About this Abstract

Meeting

MS&T24: Materials Science & Technology

Symposium

Machine Learning and Simulations

Presentation Title

B-2:Forecasting Nutrient Flows Using Terrain Elevation-Aware Spatial-Temporal Graph Neural Networks

Author(s)

Jiaqi Li, Alexander H. Bradley, Olatunde Akanbi, Laura Bruckman, Erika Barcelos, Roger French, Yinghui Wu

On-Site Speaker (Planned)

Jiaqi Li

Abstract Scope

We propose a class of Terrain Elevation-aware Spatio-Temporal Graph Neural Networks (ST-EGNN) that incorporates terrain elevation data to its edge model to improve the accuracy of time-series forecasting based agricultural nutrient flow analysis. Results were compared against three baseline models: (a) a spatial-temporal Graph Neural Network that only use edges induced from 2D Euclidean distances, and two deep neural networks: (b) sequence to sequence (seq2seq), which is a class of deep learning architectures renowned for their accomplishments in various domain, and (c) LSTM is a type of recurrent neural network architecture designed to overcome the vanishing gradient problem in traditional RNNs, respectively. In addition, the framework leverages data imputation from multiple sensors concurrently to improve the robustness of STEGNN against the impact of missing data. By learning spatial, temporal and elevation patterns, our approach endeavors to offer a more adaptable predictive framework for nutrition analysis in water and river systems.

OTHER PAPERS PLANNED FOR THIS SYMPOSIUM

A Machine Learning Approach to Predict Solute Segregation Energy in Ni Grain Boundaries

A Machine Learning Based Computational Method for Accurate Prediction of Equilibrium Cation Distribution in Complex Spinel Oxides

Assessing GPR Models for Steel Hardness Prediction in Production Environments

B-2:Forecasting Nutrient Flows Using Terrain Elevation-Aware Spatial-Temporal Graph Neural Networks

Decoding the Structural Genome of Silicate Glasses

EBSD Geometry Calibration Through SE(3) Lie Group Optimization

End-To-End Differentiability and Tensor Processing Unit (TPU) Computing to Accelerate Materials’ Inverse Design

Estimation of Thermal Hysteresis in Zirconia Using Machine Learning Molecular Dynamics and Transition State Modelling

Forward Prediction and Inverse Design of Additively Manufacturable Alloys via Autoregressive Language Models

Generation of Machine Learning Interatomic Potentials for Boron Carbide with Comparison to the Analytic Angular Dependent Potential

Graph Neural Networks for Rapid Continuum Damage Modeling of Semi-Crystalline Polymers

Machine Learning in Nuclear Waste Glass Formulation and Property Model Development

Multi-Fidelity Gaussian Process Models for Time-Series Outputs

New Machine–Learning Interatomic Potentials (MLIPs) for Si-C-O-H Compounds Enabling Atomistic Simulations of Complex Chemical Transformations

Predicting the Dynamics of Atoms in Liquids by a Surrogate Machine-Learned Simulator

Understanding Grain-Boundary Structure Using Strain Functional Descriptors and Unsupervised Machine Learning

Questions about ProgramMaster? Contact programming@programmaster.org | TMS Privacy Policy | Accessibility Statement