Search

Climate change pressure on the Arctic permafrost is rising alarmingly, creating a decisive need to produce Pan-Arctic scale permafrost landform and thaw disturbance information from remote sensing (RS) data. Very high spatial resolution (VHSR) satellite images can be utilized to detect ice-wedge polygons (IWPs)– the most important and widespread landform in the Arctic tundra region - across the Arctic without compromising spatial details. Automated analysis of peta-byte scale VHSR imagery covering millions of square kilometers is a computationally challenging task. Traditional semantic segmentation requires the use of task specific feature extraction with conventional classification techniques. Semantic complexity of VHSR images coupled with landscape heterogeneity makes it difficult to use conventional classification approaches to produce Pan-Arctic scale geospatial products. This leads to adapting deep convolutional neural network (DLCNN) approaches that have excelled in computer vision (CV) applications. Transitioning domains from everyday image understanding to remote sensing image analysis is challenging. This study aims to systematically investigate two main obstacles confronted when adapting DLCNNs in large-scale RS image analysis tasks; 1) the limited availability labeled data sets and 2) the prohibitive nature of hyperparameter tunning when designing DLCNNs that can capture the rich characteristics embedded in remotely-sensed images. With a case study on the production of the first pan-Arctic ice-wedge polygon map using thousands of VHSR images, we demonstrate the use of transfer learning and the impact of hyperparameter tuning with a 16% improvement of the Mean Average Precision (mAP50).

Trees in proximity to power lines can cause significant damage to utility infrastructure during storms, leading to substantial economic and societal costs. This study investigated the effectiveness of non-parametric machine learning algorithms in modeling tree-related outage risks to distribution power lines at a finer spatial scale. We used a vegetation risk model (VRM) comprising 15 predictor variables derived from roadside tree data, landscape information, vegetation management records, and utility infrastructure data. We evaluated the VRM’s performance using decision tree (DT), random forest (RF), k-Nearest Neighbor (k-NN), extreme gradient boosting (XGBoost), and support vector machine (SVM) techniques. The RF algorithm demonstrated the highest performance with an accuracy of 0.753, an AUC-ROC of 0.746, precision of 0.671, and an F1-score of 0.693. The SVM achieved the highest recall value of 0.727. Based on the overall performance, the RF emerged as the best machine learning algorithm, whereas the DT was the least suitable. The DT reported the lowest run times for both hyperparameter optimization (3.93 s) and model evaluation (0.41 s). XGBoost and the SVM exhibited the highest run times for hyperparameter tuning (9438.54 s) and model evaluation (112 s), respectively. The findings of this study are valuable for enhancing the resilience and reliability of the electric grid.

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.

Plot-level photography is an attractive time-saving alternative to field measurements for vegetation monitoring. However, widespread adoption of this technique relies on efficient workflows for post-processing images and the accuracy of the resulting products. Here, we estimated relative vegetation cover using both traditional field sampling methods (point frame) and semi-automated classification of photographs (plot-level photography) across thirty 1 m2 plots near Utqiaġvik, Alaska, from 2012 to 2021. Geographic object-based image analysis (GEOBIA) was applied to generate objects based on the three spectral bands (red, green, and blue) of the images. Five machine learning algorithms were then applied to classify the objects into vegetation groups, and random forest performed best (60.5% overall accuracy). Objects were reliably classified into the following classes: bryophytes, forbs, graminoids, litter, shadows, and standing dead. Deciduous shrubs and lichens were not reliably classified. Multinomial regression models were used to gauge if the cover estimates from plot-level photography could accurately predict the cover estimates from the point frame across space or time. Plot-level photography yielded useful estimates of vegetation cover for graminoids. However, the predictive performance varied both by vegetation class and whether it was being used to predict cover in new locations or change over time in previously sampled plots. These results suggest that plot-level photography may maximize the efficient use of time, funding, and available technology to monitor vegetation cover in the Arctic, but the accuracy of current semi-automated image analysis is not sufficient to detect small changes in cover.

