrete Empirical Interpolation Method. Specifically, we first identify the key locations, defined as “sensors”, which have the strongest correlation with the whole dataset. We then simulate a regular uneventful scenario with the observation data points from those key locations. By comparing the simulated and observation scenarios, events are extracted both spatially and temporally. We apply this method …
17O-Excess In Tropical Cyclones Reflects Local Rain Re-Evaporation More Than Moisture Source Conditions, Chijun Sun, Timothy Shanahan, Shaoneng He, Adriana Bailey, Jesse Nusbaumer, Jun Hu, Aubrey Hillman, Erika Ornouski, Jacob Warner, Kristine Delong
17O-Excess In Tropical Cyclones Reflects Local Rain Re-Evaporation More Than Moisture Source Conditions, Chijun Sun, Timothy Shanahan, Shaoneng He, Adriana Bailey, Jesse Nusbaumer, Jun Hu, Aubrey Hillman, Erika Ornouski, Jacob Warner, Kristine Delong
Faculty Publications
17O-excess is a relatively new water isotope parameter that could potentially provide useful information about the hydrological cycle. Previous works focusing on 17O-excess in polar regions suggest that it primarily tracks moisture source relative humidity, but little is known about how to interpret 17O-excess data in lower latitudes. Here we present quasi-hourly triple oxygen isotope data of precipitation collected from two tropical cyclones in Texas and Louisiana in 2020 to understand the impacts of environmental and meteorological processes on the 17O-excess of low-to mid-latitude precipitation. We find that at both hourly timescales and the event scale, 17O-excess is strongly correlated …
Pal-Bert: An Improved Question Answering Model, Wenfeng Zheng, Siyu Lu, Zhuohang Cai, Ruiyang Wang, Lei Wang, Lirong Yin
Pal-Bert: An Improved Question Answering Model, Wenfeng Zheng, Siyu Lu, Zhuohang Cai, Ruiyang Wang, Lei Wang, Lirong Yin
Faculty Publications
In the field of natural language processing (NLP), there have been various pre-training language models in recent years, with question answering systems gaining significant attention. However, as algorithms, data, and computing power advance, the issue of increasingly larger models and a growing number of parameters has surfaced. Consequently, model training has become more costly and less efficient. To enhance the efficiency and accuracy of the training process while reducing the model volume, this paper proposes a first-order pruning model PAL-BERT based on the ALBERT model according to the characteristics of question-answering (QA) system and language model. Firstly, a first-order network …
Gendered Perceptions And Socio-Economic And Spatial Determinants Of Fear Of Crime: An Empirical Analysis In Szczecin, Poland, Natalia Sypion, Arkadiusz Kołodziej, Michael Leitner, Marek Dutkowski
Gendered Perceptions And Socio-Economic And Spatial Determinants Of Fear Of Crime: An Empirical Analysis In Szczecin, Poland, Natalia Sypion, Arkadiusz Kołodziej, Michael Leitner, Marek Dutkowski
Faculty Publications
The study of the fear of crime phenomenon provides a socially and politically important research question. Many studies show that gender differentiates the fear of crime, which is why we examine this phenomenon in a spatial perspective. The female versus male perspective of feelings of safety in residential areas were significantly different. The research was carried out using the CAWI technique in the city of Szczecin, in Poland (n=346). The research also examined which factors influenced the fear of crime the most: darkness, socio-economic characteristics, type of violations, number of registered crimes, or the assessment of police work. The research …
Geospatial Analytics Extension For Knime, Lingbo Liu, Xiaokang Fu, Tobias Kötter, Kevin Sturm, Carsten Haubold, Weihe Wendy Guan, Shuming Bao, Fahui Wang
Geospatial Analytics Extension For Knime, Lingbo Liu, Xiaokang Fu, Tobias Kötter, Kevin Sturm, Carsten Haubold, Weihe Wendy Guan, Shuming Bao, Fahui Wang
Faculty Publications
The Geospatial Analytics Extension for KNIME (GAEK) is an innovative tool designed to integrate visual programming with geospatial analytics, streamlining GIS education and research in social sciences. GAEK simplifies access for users with an intuitive, visual interface for complex spatial analysis tasks and contributes to the organization of the GIS Knowledge Tree through its geospatial analytics nodes. This paper discusses GAEK's architecture, functionalities, and its transformative impact on GIS applications. While GAEK significantly enhances user experience and research reproducibility, future updates aim to expand its functionality and optimize its bundled environment.
