Search

Sea ice, crucial to the Arctic and Earth's climate, requires consistent monitoring and high-resolution mapping. Manual sea ice mapping, however, is time-consuming and subjective, prompting the need for automated deep learning-based classification approaches. However, training these algorithms is challenging because expert-generated ice charts, commonly used as training data, do not map single ice types but instead map polygons with multiple ice types. Moreover, the distribution of various ice types in these charts is frequently imbalanced, resulting in a performance bias towards the dominant class. In this paper, we present a novel GeoAI approach to training sea ice classification by formalizing it as a partial label learning task with explicit confidence scores to address multiple labels and class imbalance. We treat the polygon-level labels as candidate partial labels, assign the corresponding ice concentrations as confidence scores to each candidate label, and integrate them with focal loss to train a Convolutional Neural Network (CNN). Our proposed approach leads to enhanced performance for sea ice classification in Sentinel-1 dual-polarized SAR images, improving classification accuracy (from 87% to 92%) and weighted average F-1 score (from 90% to 93%) compared to the conventional training approach of using one-hot encoded labels and Categorical Cross-Entropy loss. It also improves the F-1 score in 4 out of the 6 sea ice classes., Comment: Updated DOI and copyright info. Accepted for publication at the IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

Up-to-date sea ice charts are crucial for safer navigation in ice-infested waters. Recently, Convolutional Neural Network (CNN) models show the potential to accelerate the generation of ice maps for large regions. However, results from CNN models still need to undergo scrutiny as higher metrics performance not always translate to adequate outputs. Sea ice type classes are imbalanced, requiring special treatment during training. We evaluate how three different loss functions, some developed for imbalanced class problems, affect the performance of CNN models trained to predict the dominant ice type in Sentinel-1 images. Despite the fact that Dice and Focal loss produce higher metrics, results from cross-entropy seem generally more physically consistent.

Deploying deep learning on Synthetic Aperture Radar (SAR) data is becoming more common for mapping purposes. One such case is sea ice, which is highly dynamic and rapidly changes as a result of the combined effect of wind, temperature, and ocean currents. Therefore, frequent mapping of sea ice is necessary to ensure safe marine navigation. However, there is a general shortage of expert-labeled data to train deep learning algorithms. Fine-tuning a pre-trained model on SAR imagery is a potential solution. In this paper, we compare the performance of deep learning models trained from scratch using randomly initialized weights against pre-trained models that we fine-tune for this purpose. Our results show that pre-trained models lead to better results, especially on test samples from the melt season.

Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, models trained with our largest training set have weighted F1 scores all greater than 0.95 for January and July test scenes. Specifically, the median weighted F1 score was 0.98, indicating high performance for both months. By comparison, a competitive baseline U-Net has a weighted average F1 score of ranging from 0.92 to 0.94 (median 0.93) for July, and 0.97 to 0.98 (median 0.97) for January. Multiclass ice type classification is more challenging, and even though our models achieve 2% improvement in weighted F1 average compared to the baseline U-Net, test weighted F1 is generally between 0.6 and 0.80. Our approach can efficiently segment full SAR scenes in one run, is faster than the baseline U-Net, retains spatial resolution and dimension, and is more robust against noise compared to approaches that rely on patch classification.

Electrical grids are geographical and topological structures whose voltage states are challenging to represent accurately and efficiently for visual analysis. The current common practice is to use colored contour maps, yet these can misrepresent the data. We examine the suitability of four alternative visualization methods for depicting voltage data in a geographically dense distribution system -- Voronoi polygons, H3 tessellations, S2 tessellations, and a network-weighted contour map. We find that Voronoi tessellations and network-weighted contour maps more accurately represent the statistical distribution of the data than regular contour maps., Comment: IEEE Vis 2023

Aerosols play a critical role in atmospheric chemistry, and affect clouds, climate, and human health. However, the spatial coverage of satellite-derived aerosol optical depth (AOD) products is limited by cloud cover, orbit patterns, polar night, snow, and bright surfaces, which negatively impacts the coverage and accuracy of particulate matter modeling and health studies relying on air pollution characterization. We present a random forest model trained to capture spatial dependence of AOD and produce higher coverage through imputation. By combining the models with and without the mean filters, we are able to create full-coverage high-resolution daily AOD in the conterminous U.S., which can be used for aerosol estimation and other studies leveraging air pollutant concentration levels., Comment: IEEE International Geoscience and Remote Sensing Symposium 2023 6 Pages, 2 Figures

