Search for: All records

Harmful algal blooms (HABs) are increasing in frequency in the Chesapeake Bay, posing risks to marine ecosystems, water quality, and public health. Chlorophyll-a (Chl-a) is a widely used indicator of algal biomass, and satellite observations such as Sentinel-3 Ocean and Land Color Instrument (OLCI) enable large-scale monitoring of bloom dynamics. However, cloud cover and atmospheric interference frequently introduce missing pixels in daily satellite products, reducing temporal continuity and limiting monitoring reliability. Satellite-derived chlorophyll-a (Chl-a) data exhibit substantial missingness, with daily pixel gaps ranging from approximately 52.30% to 100% (mean ≈ 88.95%). This study evaluates spatial interpolation, EOF-based, supervised machine-learning, deep-learning, and convolutional autoencoder approaches for reconstructing missing Chl-a values. Sentinel-3 OLCI Chl-a data from 2023–2024 were used for model training, while data from 2025 served as a temporally independent test set to avoid spatiotemporal leakage. To simulate cloud-induced data gaps, artificial missingness scenarios ranging from 50% to 90% were applied for the Inverse Distance Weighting (IDW) and Data Interpolating Empirical Orthogonal Functions (DINEOF) baseline approaches, while machine-learning, deep-learning, and convolutional autoencoder models were evaluated using real satellite-derived missing observations. The evaluated models include IDW, DINEOF, K-Nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), XGBoost, a Long Short-Term Memory (LSTM) network, and a Temporal Data Interpolating Convolutional Autoencoder (Temporal DINCAE). Model performance was assessed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), prediction bias, and the coefficient of determination (R2). Results indicate that tree-based ensemble models outperform spatial interpolation and EOF-based methods, with XGBoost achieving the best overall performance (R2 ≈ 0.86; RMSE ≈ 9.61 mg m−3). The LSTM model achieved lower prediction errors (RMSE ≈ 5.87 mg m−3; MAE ≈ 2.16 mg m−3), highlighting the benefit of incorporating temporal dependencies, although with slightly reduced variance capture. The convolutional autoencoder-based Temporal DINCAE model achieved strong reconstruction performance (R2 ≈ 0.84; RMSE ≈ 11.15 mg m−3). Uncertainty quantification shows that Extra Trees tends to underestimate uncertainty with narrower prediction intervals, whereas XGBoost provides better-calibrated but wider intervals. 

This study investigates uncertainty quantification using probabilistic deep learning models to detect out-of-distribution events. Deep learning models often perform poorly when exposed to data outside their training distribution, leading to unreliable predictions. This research evaluates probabilistic approaches to quantify prediction uncertainty and improve model robustness. Results demonstrate the effectiveness of uncertainty-aware deep learning methods in identifying anomalous or out-of-distribution conditions, improving reliability in real-world deployment scenarios. 

This study presents a digital twin framework for real-time monitoring of computing infrastructure systems. The framework integrates real-time sensor data, computational models, and visualization tools to create a virtual representation of physical infrastructure. The system enables real-time performance monitoring, anomaly detection, and predictive analysis, improving operational efficiency and reliability. Results demonstrate the effectiveness of digital twin approaches for enhancing infrastructure management and decision-making in computing environments. 

Abstract The Spatial Data Lab (SDL) project is a collaborative initiative by the Center for Geographic Analysis at Harvard University, KNIME, Future Data Lab, China Data Institute, and George Mason University. Co-sponsored by the NSF IUCRC Spatiotemporal Innovation Center, SDL aims to advance applied research in spatiotemporal studies across various domains such as business, environment, health, mobility, and more. The project focuses on developing an open-source infrastructure for data linkage, analysis, and collaboration. Key objectives include building spatiotemporal data services, a reproducible, replicable, and expandable (RRE) platform, and workflow-driven data analysis tools to support research case studies. Additionally, SDL promotes spatiotemporal data science training, cross-party collaboration, and the creation of geospatial tools that foster inclusivity, transparency, and ethical practices. Guided by an academic advisory committee of world-renowned scholars, the project is laying the foundation for a more open, effective, and robust scientific enterprise. 

Breathing in fine particulate matter of diameter less than 2.5 µm (PM2.5) greatly increases an individual’s risk of cardiovascular and respiratory diseases. As climate change progresses, extreme weather events, including wildfires, are expected to increase, exacerbating air pollution. However, models often struggle to capture extreme pollution events due to the rarity of high PM2.5 levels in training datasets. To address this, we implemented cluster-based undersampling and trained Transformer models to improve extreme event prediction using various cutoff thresholds (12.1 µg/m3 and 35.5 µg/m3) and partial sampling ratios (10/90, 20/80, 30/70, 40/60, 50/50). Our results demonstrate that the 35.5 µg/m3 threshold, paired with a 20/80 partial sampling ratio, achieved the best performance, with an RMSE of 2.080, MAE of 1.386, and R2 of 0.914, particularly excelling in forecasting high PM2.5 events. Overall, models trained on augmented data significantly outperformed those trained on original data, highlighting the importance of resampling techniques in improving air quality forecasting accuracy, especially for high-pollution scenarios. These findings provide critical insights into optimizing air quality forecasting models, enabling more reliable predictions of extreme pollution events. By advancing the ability to forecast high PM2.5 levels, this study contributes to the development of more informed public health and environmental policies to mitigate the impacts of air pollution, and advanced the technology for building better air quality digital twins. 

Data dashboards provide a means for sharing multiple data products at a glance and were ubiquitous during the COVID-19 pandemic. Data dashboards tracked global and country-specific statistics and provided cartographic visualizations of cases, deaths, vaccination rates and other metrics. We examined the role of geospatial data on COVID-19 dashboards in the form of maps, charts, and graphs. We organize our review of 193 COVID-19 dashboards by region and compare the accessibility and operationality of dashboards over time and the use of web maps and geospatial visualizations. We found that of the dashboards reviewed, only 17% included geospatial visualizations. We observe that many of the COVID-19 dashboards from our analysis are no longer accessible (66%) and consider the ephemeral nature of data and dashboards. We conclude that coordinated efforts and a call to action to ensure the standardization, storage, and maintenance of geospatial data for use on data dashboards and web maps are needed for long-term use, analyses, and monitoring to address current and future public health and other challenging issues. 

Chlorophyll-a (chl-a) is a key indicator of water quality in coastal and estuarine ecosystems. In regions like the Chesapeake Bay, elevated chl-a levels often signal the presence of harmful algal blooms and biomass accumulation. However, satellite-based chl-a observations are frequently obscured by cloud cover, limiting their use in continuous coastal monitoring. Spatial interpolation models, which estimate values at unsampled locations based on existing data, offer one solution to resolve this scarcity. Existing research has examined the effectiveness of different interpolation models for the bay’s salinity and temperature; however, few studies have investigated the application of these models for chl-a. In this study, we evaluate the performance of three kriging-based models—universal kriging (UK), ordinary kriging (OK), and empirical bayesian kriging (EBK)—and three machine learning-based models—k-Nearest Neighbor (KNN), Extra Trees (ET), and XGBoost—for interpolating chl-a concentrations. Using over 5 million remotely sensed observations across nine days in early 2025, we find that EBK exhibits the best performance among kriging-based models, while ET outperforms all other machine learning models. Our results also demonstrate that while kriging-based models outperform machine learning models in data-rich conditions, machine learning models are more adaptable and accurate for data-sparse conditions. Since data availability varies significantly from day-to-day based on cloud cover, these findings suggest that no one model is universally optimal. Integrating both approaches may offer a hybrid framework for improving the continuity and reliability of chl-a monitoring in coastal regions.