An Examination Of Homo Naledi Early Juveniles Recovered From The Rising Star Cave System, South Africa, Juliet K. Brophy, Debra R. Bolter, Marina Elliott, John Hawks, Lee R. Berger
An Examination Of Homo Naledi Early Juveniles Recovered From The Rising Star Cave System, South Africa, Juliet K. Brophy, Debra R. Bolter, Marina Elliott, John Hawks, Lee R. Berger
Faculty Publications
Background: Six Homo naledi early juveniles were recovered from U.W. 101 (Dinaledi Chamber), U.W. 102 (Lesedi Chamber), and U.W. 110 in the Rising Star cave system. Aim: This paper develops the information for the H. naledi early juvenile life stage, as defined by a combination of deciduous and permanent dentition, and the eruption of the first permanent molar. Subjects and methods: The growing number of young individuals recovered from the Rising Star cave system allows us to gain a better understanding of their variation, or lack thereof, and provides a basis to estimate broad ranges for age at death of …
Human–Environment Interactions At Ta’Ab Nuk Na, A Submerged Maya Salt Works Site In Belize, Cheryl M. Foster, Heather Mckillop, E. Cory Sills
Human–Environment Interactions At Ta’Ab Nuk Na, A Submerged Maya Salt Works Site In Belize, Cheryl M. Foster, Heather Mckillop, E. Cory Sills
Faculty Publications
Sea-level rise and settlement are investigated at Ta’ab Nuk Na, an ancient Maya salt works in Belize, by examining samples from wooden posts and marine sediment. The samples included Post 145 of Building B and the Nunavut beam, along with marine sediment columns cut from beside both wooden posts. The sediment columns were sampled at 2 cm intervals. Loss-on ignition confirmed the presence of organic material. Identifying the organic content involved removing nonorganic material from the sediment and sorting the organic material under magnification. This procedure established that most of the organic material was red mangrove (Rhizophora mangle). Red mangroves …
Flooded Mangrove Landscapes Hide Ancient Maya Coastal Sites In Belize, Heather I. Mckillop
Flooded Mangrove Landscapes Hide Ancient Maya Coastal Sites In Belize, Heather I. Mckillop
Faculty Publications
Evidence of ancient Maya exploitation of salt, other marine resources, settlement, and sea trade is hidden in flooded mangrove landscapes on the cays, mainland, and in shallow offshore locations on the south coast of Belize. This article includes a discussion of the coastal economy from the Middle Preclassic through the Postclassic periods (600 B.C.–A.D. 1500). Data from sites discovered and excavated since 1982 in the coastal area of the Port Honduras and Paynes Creek National Park support a model of coastal reliance on marine resources and tree crops. The need for a regular supply of coastal salt to inland cities …
Dpal-Bert: A Faster And Lighter Question Answering Model, Lirong Yin, Lei Wang, Zhuohang Cai, Siyu Lu, Ruiyang Wang, Ahmed Alsanad, Salman A. Alqahtani, Xiaobing Chen, Zhengtong Yin, Xiaolu Li, Wenfeng Zheng
Dpal-Bert: A Faster And Lighter Question Answering Model, Lirong Yin, Lei Wang, Zhuohang Cai, Siyu Lu, Ruiyang Wang, Ahmed Alsanad, Salman A. Alqahtani, Xiaobing Chen, Zhengtong Yin, Xiaolu Li, Wenfeng Zheng
Faculty Publications
Recent advancements in natural language processing have given rise to numerous pre-training language models in question-answering systems. However, with the constant evolution of algorithms, data, and computing power, the increasing size and complexity of these models have led to increased training costs and reduced efficiency. This study aims to minimize the inference time of such models while maintaining computational performance. It also proposes a novel Distillation model for PAL-BERT (DPAL-BERT), specifically, employs knowledge distillation, using the PAL-BERT model as the teacher model to train two student models: DPAL-BERT-Bi and DPAL-BERT-C. This research enhances the dataset through techniques such as masking, …
Convolution-Transformer For Image Feature Extraction, Lirong Yin, Lei Wang, Siyu Lu, Ruiyang Wang, Youshuai Yang, Bo Yang, Shan Liu, Ahmed Alsanad, Salman A. Alqahtani, Zhengtong Yin, Xiaolu Li, Xiaobing Chen, Wenfeng Zheng
Convolution-Transformer For Image Feature Extraction, Lirong Yin, Lei Wang, Siyu Lu, Ruiyang Wang, Youshuai Yang, Bo Yang, Shan Liu, Ahmed Alsanad, Salman A. Alqahtani, Zhengtong Yin, Xiaolu Li, Xiaobing Chen, Wenfeng Zheng
Faculty Publications