We evaluated the performance of a variety of time series models, that include the harmonic (HR) model, autoregressive (AR) model, linear Gaussian state-space (LGSS) model, cubic spline (SP) model, double logistic (DL) model, and asymmetric Gaussian (AG) model, for reconstructing (all six models) and forecasting (HR, AR, and LGSS models) dense Landsats 5–7 time series based on 4562 samples. To remove the impact of land change and human interventions on data reconstruction and forecasting, this evaluation excluded croplands and samples changed between 2000 and 2011. Results show that the widely used HR model is not a good model for data reconstruction but outperforms other models in data forecasting. The DL and AG models have the best performance in data reconstruction but cannot forecast Landsat observations. The AR and LGSS models shared similar performance in reconstructing Landsat data but are less ideal for data forecasting, particularly for the LGSS model. Integrating the HR (for forecasting) and DL or AG (for reconstruction) is recommended to improve land change detection and land cover classification results. We also evaluated the impact of data density and irregularity on reconstructing and forecasting Landsat observations. When the data density is low (

Retrogressive thaw slumps (RTS) are considered one of the most dynamic permafrost disturbance features in the Arctic. Sub-meter resolution multispectral imagery acquired by very high spatial resolution (VHSR) commercial satellite sensors offer unique capacities in capturing the morphological dynamics of RTSs. The central goal of this study is to develop a deep learning convolutional neural net (CNN) model (a UNet-based workflow) to automatically detect and characterize RTSs from VHSR imagery. We aimed to understand: (1) the optimal combination of input image tile size (array size) and the CNN network input size (resizing factor/spatial resolution) and (2) the interoperability of the trained UNet models across heterogeneous study sites based on a limited set of training samples. Hand annotation of RTS samples, CNN model training and testing, and interoperability analyses were based on two study areas from high-Arctic Canada: (1) Banks Island and (2) Axel Heiberg Island and Ellesmere Island. Our experimental results revealed the potential impact of image tile size and the resizing factor on the detection accuracies of the UNet model. The results from the model transferability analysis elucidate the effects on the UNet model due the variability (e.g., shape, color, and texture) associated with the RTS training samples. Overall, study findings highlight several key factors that we should consider when operationalizing CNN-based RTS mapping over large geographical extents.

Rapid global warming is catalyzing widespread permafrost degradation in the Arctic, leading to destructive land-surface subsidence that destabilizes and deforms the ground. Consequently, human-built infrastructure constructed upon permafrost is currently at major risk of structural failure. Risk assessment frameworks that attempt to study this issue assume that precise information on the location and extent of infrastructure is known. However, complete, high-quality, uniform geospatial datasets of built infrastructure that are readily available for such scientific studies are lacking. While imagery-enabled mapping can fill this knowledge gap, the small size of individual structures and vast geographical extent of the Arctic necessitate large volumes of very high spatial resolution remote sensing imagery. Transforming this ‘big’ imagery data into ‘science-ready’ information demands highly automated image analysis pipelines driven by advanced computer vision algorithms. Despite this, previous fine resolution studies have been limited to manual digitization of features on locally confined scales. Therefore, this exploratory study serves as the first investigation into fully automated analysis of sub-meter spatial resolution satellite imagery for automated detection of Arctic built infrastructure. We tasked the U-Net, a deep learning-based semantic segmentation model, with classifying different infrastructure types (residential, commercial, public, and industrial buildings, as well as roads) from commercial satellite imagery of Utqiagvik and Prudhoe Bay, Alaska. We also conducted a systematic experiment to understand how image augmentation can impact model performance when labeled training data is limited. When optimal augmentation methods were applied, the U-Net achieved an average F1 score of 0.83. Overall, our experimental findings show that the U-Net-based workflow is a promising method for automated Arctic built infrastructure detection that, combined with existing optimized workflows, such as MAPLE, could be expanded to map a multitude of infrastructure types spanning the pan-Arctic.

