Search

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.

Serious traffic congestion and emission by excessive usage of private cars are crucial issues in our modern society. As one solution for these, a concept of Park-and-Ride (PnR) where people stop their private cars (i.e. single-occupancy vehicles) at stations and ride on public vehicles (i.e. mass transportation) are receiving wide attention recently. In this paper, we propose a comprehensive mathematical model which can evaluate waiting times and traveling times of customers, and the total emission of vehicles for various usage ratio of PnR and operation policies of public transportation. Using a system of queues integrated with an emissions model we perform a case-study of Tsukuba city, in Japan. We indicate an intriguing trade-off between the waiting time of customers for the PnR and the long traveling time due to the traffic congestion (leading to high emissions) caused by private cars depending on the usage ratio through some numerical experiments. Moreover, we study the total cost to society caused by total trip times and pollution, in which the decision variables are the capacities and frequencies of the public transportation for the PnR system. Our numerical results showed a significant reduction in the total social cost under the optimal transit policy for the current high usage rate of single-occupancy vehicles. Furthermore, we show that further reduction in the total social cost can be revealed by considering the reduction on the use of private cars compared to the current state implying the social importance of promoting car-free movement., Comment: 52 pages, 35 figures

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., Comment: Minor revision; to appear in Crop Sciences