This study addresses the limitations of Transformer models in image feature extraction, particularly their lack of inductive bias for visual structures. Compared to Convolutional Neural Networks (CNNs), the Transformers are more sensitive to different hyperparameters of optimizers, which leads to a lack of stability and slow convergence. To tackle these challenges, we propose the Convolution-based Efficient Transformer Image Feature Extraction Network (CEFormer) as an enhancement of the Transformer architecture. Our model incorporates E-Attention, depthwise separable convolution, and dilated convolution to introduce crucial inductive biases, such as translation invariance, locality, and scale invariance, into the Transformer framework. Additionally, we implement a …
Afbnet: A Lightweight Adaptive Feature Fusion Module For Super-Resolution Algorithms, Lirong Yin, Lei Wang, Siyu Lu, Ruiyang Wang, Haitao Ren, Ahmed Alsanad, Salman A. Alqahtani, Zhengtong Yin, Xiaolu Li, Wenfeng Zheng
Afbnet: A Lightweight Adaptive Feature Fusion Module For Super-Resolution Algorithms, Lirong Yin, Lei Wang, Siyu Lu, Ruiyang Wang, Haitao Ren, Ahmed Alsanad, Salman A. Alqahtani, Zhengtong Yin, Xiaolu Li, Wenfeng Zheng
Faculty Publications
At present, super-resolution algorithms are employed to tackle the challenge of low image resolution, but it is difficult to extract differentiated feature details based on various inputs, resulting in poor generalization ability. Given this situation, this study first analyzes the features of some feature extraction modules of the current super-resolution algorithm and then proposes an adaptive feature fusion block (AFB) for feature extraction. This module mainly comprises dynamic convolution, attention mechanism, and pixel-based gating mechanism. Combined with dynamic convolution with scale information, the network can extract more differentiated feature information. The introduction of a channel spatial attention mechanism combined with …
African Bovid Tribe Classification Using Transfer Learning And Computer Vision, Manuel Domínguez-Rodrigo, Juliet Brophy, Gregory J. Mathews, Marcos Pizarro-Monzo, Enrique Baquedano
African Bovid Tribe Classification Using Transfer Learning And Computer Vision, Manuel Domínguez-Rodrigo, Juliet Brophy, Gregory J. Mathews, Marcos Pizarro-Monzo, Enrique Baquedano
Faculty Publications
Objective analytical identification methods are still a minority in the praxis of paleobiological sciences. Subjective interpretation of fossils and their modifications remains a nonreplicable expert endeavor. Identification of African bovids is a crucial element in the reconstruction of paleo-landscapes, ungulate paleoecology, and, eventually, hominin adaptation and ecosystemic reconstruction. Recent analytical efforts drawing on Fourier functional analysis and discrimination methods applied to occlusal surfaces of teeth have provided a highly accurate framework to correctly classify African bovid tribes and taxa. Artificial intelligence tools, like computer vision, have also shown their potential to be objectively more accurate in the identification of taphonomic …
Multiscale Analysis Of Spatial Accessibility To Acute Hospitals In Carinthia, Austria, Changzhen Wang, Michael Leitner, Gernot Paulus
Multiscale Analysis Of Spatial Accessibility To Acute Hospitals In Carinthia, Austria, Changzhen Wang, Michael Leitner, Gernot Paulus
Faculty Publications
Health care accessibility studies are well established in the US but lacking in Austria, even though both experience high costs and have hospital care as the largest contributor to health care spending. This study aims to examine multiscale spatial accessibility to acute hospitals in Carinthia, Austria. Using the most recent data at census block and 250 meter grid levels, we refine proximity and generalized two-step floating catchment area (G2SFCA) methods while accounting for the modifiable areal unit problem (MAUP) and edge effects. For census blocks and 250 meter grids, the mean travel times to the nearest acute hospitals are 16 …
Historical Archives Reveal Record Rainfall And Severe Flooding In December 1867 Resulting From An Atmospheric River And Snowmelt, Western Washington, Usa, Daniel G. Gavin, Patrick J. Bartlein, Cary J. Mock
Historical Archives Reveal Record Rainfall And Severe Flooding In December 1867 Resulting From An Atmospheric River And Snowmelt, Western Washington, Usa, Daniel G. Gavin, Patrick J. Bartlein, Cary J. Mock
Faculty Publications
The flooding of 1861-1862 in California and Oregon is the most severe flood event documented in the far western USA and stands as a benchmark for a worst-case atmospheric-river flooding event. In western Washington, historical data are sparser, and 19th-century flood events have consequently not been well documented. We found that rainfall observations from five locations spanning western Washington had no detectable bias when compared to nearby 20th and 21st-century comparator stations. Time series of the four-day precipitation sum revealed an event in December 1867 that was greater than any of the last century at three locations, and in the …