Increasing availability and advancements of aerial Light Detection and Ranging (LiDAR) data have radically been shifting the way archeological surveys are performed. Unlike optical remote sensing imagery, LiDAR pulses travel through small gaps in dense tree canopies enabling archeologists to discover “hidden” past settlements and anthropogenic landscape features. While LiDAR has been increasingly adopted in archeological studies worldwide, its full potential is still being explored in the United States. Furthermore, while hand-digitizing features in remote-sensing datasets remain a valuable method for archeological surveys, it is often time- and labor intensive. The central objective of this research is to develop a geographic object-based image analysis-driven methodological framework linking low-level features and domain knowledge to automatically extract targets of interest from LiDAR-based digital terrain models (DTMs) and to closely examine the degree of interoperability of knowledge-based rulesets across different study sites focusing on the same semantic class. We apply this framework in southern New England, a geographic region in the northeastern United States where numerous seventeenth-century to early twentieth-century features such as relict charcoal hearths (RCHs), stone walls, and building foundations lie abandoned in densely forested terrain. Focusing on RCHs in this study, our results show promising agreement between manual and automated detection of these features. Overall, we show that the use of LiDAR data augmented with object-based classification workflows provides valuable baseline data for future archeological study and reconstruction of land-use/land-cover change over the past 300 years.

Advanced deep learning methods combined with regional, open access, airborne Light Detection and Ranging (LiDAR) data have great potential to study the spatial extent of historic land use features preserved under the forest canopy throughout New England, a region in the northeastern United States. Mapping anthropogenic features plays a key role in understanding historic land use dynamics during the 17th to early 20th centuries, however previous studies have primarily used manual or semi-automated digitization methods, which are time consuming for broad-scale mapping. This study applies fully-automated deep convolutional neural networks (i.e., U-Net) with LiDAR derivatives to identify relict charcoal hearths (RCHs), a type of historical land use feature. Results show that slope, hillshade, and Visualization for Archaeological Topography (VAT) rasters work well in six localized test regions (spatial scale: 2, best F1 score: 95.5%), but also at broader extents at the town level (spatial scale: 493 km2, best F1 score: 86%). The model performed best in areas with deciduous forest and high slope terrain (e.g., >15 degrees) (F1 score: 86.8%) compared to coniferous forest and low slope terrain (e.g.,

Beavers have established themselves as a key component of low arctic ecosystems over the past several decades. Beavers are widely recognized as ecosystem engineers, but their effects on permafrost-dominated landscapes in the Arctic remain unclear. In this study, we document the occurrence, reconstruct the timing, and highlight the effects of beaver activity on a small creek valley confined by ice-rich permafrost on the Seward Peninsula, Alaska using multi-dimensional remote sensing analysis of satellite (Landsat-8, Sentinel-2, Planet CubeSat, and DigitalGlobe Inc./MAXAR) and unmanned aircraft systems (UAS) imagery. Beaver activity along the study reach of Swan Lake Creek appeared between 2006 and 2011 with the construction of three dams. Between 2011 and 2017, beaver dam numbers increased, with the peak occurring in 2017 (n = 9). Between 2017 and 2019, the number of dams decreased (n = 6), while the average length of the dams increased from 20 to 33 m. Between 4 and 20 August 2019, following a nine-day period of record rainfall (>125 mm), the well-established dam system failed, triggering the formation of a beaver-induced permafrost degradation feature. During the decade of beaver occupation between 2011 and 2021, the creek valley widened from 33 to 180 m (~450% increase) and the length of the stream channel network increased from ~0.6 km to more than 1.9 km (220% increase) as a result of beaver engineering and beaver-induced permafrost degradation. Comparing vegetation (NDVI) and snow (NDSI) derived indices from Sentinel-2 time-series data acquired between 2017 and 2021 for the beaver-induced permafrost degradation feature and a nearby unaffected control site, showed that peak growing season NDVI was lowered by 23% and that it extended the length of the snow-cover period by 19 days following the permafrost disturbance. Our analysis of multi-dimensional remote sensing data highlights several unique aspects of beaver engineering impacts on ice-rich permafrost landscapes. Our detailed reconstruction of the beaver-induced permafrost degradation event may also prove useful for identifying degradation of ice-rich permafrost in optical time-series datasets across regional scales. Future field- and remote sensing-based observations of this site, and others like it, will provide valuable information for the NSF-funded Arctic Beaver Observation Network (A-BON) and the third phase of the NASA Arctic-Boreal Vulnerability Experiment (ABoVE) Field Campaign.

