USGS Science⌕ Search

Geology topics

Samantha T. Arundel

Publications and source records attributed to Samantha T. Arundel.

At least 19 recordsLinked to original sources
USGS2025

GIScience in the era of Artificial Intelligence: A research agenda towards Autonomous GIS

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five levels of autonomy, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modelling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIScience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, we emphasize that as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future.

Annals of GIS↗
USGS2025

Harnessing geospatial artificial intelligence and deep learning for landslide inventory mapping: Advances, challenges, and emerging directions

Recent advancements in artificial intelligence (AI) and deep learning enable more accurate, scalable, and automated mapping. This paper provides a comprehensive review of the applications of AI, particularly deep learning, in landslide inventory mapping. In addition to examining commonly used data sources and model architectures, we explore innovative strategies such as feature enhancement and fusion, attention-boosted techniques, and advanced learning approaches, including active learning and transfer learning, to enhance model adaptability and predictability. We also highlight the remaining challenges and potential research directions, including the estimation of more diverse variables in landslide mapping, multimodal data alignment, modeling regional variability and replicability, as well as issues related to data misinterpretation and model explainability. This review aims to serve as a useful resource for researchers and practitioners, promoting the integration of deep learning into landslide research and disaster management.

Remote Sensing↗
USGS2024

GeoAI for science and the science of GeoAI

This paper reviews trends in GeoAI research and discusses cutting-edge ad- vances in GeoAI and its roles in accelerating environmental and social sciences. It ad- dresses ongoing attempts to improve the predictability of GeoAI models and recent re- search aimed at increasing model explainability and reproducibility to ensure trustworthy geospatial findings. The paper also provides reflections on the importance of defining the "science" of GeoAI in terms of its fundamental principles, theories, and methods to ensure scientific rigor, social responsibility, and lasting impacts.

Journal of Spatial Information Science↗
USGS2024

Evaluation of classified ground points from National Agriculture Imagery program photogrammetrically derived point clouds

Studies have shown that digital surface models and point clouds generated by the United States Department of Agriculture’s National Agriculture Imagery Program (NAIP) can measure basic forest parameters such as canopy height. However, all measured forest parameters from these studies are evaluated using the differences between NAIP digital surface models (DSMs) and available lidar digital terrain models (DTMs). A survey of NAIP point cloud classification and related ground point-generated DTMs has not yet been undertaken. This study applies a Support Vector Machine (SVM) to classifying ground and nonground points from NAIP point clouds for test sites in Wyoming and Arizona, USA. Light detection and ranging (lidar) data from the U.S. Geological Survey 3D Elevation Program (3DEP) are used to validate the classified NAIP ground points and their corresponding DTMs. Comparing height differences between filtered NAIP ground points and 3DEP ground points, the SVM classifier’s results show that the vertical root mean square error value is 1.87 m and 1.69 m for the Wyoming and Arizona sites, respectively. If NAIP point clouds were continuously measured, the resulting availability of medium-resolution DTMs would benefit the application of multitemporal forest health monitoring and DTM generation.

Remote Sensing Letters↗
USGS2024

Segment anything model can not segment anything: Assessing AI foundation model's generalizability in permafrost mapping

This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta’s Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM’s performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM’s applicability in challenging geospatial domains.

Remote Sensing↗
USGS2024

Assessing the utility of uncrewed aerial system photogrammetrically derived point clouds for land cover classification in the Alaska North Slope

Uncrewed aerial systems (UASs) have been used to collect “pseudo field plot” data in the form of large-scale stereo imagery to supplement and bolster direct field observations to monitor areas in Alaska. These data supplement field data that is difficult to collect in such a vast landscape with a relatively short field season. Dense photogrammetrically derived point clouds are created and are facilitated to extract land cover data using a support vector machine (SVM) classifier in this study. We test our approach using point clouds derived from 1-cm stereo imagery of plots in the Alaska North Slope region and compare the results to field observations. The results show that the overall accuracy of six land cover classes (bare soil, shrub, grass, forb/herb, rock, and litter) is 96.8% from classified patches. Shrub had the highest accuracy (>99%) and forb/herb achieved the lowest (<48%). This study reveals that the approach could be used as reference data to check field observations in remote areas.

Alaska↗
USGS2023

Reimagining standardization and geospatial interoperability in today’s GeoAI culture

Integrating Geospatial Artificial Intelligence (GeoAI) into our technological landscape has revolutionized our capacity to understand and engage with the world. However, the burgeoning adoption of GeoAI applications has underscored the imperative of data, format, and conveyance standardization and enhancing geospatial interoperability. This vision paper delves into the intricacies of the evolving GeoAI environment, emphasizing the indispensable role of standardized practices and elevated interoperability. By synthesizing insights from geography, computer science, and data ethics, this contribution envisions a future characterized by seamless synergy between AI systems and geospatial data, driving impactful decision-making and transformative innovation.

