arXiv subjects

Fabiana Ferracina

Publications and source records attributed to Fabiana Ferracina.

3 recordsLinked to original sources

arXiv2024

Learning to Simulate Aerosol Dynamics with Graph Neural Networks

Aerosol effects on climate, weather, and air quality depend on characteristics of individual particles, which are tremendously diverse and change in time. Particle-resolved models are the only models able to capture this diversity in particle physiochemical properties, and these models are computationally expensive. As a strategy for accelerating particle-resolved microphysics models, we introduce Graph-based Learning of Aerosol Dynamics (GLAD) and use this model to train a surrogate of the particle-resolved model PartMC-MOSAIC. GLAD implements a Graph Network-based Simulator (GNS), a machine learning framework that has been used to simulate particle-based fluid dynamics models. In GLAD, each particle is represented as a node in a graph, and the evolution of the particle population over time is simulated through learned message passing. We demonstrate our GNS approach on a simple aerosol system that includes condensation of sulfuric acid onto particles composed of sulfate, black carbon, organic carbon, and water. A graph with particles as nodes is constructed, and a graph neural network (GNN) is then trained using the model output from PartMC-MOSAIC. The trained GNN can then be used for simulating and predicting aerosol dynamics over time. Results demonstrate the framework's ability to accurately learn chemical dynamics and generalize across different scenarios, achieving efficient training and prediction times. We evaluate the performance across three scenarios, highlighting the framework's robustness and adaptability in modeling aerosol microphysics and chemistry.

physics.ao-ph↗

arXiv2024

Reducing Total Trip Time and Vehicle Emission through Park-and-Ride -- methods and case-study

This study addresses important issues of traffic congestion and vehicle emissions in urban areas by developing a comprehensive mathematical framework to evaluate Park-and-Ride (PnR) systems. The proposed approach integrates queueing theory and emissions modeling to simultaneously assess waiting times, travel times, and vehicle emissions under various PnR usage scenarios. The methodology employs a novel combination of Monte Carlo simulation and matrix geometric analytic methods to analyze a queueing network representing PnR facilities and road traffic. A case study of Tsukuba, Japan demonstrates the model's applicability, revealing potential reductions in social costs related to total trip time and emissions through optimized PnR policies. Specifically, the study found that implementing optimal bus frequency and capacity policies could reduce total social costs by up to 30\% compared to current conditions. This research contributes to the literature by providing a unified framework for evaluating PnR systems that considers both time and environmental costs, offering valuable insights for urban planners and policymakers seeking to improve transportation sustainability. The proposed model utilizes a single server queue with a deterministic service time and multiple arrival streams to represent traffic flow, incorporating both private cars and public buses. Emissions are calculated using the Methodologies for Estimating Air Pollutant Emissions from Transport (MEET) framework. The social cost of emissions and total trip time (SCETT) is introduced as a comprehensive metric for evaluating PnR system performance.

stat.CO↗

arXiv2024

Predictive Analytics of Varieties of Potatoes

We explore the application of machine learning algorithms specifically to enhance the selection process of Russet potato clones in breeding trials by predicting their suitability for advancement. This study addresses the challenge of efficiently identifying high-yield, disease-resistant, and climate-resilient potato varieties that meet processing industry standards. Leveraging manually collected data from trials in the state of Oregon, we investigate the potential of a wide variety of state-of-the-art binary classification models. The dataset includes 1086 clones, with data on 38 attributes recorded for each clone, focusing on yield, size, appearance, and frying characteristics, with several control varieties planted consistently across four Oregon regions from 2013-2021. We conduct a comprehensive analysis of the dataset that includes preprocessing, feature engineering, and imputation to address missing values. We focus on several key metrics such as accuracy, F1-score, and Matthews correlation coefficient (MCC) for model evaluation. The top-performing models, namely a neural network classifier (Neural Net), histogram-based gradient boosting classifier (HGBC), and a support vector machine classifier (SVM), demonstrate consistent and significant results. To further validate our findings, we conduct a simulation study. By simulating different data-generating scenarios, we assess model robustness and performance through true positive, true negative, false positive, and false negative distributions, area under the receiver operating characteristic curve (AUC-ROC) and MCC. The simulation results highlight that non-linear models like SVM and HGBC consistently show higher AUC-ROC and MCC than logistic regression (LR), thus outperforming the traditional linear model across various distributions, and emphasizing the importance of model selection and tuning in agricultural trials.

cs.LG↗