Very high spatial resolution commercial satellite imagery can inform observation, mapping, and documentation of micro-topographic transitions across large tundra regions. The bridging of fine-scale field studies with pan-Arctic system assessments has until now been constrained by a lack of overlap in spatial resolution and geographical coverage. This likely introduced biases in climate impacts on, and feedback from the Arctic region to the global climate system. The central objective of this exploratory study is to develop an object-based image analysis workflow to automatically extract ice-wedge polygon troughs from very high spatial resolution commercial satellite imagery. We employed a systematic experiment to understand the degree of interoperability of knowledge-based workflows across distinct tundra vegetation units—sedge tundra and tussock tundra—focusing on the same semantic class. In our multi-scale trough modelling workflow, we coupled mathematical morphological filtering with a segmentation process to enhance the quality of image object candidates and classification accuracies. Employment of the master ruleset on sedge tundra reported classification accuracies of correctness of 0.99, completeness of 0.87, and F1 score of 0.92. When the master ruleset was applied to tussock tundra without any adaptations, classification accuracies remained promising while reporting correctness of 0.87, completeness of 0.77, and an F1 score of 0.81. Overall, results suggest that the object-based image analysis-based trough modelling workflow exhibits substantial interoperability across the terrain while producing promising classification accuracies. From an Arctic earth science perspective, the mapped troughs combined with the ArcticDEM can allow hydrological assessments of lateral connectivity of the rapidly changing Arctic tundra landscape, and repeated mapping can allow us to track fine-scale changes across large regions and that has potentially major implications on larger riverine systems.

We developed a high-throughput mapping workflow, which centers on deep learning (DL) convolutional neural network (CNN) algorithms on high-performance distributed computing resources, to automatically characterize ice-wedge polygons (IWPs) from sub-meter resolution commercial satellite imagery. We applied a region-based CNN object instance segmentation algorithm, namely the Mask R-CNN, to automatically detect and classify IWPs in North Slope of Alaska. The central goal of our study was to systematically expound the DLCNN model interoperability across varying tundra types (sedge, tussock sedge, and non-tussock sedge) and image scene complexities to refine the understanding of opportunities and challenges for regional-scale mapping applications. We corroborated quantitative error statistics along with detailed visual inspections to gauge the IWP detection accuracies. We found promising model performances (detection accuracies: 89% to 96% and classification accuracies: 94% to 97%) for all candidate image scenes with varying tundra types. The mapping workflow discerned the IWPs by exhibiting low absolute mean relative error (AMRE) values (0.17–0.23). Results further suggest the importance of increasing the variability of training samples when practicing transfer-learning strategy to map IWPs across heterogeneous tundra cover types. Overall, our findings demonstrate the robust performances of IWPs mapping workflow in multiple tundra landscapes.

Deep learning (DL) convolutional neural networks (CNNs) have been rapidly adapted in very high spatial resolution (VHSR) satellite image analysis. DLCNN-based computer visions (CV) applications primarily aim for everyday object detection from standard red, green, blue (RGB) imagery, while earth science remote sensing applications focus on geo object detection and classification from multispectral (MS) imagery. MS imagery includes RGB and narrow spectral channels from near- and/or middle-infrared regions of reflectance spectra. The central objective of this exploratory study is to understand to what degree MS band statistics govern DLCNN model predictions. We scaffold our analysis on a case study that uses Arctic tundra permafrost landform features called ice-wedge polygons (IWPs) as candidate geo objects. We choose Mask RCNN as the DLCNN architecture to detect IWPs from eight-band Worldview-02 VHSR satellite imagery. A systematic experiment was designed to understand the impact on choosing the optimal three-band combination in model prediction. We tasked five cohorts of three-band combinations coupled with statistical measures to gauge the spectral variability of input MS bands. The candidate scenes produced high model detection accuracies for the F1 score, ranging between 0.89 to 0.95, for two different band combinations (coastal blue, blue, green (1,2,3) and green, yellow, red (3,4,5)). The mapping workflow discerned the IWPs by exhibiting low random and systematic error in the order of 0.17–0.19 and 0.20–0.21, respectively, for band combinations (1,2,3). Results suggest that the prediction accuracy of the Mask-RCNN model is significantly influenced by the input MS bands. Overall, our findings accentuate the importance of considering the image statistics of input MS bands and careful selection of optimal bands for DLCNN predictions when DLCNN architectures are restricted to three spectral channels.