With COVID-19 affecting every country globally and changing everyday life, the ability to forecast the spread of the disease is more important than any previous epidemic. The conventional methods of disease-spread modeling, compartmental models, are based on the assumption of spatiotemporal homogeneity of the spread of the virus, which may cause forecasting to underperform, especially at high spatial resolutions. In this paper we approach the forecasting task with an alternative technique - spatiotemporal machine learning. We present COVID-LSTM, a data-driven model based on a Long Short-term Memory deep learning architecture for forecasting COVID-19 incidence at the county-level in the US. We use the weekly number of new positive cases as temporal input, and hand-engineered spatial features from Facebook movement and connectedness datasets to capture the spread of the disease in time and space. COVID-LSTM outperforms the COVID-19 Forecast Hub's Ensemble model (COVIDhub-ensemble) on our 17-week evaluation period, making it the first model to be more accurate than the COVIDhub-ensemble over one or more forecast periods. Over the 4-week forecast horizon, our model is on average 50 cases per county more accurate than the COVIDhub-ensemble. We highlight that the underutilization of data-driven forecasting of disease spread prior to COVID-19 is likely due to the lack of sufficient data available for previous diseases, in addition to the recent advances in machine learning methods for spatiotemporal forecasting. We discuss the impediments to the wider uptake of data-driven forecasting, and whether it is likely that more deep learning-based models will be used in the future.

Online sampling-supported visual analytics is increasingly important, as it allows users to explore large datasets with acceptable approximate answers at interactive rates. However, existing online spatiotemporal sampling techniques are often biased, as most researchers have primarily focused on reducing computational latency. Biased sampling approaches select data with unequal probabilities and produce results that do not match the exact data distribution, leading end users to incorrect interpretations. In this paper, we propose a novel approach to perform unbiased online sampling of large spatiotemporal data. The proposed approach ensures the same probability of selection to every point that qualifies the specifications of a user's multidimensional query. To achieve unbiased sampling for accurate representative interactive visualizations, we design a novel data index and an associated sample retrieval plan. Our proposed sampling approach is suitable for a wide variety of visual analytics tasks, e.g., tasks that run aggregate queries of spatiotemporal data. Extensive experiments confirm the superiority of our approach over a state-of-the-art spatial online sampling technique, demonstrating that within the same computational time, data samples generated in our approach are at least 50% more accurate in representing the actual spatial distribution of the data and enable approximate visualizations to present closer visual appearances to the exact ones., Comment: IEEE VIS (InfoVis/VAST/SciVis) 2020 ACM 2012 CCS - Human-centered computing, Visualization, Visualization design and evaluation methods

The first responder community has traditionally relied on calls from the public, officially-provided geographic information and maps for coordinating actions on the ground. The ubiquity of social media platforms created an opportunity for near real-time sensing of the situation (e.g. unfolding weather events or crises) through volunteered geographic information. In this article, we provide an overview of the design process and features of the Social Media Analytics Reporting Toolkit (SMART), a visual analytics platform developed at Purdue University for providing first responders with real-time situational awareness. We attribute its successful adoption by many first responders to its user-centered design, interactive (geo)visualizations and interactive machine learning, giving users control over analysis.

Real-time tweets can provide useful information on evolving events and situations. Geotagged tweets are especially useful, as they indicate the location of origin and provide geographic context. However, only a small portion of tweets are geotagged, limiting their use for situational awareness. In this paper, we adapt, improve, and evaluate a state-of-the-art deep learning model for city-level geolocation prediction, and integrate it with a visual analytics system tailored for real-time situational awareness. We provide computational evaluations to demonstrate the superiority and utility of our geolocation prediction model within an interactive system., Comment: 4 pages, 2 tables, 1 figure, SIGSPATIAL GeoAI Workshop

We present route packing, a novel (geo)visualization technique for displaying several routes simultaneously on a geographic map while preserving the geospatial layout, identity, directionality, and volume of individual routes. The technique collects variable-width route lines side by side while minimizing crossings, encodes them with categorical colors, and decorates them with glyphs to show their directions. Furthermore, nodes representing sources and sinks use glyphs to indicate whether routes stop at the node or merely pass through it. We conducted a crowd-sourced user study investigating route tracing performance with road networks visualized using our route packing technique. Our findings highlight the visual parameters under which the technique yields optimal performance., Comment: 10 pages, 11 figures, 2 tables, The 53rd Hawaii International Conference on System Sciences (HICSS-53)

Social media data has been increasingly used to facilitate situational awareness during events and emergencies such as natural disasters. While researchers have investigated several methods to summarize, visualize or mine the data for analysis, first responders have not been able to fully leverage research advancements largely due to the gap between academic research and deployed, functional systems. In this paper, we explore the opportunities and barriers for the effective use of social media data from first responders' perspective. We present the summary of several detailed interviews with first responders on their use of social media for situational awareness. We further assess the impact of SMART-a social media visual analytics system-on first responder operations., Comment: 8 pages, IEEE International Symposium on Technologies for Homeland Security

