Publications (27)
In Situ Framework for Coupling Simulation and Machine Learning with Application to CFD
Riccardo Balin, Filippo Simini, Cooper Simpson +7
Recent years have seen many successful applications of machine learning (ML) to facilitate fluid dynamic computations. As simulations grow, generating new training datasets for tra…
A Deep Probabilistic Framework for Continuous Time Dynamic Graph Generation
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath +1
Recent advancements in graph representation learning have shifted attention towards dynamic graphs, which exhibit evolving topologies and features over time. The increased use of s…
Prediction of next career moves from scientific profiles
Charlotte James, Luca Pappalardo, Alina Sirbu +1
Changing institution is a scientist's key career decision, which plays an important role in education, scientific productivity, and the generation of scientific knowledge. Yet, our…
Universal Scaling of Optimal Current Distribution in Transportation Networks
Filippo Simini, Andrea Rinaldo, Amos Maritan
Transportation networks are inevitably selected with reference to their global cost which depends on the strengths and the distribution of the embedded currents. We prove that opti…
The agglomeration and dispersion dichotomy of human settlements on Earth
Emanuele Strano, Filippo Simini, Marco De Nadai +2
Human settlements on Earth are scattered in a multitude of shapes, sizes and spatial arrangements. These patterns are often not random but a result of complex geographical, cultura…
Identifying the structural discontinuities of human interactions
Sebastian Grauwin, Michael Szell, Stanislav Sobolevsky +6
The idea of a hierarchical spatial organization of society lies at the core of seminal theories in human geography that have strongly influenced our understanding of social organiz…
Evacuation time estimate for a total pedestrian evacuation using queuing network model and volunteered geographic information
Bharat Kunwar, Filippo Simini, Anders Johansson
Estimating city evacuation time is a non-trivial problem due to the interaction between thousands of individual agents, giving rise to various collective phenomena, such as bottlen…
Aurora: Architecting Argonne's First Exascale Supercomputer for Accelerated Scientific Discovery
William E. Allcock, Benjamin S. Allen, James Anchell +106
Aurora is Argonne National Laboratory's pioneering Exascale supercomputer, designed to accelerate scientific discovery with cutting-edge architectural innovations. Key new technolo…
Deep Surrogate Docking: Accelerating Automated Drug Discovery with Graph Neural Networks
Ryien Hosseini, Filippo Simini, Austin Clyde +1
The process of screening molecules for desirable properties is a key step in several applications, ranging from drug discovery to material design. During the process of drug discov…
Human Mobility in a Continuum Approach
Filippo Simini, Amos Maritan, Zoltán Néda
Human mobility is investigated using a continuum approach that allows to calculate the probability to observe a trip to anyarbitrary region, and the fluxes between any two regions.…
A universal model for mobility and migration patterns
Filippo Simini, Marta C. González, Amos Maritan +1
Introduced in its contemporary form by George Kingsley Zipf in 1946, but with roots that go back to the work of Gaspard Monge in the 18th century, the gravity law is the prevailing…
Quality Measures for Dynamic Graph Generative Models
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath +2
Deep generative models have recently achieved significant success in modeling graph data, including dynamic graphs, where topology and features evolve over time. However, unlike in…
Data-driven generation of spatio-temporal routines in human mobility
Luca Pappalardo, Filippo Simini
The generation of realistic spatio-temporal trajectories of human mobility is of fundamental importance in a wide range of applications, such as the developing of protocols for mob…
Operation-Level Performance Benchmarking of Graph Neural Networks for Scientific Applications
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath
As Graph Neural Networks (GNNs) increase in popularity for scientific machine learning, their training and inference efficiency is becoming increasingly critical. Additionally, the…
Human Mobility: Models and Applications
Hugo Barbosa-Filho, Marc Barthelemy, Gourab Ghoshal +7
Recent years have witnessed an explosion of extensive geolocated datasets related to human movement, enabling scientists to quantitatively study individual and collective mobility…
A Multi-Level, Multi-Scale Visual Analytics Approach to Assessment of Multifidelity HPC Systems
Shilpika, Bethany Lusch, Murali Emani +4
The ability to monitor and interpret of hardware system events and behaviors are crucial to improving the robustness and reliability of these systems, especially in a supercomputin…
Scikit-mobility: a Python library for the analysis, generation and risk assessment of mobility data
Luca Pappalardo, Filippo Simini, Gianni Barlacchi +1
The last decade has witnessed the emergence of massive mobility data sets, such as tracks generated by GPS devices, call detail records, and geo-tagged posts from social media plat…
Zipf's and Taylor's Laws
Charlotte James, Sandro Azaele, Amos Maritan +1
Zipf's law states that the frequency of an observation with a given value is inversely proportional to the square of that value; Taylor's law, instead, describes the scaling betwee…
Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
Ryien Hosseini, Filippo Simini, Venkatram Vishwanath +2
Graph Neural Networks learn on graph-structured data by iteratively aggregating local neighborhood information. While this local message passing paradigm imparts a powerful inducti…
An allometry-based approach for understanding forest structure, predicting tree-size distribution and assessing the degree of disturbance
Tommaso Anfodillo, Marco Carrer, Filippo Simini +3
Tree-size distribution is one of the most investigated subjects in plant population biology. The forestry literature reports that tree-size distribution trajectories vary across di…
Power-law of Aggregate-size Spectra in Natural Systems
Matteo Convertino, Filippo Simini, Filippo Catani +2
Patterns of animate and inanimate systems show remarkable similarities in their aggregation. One similarity is the double-Pareto distribution of the aggregate-size of system compon…
Social media usage reveals how regions recover after natural disaster
Robert Eyre, Flavia De Luca, Filippo Simini
The challenge of nowcasting and forecasting the effect of natural disasters (e.g. earthquakes, floods, hurricanes) on assets, people and society is of primary importance for assess…
Nanoscale artificial intelligence: creating artificial neural networks using autocatalytic reactions
Filippo Simini
A general methodology is proposed to engineer a system of interacting components (particles) which is able to self-regulate their concentrations in order to produce any prescribed…
Emergence of structural and dynamical properties of ecological mutualistic networks
Samir Suweis, Filippo Simini, Jayanth R. Banavar +1
Mutualistic networks are formed when the interactions between two classes of species are mutually beneficial. They are important examples of cooperation shaped by evolution. Mutual…
Discovering the laws of urbanisation
Filippo Simini, Charlotte James
In 2012 the world's population exceeded 7 billion, and since 2008 the number of individuals living in urban areas has surpassed that of rural areas. This is the result of an overal…
Deep Gravity: enhancing mobility flows generation with deep neural networks and geographic information
Filippo Simini, Gianni Barlacchi, Massimiliano Luca +1
The movements of individuals within and among cities influence critical aspects of our society, such as well-being, the spreading of epidemics, and the quality of the environment.…
Self-Similarity and Scaling in Forest Communities
Filippo Simini, Tommaso Anfodillo, Marco Carrer +2
Ecological communities exhibit pervasive patterns and inter-relationships between size, abundance, and the availability of resources. We use scaling ideas to develop a unified, mod…