The microtopography associated with ice-wedge polygons governs many aspects of Arctic ecosystem, permafrost, and hydrologic dynamics from local to regional scales owing to the linkages between microtopography and the flow and storage of water, vegetation succession, and permafrost dynamics. Wide-spread ice-wedge degradation is transforming low-centered polygons into high-centered polygons at an alarming rate. Accurate data on spatial distribution of ice-wedge polygons at a pan-Arctic scale are not yet available, despite the availability of sub-meter-scale remote sensing imagery. This is because the necessary spatial detail quickly produces data volumes that hamper both manual and semi-automated mapping approaches across large geographical extents. Accordingly, transforming big imagery into ‘science-ready’ insightful analytics demands novel image-to-assessment pipelines that are fueled by advanced machine learning techniques and high-performance computational resources. In this exploratory study, we tasked a deep-learning driven object instance segmentation method (i.e., the Mask R-CNN) with delineating and classifying ice-wedge polygons in very high spatial resolution aerial orthoimagery. We conducted a systematic experiment to gauge the performances and interoperability of the Mask R-CNN across spatial resolutions (0.15 m to 1 m) and image scene contents (a total of 134 km2) near Nuiqsut, Northern Alaska. The trained Mask R-CNN reported mean average precisions of 0.70 and 0.60 at thresholds of 0.50 and 0.75, respectively. Manual validations showed that approximately 95% of individual ice-wedge polygons were correctly delineated and classified, with an overall classification accuracy of 79%. Our findings show that the Mask R-CNN is a robust method to automatically identify ice-wedge polygons from fine-resolution optical imagery. Overall, this automated imagery-enabled intense mapping approach can provide a foundational framework that may propel future pan-Arctic studies of permafrost thaw, tundra landscape evolution, and the role of high latitudes in the global climate system.

Traditional methods of detecting and mapping utility poles are inefficient and costly because of the demand for visual interpretation with quality data sources or intense field inspection. The advent of deep learning for object detection provides an opportunity for detecting utility poles from side-view optical images. In this study, we proposed using a deep learning-based method for automatically mapping roadside utility poles with crossarms (UPCs) from Google Street View (GSV) images. The method combines the state-of-the-art DL object detection algorithm (i.e., the RetinaNet object detection algorithm) and a modified brute-force-based line-of-bearing (LOB, a LOB stands for the ray towards the location of the target [UPC at here] from the original location of the sensor [GSV mobile platform]) measurement method to estimate the locations of detected roadside UPCs from GSV. Experimental results indicate that: (1) both the average precision (AP) and the overall accuracy (OA) are around 0.78 when the intersection-over-union (IoU) threshold is greater than 0.3, based on the testing of 500 GSV images with a total number of 937 objects; and (2) around 2.6%, 47%, and 79% of estimated locations of utility poles are within 1 m, 5 m, and 10 m buffer zones, respectively, around the referenced locations of utility poles. In general, this study indicates that even in a complex background, most utility poles can be detected with the use of DL, and the LOB measurement method can estimate the locations of most UPCs.

The logistical challenges of Antarctic field work and the increasing availability of very high resolution commercial imagery have driven an interest in more efficient search and classification of remotely sensed imagery. This exploratory study employed geographic object-based analysis (GEOBIA) methods to classify guano stains, indicative of chinstrap and Adélie penguin breeding areas, from very high spatial resolution (VHSR) satellite imagery and closely examined the transferability of knowledge-based GEOBIA rules across different study sites focusing on the same semantic class. We systematically gauged the segmentation quality, classification accuracy, and the reproducibility of fuzzy rules. A master ruleset was developed based on one study site and it was re-tasked “without adaptation” and “with adaptation” on candidate image scenes comprising guano stains. Our results suggest that object-based methods incorporating the spectral, textural, spatial, and contextual characteristics of guano are capable of successfully detecting guano stains. Reapplication of the master ruleset on candidate scenes without modifications produced inferior classification results, while adapted rules produced comparable or superior results compared to the reference image. This work provides a road map to an operational “image-to-assessment pipeline” that will enable Antarctic wildlife researchers to seamlessly integrate VHSR imagery into on-demand penguin population census.