Various domain users are increasingly leveraging real-time social media data to gain rapid situational awareness. However, due to the high noise in the deluge of data, effectively determining semantically relevant information can be difficult, further complicated by the changing definition of relevancy by each end user for different events. The majority of existing methods for short text relevance classification fail to incorporate users' knowledge into the classification process. Existing methods that incorporate interactive user feedback focus on historical datasets. Therefore, classifiers cannot be interactively retrained for specific events or user-dependent needs in real-time. This limits real-time situational awareness, as streaming data that is incorrectly classified cannot be corrected immediately, permitting the possibility for important incoming data to be incorrectly classified as well. We present a novel interactive learning framework to improve the classification process in which the user iteratively corrects the relevancy of tweets in real-time to train the classification model on-the-fly for immediate predictive improvements. We computationally evaluate our classification model adapted to learn at interactive rates. Our results show that our approach outperforms state-of-the-art machine learning models. In addition, we integrate our framework with the extended Social Media Analytics and Reporting Toolkit (SMART) 2.0 system, allowing the use of our interactive learning framework within a visual analytics system tailored for real-time situational awareness. To demonstrate our framework's effectiveness, we provide domain expert feedback from first responders who used the extended SMART 2.0 system., Comment: 12 pages, 8 figures, 3 tables, IEEE VIS VAST 2019, TVCG

Feature selection is used in machine learning to improve predictions, decrease computation time, reduce noise, and tune models based on limited sample data. In this article, we present FeatureExplorer, a visual analytics system that supports the dynamic evaluation of regression models and importance of feature subsets through the interactive selection of features in high-dimensional feature spaces typical of hyperspectral images. The interactive system allows users to iteratively refine and diagnose the model by selecting features based on their domain knowledge, interchangeable (correlated) features, feature importance, and the resulting model performance., Comment: To appear in IEEE VIS 2019 Short Papers

Evaluating employee performance in organizations with varying workloads and tasks is challenging. Specifically, it is important to understand how quantitative measurements of employee achievements relate to supervisor expectations, what the main drivers of good performance are, and how to combine these complex and flexible performance evaluation metrics into an accurate portrayal of organizational performance in order to identify shortcomings and improve overall productivity. To facilitate this process, we summarize common organizational performance analyses into four visual exploration task categories. Additionally, we develop MetricsVis, a visual analytics system composed of multiple coordinated views to support the dynamic evaluation and comparison of individual, team, and organizational performance in public safety organizations. MetricsVis provides four primary visual components to expedite performance evaluation: (1) a priority adjustment view to support direct manipulation on evaluation metrics; (2) a reorderable performance matrix to demonstrate the details of individual employees; (3) a group performance view that highlights aggregate performance and individual contributions for each group; and (4) a projection view illustrating employees with similar specialties to facilitate shift assignments and training. We demonstrate the usability of our framework with two case studies from medium-sized law enforcement agencies and highlight its broader applicability to other domains., Comment: To appear in 2019 IEEE Transactions on Visualization and Computer Graphics

Social media platforms such as Twitter are filled with social spambots. Detecting these malicious accounts is essential, yet challenging, as they continually evolve and evade traditional detection techniques. In this work, we propose VASSL, a visual analytics system that assists in the process of detecting and labeling spambots. Our tool enhances the performance and scalability of manual labeling by providing multiple connected views and utilizing dimensionality reduction, sentiment analysis and topic modeling techniques, which offer new insights that enable the identification of spambots. The system allows users to select and analyze groups of accounts in an interactive manner, which enables the detection of spambots that may not be identified when examined individually. We conducted a user study to objectively evaluate the performance of VASSL users, as well as capturing subjective opinions about the usefulness and the ease of use of the tool., Comment: IEEE VIS (VAST) 2019

Many evaluation methods have been used to assess the usefulness of Visual Analytics (VA) solutions. These methods stem from a variety of origins with different assumptions and goals, which cause confusion about their proofing capabilities. Moreover, the lack of discussion about the evaluation processes may limit our potential to develop new evaluation methods specialized for VA. In this paper, we present an analysis of evaluation methods that have been used to summatively evaluate VA solutions. We provide a survey and taxonomy of the evaluation methods that have appeared in the VAST literature in the past two years. We then analyze these methods in terms of validity and generalizability of their findings, as well as the feasibility of using them. We propose a new metric called summative quality to compare evaluation methods according to their ability to prove usefulness, and make recommendations for selecting evaluation methods based on their summative quality in the VA domain., Comment: IEEE VIS (VAST) 2019