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

The current fuel moisture content (FMC) subsystems in WRF-SFIRE and itsworkflow system WRFx use a time-lag differential equation model withassimilation of data from FMC sensors on Remote Automated Weather Stations(RAWS) by the extended augmented Kalman filter. But the quality of the resultis constrained by the limitations of the model and of the Kalman filter. Weobserve that the data flow in a system consisting of a model and the Kalmanfilter can be interpreted to be the same as the data flow in a recurrent neuralnetwork (RNN). Thus, instead of building more sophisticated models and dataassimilation methods, we want to train a RNN to approximate the dynamics of theresponse of the FMC sensor to a time series of environmental data. Becausestandard AI approaches did not converge to reasonable solutions, we pre-trainthe RNN with special initial weights devised to turn it into a numerical solverof the differential equation. We then allow the AI training machinery tooptimize the RNN weights to fit the data better. We illustrate the method on anexample of a time series of 10h-FMC from RAWS and weather data from theReal-Time Mesoscale Analysis (RTMA).

Building a Fuel Moisture Model for the Coupled Fire-Atmosphere Model WRF-SFIRE from Data: From Kalman Filters to Recurrent Neural Networks