English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Improving predictive understanding of Earth system variability and changerequires data-model integration. Efficient data-model integration for complexmodels requires surrogate modeling to reduce model evaluation time. However,building a surrogate of a large-scale Earth system model (ESM) with many outputvariables is computationally intensive because it involves a large number ofexpensive ESM simulations. In this effort, we propose an efficient surrogatemethod capable of using a few ESM runs to build an accurate andfast-to-evaluate surrogate system of model outputs over large spatial andtemporal domains. We first use singular value decomposition to reduce theoutput dimensions, and then use Bayesian optimization techniques to generate anaccurate neural network surrogate model based on limited ESM simulationsamples. Our machine learning based surrogate methods can build and evaluate alarge surrogate system of many variables quickly. Thus, whenever the quantitiesof interest change such as a different objective function, a new site, and alonger simulation time, we can simply extract the information of interest fromthe surrogate system without rebuilding new surrogates, which significantlysaves computational efforts. We apply the proposed method to a regionalecosystem model to approximate the relationship between 8 model parameters and42660 carbon flux outputs. Results indicate that using only 20 modelsimulations, we can build an accurate surrogate system of the 42660 variables,where the consistency between the surrogate prediction and actual modelsimulation is 0.93 and the mean squared error is 0.02. This highly-accurate andfast-to-evaluate surrogate system will greatly enhance the computationalefficiency in data-model integration to improve predictions and advance ourunderstanding of the Earth system.

Efficient surrogate modeling methods for large-scale Earth system models based on machine learning techniques