Conference Paper↗
USGS2023

Assessment of a new GeoAI foundation model for floodinundation mapping

Vision foundation models are a new frontier in GeoAI research because of their potential to enable powerful image analysis by analyzing and extracting important image features from vast amounts of geospatial data. This paper evaluates the performance of the first-of-its-kind geospatial foundation model, IBM-NASA’s Prithvi, to support a crucial geospatial analysis task: flood inundation mapping. This model is compared with popular convolutional neural networks and vision transformer-based architectures regarding mapping accuracy for flooded areas. A benchmark dataset, Sen1Floods11, is used in the experiments, and the models' predictability, generalizability, and transferability are evaluated based on both validation datasets and datasets completely unseen by the model. Results show the impressive transferability of the Prithvi model, highlighting its performance advantages in segmenting flooded areas in previously unseen regions. The findings also suggest areas for improvement for the Prithvi model in adopting multi-scale representation learning, developing more end-to-end pipelines for high-level image analysis tasks, and offering more flexibility in allowable input data bands.

Conference Paper↗
USGS2023

A guide to creating an effective big data management framework

Many agencies and organizations, such as the U.S. Geological Survey, handle massive geospatial datasets and their auxiliary data and are thus faced with challenges in storing data and ingesting it, transferring it between internal programs, and egressing it to external entities. As a result, these agencies and organizations may inadvertently devote unnecessary time and money to convey data without existing or outdated standards. This research aims to evaluate the components of data conveyance systems, such as transfer methods, tracking, and automation, to guide their improved performance. Specifically, organizations face the challenges of slow dispatch time and manual intervention when conveying data into, within, and from their systems. Conveyance often requires skilled workers when the system depends on physical media such as hard drives, particularly when terabyte transfers are required. In addition, incomplete or inconsistent metadata may necessitate manual intervention, process changes, or both. A proposed solution is organization-wide guidance for efficient data conveyance. That guidance involves systems analysis to outline a data management framework, which may include understanding the minimum requirements of data manifests, specification of transport mechanisms, and improving automation capabilities.

Journal of Big Data↗
USGS2023

GeoAI for spatial image processing

The development of digital image processing, as a subset of digital signal processing, depended upon the maturity of photography and image science, introduction of computers, discovery and advancement of digital recording devices, and the capture of digital images. In addition, government and industry applications in the Earth and medical sciences were paramount to the growth of the technology. From the early days when photography was first introduced to science to today, artificial intelligence and deep learning technologies have been intensively used to analyze imagery. Spatial image processing has experienced breakthroughs and evolutions. This chapter presents an overview of the history of image processing, GeoAI-based image processing applications, and the role of GeoAI in advancing image processing methods and research. We also discussed the remaining challenges to using GeoAI for image processing regarding training data annotation, the issues of scale, resolution, and change in space over time.

Book chapter↗
USGS2023

Geomorphometric analysis of the Summit and Ridge classes of the Geographic Names Information System

This research aims to conduct a geosemantic comparison of landforms classified in the Summit and Ridge feature classes in the Geographic Names Information System (GNIS). The comparison is based on a 2D shape analysis of manually delineated polygons produced by USGS staff to correspond to 33,304 Summit and 8,006 Ridge features. Five shape measures were chosen for this specific geomorphometry-based analysis. Univariate and bivariate statistics are first calculated to compare the two feature classes. This is followed by unsupervised learning with k-means cluster analysis to identify two major geomorphometric clusters corresponding to Summit and Ridge features. Although this supports sufficient internal homogeneity to have stable Summit and Ridge feature classes, more than 7,500 (18%) special features were also identified, which were assigned by k-means to the cluster not corresponding to their given GNIS class. These features remain to be analyzed further to decide if GNIS features should be reclassified based on geomorphometric analysis of available polygonal representations.

Conference Paper↗
USGS2022

GeoImageNet: A multi-source natural feature benchmark dataset for GeoAI and supervised machine learning

The field of GeoAI or Geospatial Artificial Intelligence has undergone rapid development since 2017. It has been widely applied to address environmental and social science problems, from understanding climate change to tracking the spread of infectious disease. A foundational task in advancing GeoAI research is the creation of open, benchmark datasets to train and evaluate the performance of GeoAI models. While a number of datasets have been published, very few have centered on the natural terrain and its landforms. To bridge this gulf, this paper introduces a first-of-its-kind benchmark dataset, GeoImageNet, which supports natural feature detection in a supervised machine-learning paradigm. A distinctive feature of this dataset is the fusion of multi-source data, including both remote sensing imagery and DEM in depicting spatial objects of interest. This multi-source dataset allows a GeoAI model to extract rich spatio-contextual information to gain stronger confidence in high-precision object detection and recognition. The image dataset is tested with a multi-source GeoAI extension against two well-known object detection models, Faster-RCNN and RetinaNet. The results demonstrate the robustness of the dataset in aiding GeoAI models to achieve convergence and the superiority of multi-source data in yielding much higher prediction accuracy than the commonly used single data source.

