Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Holmes, Andrew, Jensen, Matt, Coffland, Sarah, Shen, Hidemi Mitani, Sizemore, Logan, Bassetti, Seth, Nieva, Brenna, Tebaldi, Claudia, Snyder, Abigail, Hutchinson, Brian
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.08850
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913609300312064
author Holmes, Andrew
Jensen, Matt
Coffland, Sarah
Shen, Hidemi Mitani
Sizemore, Logan
Bassetti, Seth
Nieva, Brenna
Tebaldi, Claudia
Snyder, Abigail
Hutchinson, Brian
author_facet Holmes, Andrew
Jensen, Matt
Coffland, Sarah
Shen, Hidemi Mitani
Sizemore, Logan
Bassetti, Seth
Nieva, Brenna
Tebaldi, Claudia
Snyder, Abigail
Hutchinson, Brian
contents The Global Change Analysis Model (GCAM) simulates complex interactions between the coupled Earth and human systems, providing valuable insights into the co-evolution of land, water, and energy sectors under different future scenarios. Understanding the sensitivities and drivers of this multisectoral system can lead to more robust understanding of the different pathways to particular outcomes. The interactions and complexity of the coupled human-Earth systems make GCAM simulations costly to run at scale - a requirement for large ensemble experiments which explore uncertainty in model parameters and outputs. A differentiable emulator with similar predictive power, but greater efficiency, could provide novel scenario discovery and analysis of GCAM and its outputs, requiring fewer runs of GCAM. As a first use case, we train a neural network on an existing large ensemble that explores a range of GCAM inputs related to different relative contributions of energy production sources, with a focus on wind and solar. We complement this existing ensemble with interpolated input values and a wider selection of outputs, predicting 22,528 GCAM outputs across time, sectors, and regions. We report a median $R^2$ score of 0.998 for the emulator's predictions and an $R^2$ score of 0.812 for its input-output sensitivity.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08850
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Emulating the Global Change Analysis Model with Deep Learning
Holmes, Andrew
Jensen, Matt
Coffland, Sarah
Shen, Hidemi Mitani
Sizemore, Logan
Bassetti, Seth
Nieva, Brenna
Tebaldi, Claudia
Snyder, Abigail
Hutchinson, Brian
General Economics
Economics
Machine Learning
Neural and Evolutionary Computing
The Global Change Analysis Model (GCAM) simulates complex interactions between the coupled Earth and human systems, providing valuable insights into the co-evolution of land, water, and energy sectors under different future scenarios. Understanding the sensitivities and drivers of this multisectoral system can lead to more robust understanding of the different pathways to particular outcomes. The interactions and complexity of the coupled human-Earth systems make GCAM simulations costly to run at scale - a requirement for large ensemble experiments which explore uncertainty in model parameters and outputs. A differentiable emulator with similar predictive power, but greater efficiency, could provide novel scenario discovery and analysis of GCAM and its outputs, requiring fewer runs of GCAM. As a first use case, we train a neural network on an existing large ensemble that explores a range of GCAM inputs related to different relative contributions of energy production sources, with a focus on wind and solar. We complement this existing ensemble with interpolated input values and a wider selection of outputs, predicting 22,528 GCAM outputs across time, sectors, and regions. We report a median $R^2$ score of 0.998 for the emulator's predictions and an $R^2$ score of 0.812 for its input-output sensitivity.
title Emulating the Global Change Analysis Model with Deep Learning
topic General Economics
Economics
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2412.08850