Several models have correlated COVID-19 spread with specific climatic, geophysical, and air pollution conditions, and early models had predicted the lowering of infection cases in Summer 2020. These approaches have been criticized for their coarse assumptions and because they could produce biases if used without considering dynamic factors such as human mobility and interaction. However, human mobility and interaction models alone have not been able to suggest more innovative recommendations than simple social distancing and lockdown, and would definitely need to include information about the base environmental suitability of a World area to COVID-19 spread. This scenario would benefit from a global-scale high-resolution environmental model that could be coupled with dynamic models for large-scale and regional analyses. This article presents a 0.1˚ high-resolution global-scale probability map of low and high-infection-rates of COVID-19 that uses annual-average surface air temperature, precipitation, and CO2 as environmental parameters, and Italian provinces as training locations. A risk index calculated on this map correctly identifies 87% of the World countries that reported high infection rates in 2020 and 80% of the low and high infection-rate countries overall. Our model is meant to be used as an additional factor in other models for monthly weather and human mobility. It estimates the base environmental inertia that a geographical place opposes to COVID-19 when mobility restrictions are not in place and can support how much the monthly weather favors or penalizes infection increase. Its high resolution and extent make it consistently usable in global and regional-scale analyses, also thanks to the availability of our results as FAIR data and software as an Open Science-oriented Web service.

A High-resolution Global-scale Model for COVID-19 Infection Rate

Tlife-GDN: Detecting and Forecasting Spatio-Temporal Anomalies via Persistent Homology and Geometric Deep Learning

This paper introduces an interactive visualization interface with a machine learning consensus analysis that enables the researchers to explore the impact of atmospheric and socioeconomic factors on COVID-19 clinical severity by employing multiple Recurrent Graph Neural Networks. We designed and implemented a visualization interface that leverages coordinated multi-views to support exploratory and predictive analysis of hospitalizations and other socio-geographic variables at multiple dimensions, simultaneously. By harnessing the strength of geometric deep learning, we build a consensus machine learning model to include knowledge from county-level records and investigate the complex interrelationships between global infectious disease, environment, and social justice. Additionally, we make use of unique NASA satellite-based observations which are not broadly used in the context of climate justice applications. Our current interactive interface focus on three US states (California, Pennsylvania, and Texas) to demonstrate its scientific value and presented three case studies to make qualitative evaluations. 

/pdf/learning-on-health-fairness-and-environmental-justice-via-1n6f15us.pdf

Learning on Health Fairness and Environmental Justice via Interactive Visualization

This paper introduces an interactive visualization interface with a machine learning consensus analysis that enables the researchers to explore the impact of atmospheric and socioeconomic factors on COVID-19 clinical severity by employing multiple Recurrent Graph Neural Networks. We designed and implemented a visualization interface that leverages coordinated multi-views to support exploratory and predictive analysis of hospitalizations and other socio-geographic variables at multiple dimensions, simultaneously. By harnessing the strength of geometric deep learning, we build a consensus machine learning model to include knowledge from county-level records and investigate the complex interrelationships between global infectious disease, environment, and social justice. Additionally, we make use of unique NASA satellite-based observations which are not broadly used in the context of climate justice applications. Our current interactive interface focus on three US states (California, Pennsylvania, and Texas) to demonstrate its scientific value and presented three case studies to make qualitative evaluations.

As multiple adverse events in 2021 illustrated, virtually all aspects of our societal functioning -- from water and food security to energy supply to healthcare -- more than ever depend on the dynamics of environmental factors. Nevertheless, the social dimensions of weather and climate are noticeably less explored by the machine learning community, largely, due to the lack of reliable and easy access to use data. Here we present a unique not yet broadly available NASA's satellite dataset on aerosol optical depth (AOD), temperature and relative humidity and discuss the utility of these new data for COVID-19 biosurveillance. In particular, using the geometric deep learning models for semi-supervised classification on a county-level basis over the contiguous United States, we investigate the pressing societal question whether atmospheric variables have considerable impact on COVID-19 clinical severity.

Using NASA Satellite Data Sources and Geometric Deep Learning to Uncover Hidden Patterns in COVID-19 Clinical Severity.

Given that persons with a prior history of respiratory diseases tend to demonstrate more severe illness from COVID-19 and, hence, are at higher risk of serious symptoms, ambient air quality data from NASA's satellite observations might provide a critical insight into which geographical areas may exhibit higher numbers of hospitalizations due to COVID-19, how the expected severity of COVID-19 and associated survival rates may vary across space in the future, and most importantly how given this information, health professionals can distribute vaccines in a more efficient, timely, and fair manner. Despite the utmost urgency of this problem, there yet exists no systematic analysis on linkages among COVID-19 clinical severity, air quality, and other atmospheric conditions, beyond relatively simplistic regression-based models. The goal of this project is to glean a deeper insight into sophisticated spatio-temporal dependencies among air quality, atmospheric conditions, and COVID-19 clinical severity using the machinery of Geometric Deep Learning (GDL), while providing quantitative uncertainty estimates. Our results based on the GDL model on a county level in three US states, California, Pennsylvania and Texas, indicate that AOD attributes to COVID-19 clinical severity in 39, 30, and 132 counties out of 58, 67, and 254 total counties, respectively. In turn, relative humidity is another important factor for understanding dynamics of clinical course and mortality risks due COVID-19, but predictive utility of temperature is noticeably lower. Our findings do not only contribute to understanding of latent factors behind COVID-19 progression but open new perspectives for innovative use of NASA's datasets for biosurveillance and social good.

https://dl.acm.org/doi/pdf/10.1145/3447548.3467207

Does Air Quality Really Impact COVID-19 Clinical Severity: Coupling NASA Satellite Datasets with Geometric Deep Learning

Motivated by the recent surge of criminal activities with cross-cryptocurrency trades, we introduce a new topological perspective to structural anomaly detection in dynamic multilayer networks. We postulate that anomalies in the underlying blockchain transaction graph that are composed of multiple layers are likely to be also manifested in anomalous patterns of the network shape properties. As such, we invoke the machinery of clique persistent homology on graphs to systematically and efficiently track evolution of the network shape and, as a result, to detect changes in the underlying network topology and geometry. We develop a new persistence summary for multilayer networks, called stacked persistence diagram, and prove its stability under input data perturbations. We validate our new topological anomaly detection framework in application to dynamic multilayer networks from the Ethereum Blockchain and the Ripple Credit Network, and show that our stacked PD approach substantially outperforms the state-of-art techniques, yielding up to 40% gains in precision.

Ignacio Segovia Dominguez

Papers

Does Air Quality Really Impact COVID-19 Clinical Severity: Coupling NASA Satellite Datasets with Geometric Deep Learning

Topological Anomaly Detection in Dynamic Multilayer Blockchain Networks