GeoInformatica↗
USGS2022

GeoAI and the future of spatial analytics

This chapter discusses the challenges of traditional spatial analytical methods in their limited capacity to handle big and messy data, as well as mining unknown or latent patterns. It then introduces a new form of spatial analytics—geospatial artificial intelligence (GeoAI)—and describes the advantages of this new strategy in big data analytics and data-driven discovery. Finally, a convergent spatial analytical framework is suggested as a potential future pathway for spatial analysis.

Book chapter↗
USGS2022

Deep learning detection and recognition of spot elevations on historic topographic maps

Some information contained in historical topographic maps has yet to be captured digitally, which limits the ability to automatically query such data. For example, U.S. Geological Survey’s historical topographic map collection (HTMC) displays millions of spot elevations at locations that were carefully chosen to best represent the terrain at the time. Although research has attempted to reproduce these data points, it has proven inadequate to automatically detect and recognize spot elevations in the HTMC. We propose a deep learning workflow pretrained using large benchmark text datasets. To these datasets we add manually crafted training image/label pairs, and test how many are required to improve prediction accuracy. We find that the initial model, pretrained solely with benchmark data, fails to predict any HTMC spot elevations correctly, whereas the addition of just 50 custom image/label pairs increases the predictive ability by ~50%, and the inclusion of 350 data pairs increased performance by ~80%. Data augmentation in the form of rotation, scaling and translation (offset) expanded the size and diversity of the training dataset and vastly improved recognition accuracy up to ~95%. Visualization methods, such as heat map generation and salient feature detection are recommended to better understand why some predictions fail.

Frontiers in Environmental Science↗
USGS2021

GeoAI in the US Geological Survey for topographic mapping

Geospatial artificial intelligence (GeoAI) can be defined broadly as the application of artificial intelligence methods and techniques to geospatial data, processes, models, and applications. The application of these methods to topographic data and phenomena is a focus of research in the US Geological Survey (USGS). Specifically, the USGS has researched and developed applications in terrain feature extraction, hydrographic network extraction, and semantic modeling. This article is a documentation of the recent work and current state of research and development. The article helps define the accomplishments and directions of research and applications in fields of GeoAI for topographic mapping within the USGS and more broadly.

Transactions in GIS↗
USGS2021

The evolution of geospatial reasoning, analytics, and modeling

The field of geospatial analytics and modeling has a long history coinciding with the physical and cultural evolution of humans. This history is analyzed relative to the four scientific paradigms: (1) empirical analysis through description, (2) theoretical explorations using models and generalizations, (3) simulating complex phenomena and (4) data exploration. Correlations among developments in general science and those of the geospatial sciences are explored. Trends identify areas ripe for growth and improvement in the fourth and current paradigm that has been spawned by the big data explosion, such as exposing the ‘black box’ of GeoAI training and generating big geospatial training datasets. Future research should focus on integrating both theory- and data-driven knowledge discovery.

Book chapter↗
USGS2021

Spatial data reduction through element -of-interest (EOI) extraction

Any large, multifaceted data collection that is challenging to handle with traditional management practices can be branded ‘Big Data.’ Any big data containing geo-referenced attributes can be considered big geospatial data. The increased proliferation of big geospatial data is currently reforming the geospatial industry into a data-driven enterprise. Challenges in the big spatial data domain can be summarized as the ‘Big Vs’ – variety, volume, velocity, veracity and value. Big spatial data sources can be considered in two broad classes, active and passive, as each is impacted to varying degrees. Some of these challenges may be alleviated by reducing unprocessed, or minimally processed, (raw) data to features, which we refer to as the extraction of Elements of Interest (EOI). In fact, many applications require EOI extraction from raw data to enable their basic employment. This chapter presents current state-of-the-art methods to create EOI from some types of georeferenced big data. We classify the data types into two realms: active and passive. Active data are those collected specifically for the purpose to which they are applied. Passive data are those collected for purposes other than those for which they are utilized, included those ‘collected’ for no particular purpose at all. The chapter then presents use cases from both the active and passive spatial realms, including the active applications of terrain feature extraction from digital elevation models and vegetation mapping from remotely-sensed imagery and passive applications like building identification from VGI and point-of-interest data mining from social networks for land use classification. Finally, the chapter concludes with future research needs.

Book chapter↗