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

Dangerous large wave put the coastal communities and vessels operating underthreats and wave predictions are strongly needed for early warnings. Whilenumerical wave models, such as WAVEWATCH III (WW3), are useful to providespatially continuous information to supplement in situ observations, however,they often require intensive computational costs. An attractive alternative ismachine-learning method, which can potentially provide comparable performanceof numerical wave models but only requires a small fraction of computationalcosts. In this study, we applied and tested a novel machine learning methodbased on XGBoost for predicting waves in Lake Erie in 2016-2017. In this study,buoy data from 1994 to 2017 were processed for model training and testing. Wetrained the model with data from 1994-2015, then used the trained model topredict 2016 and 2017 wave features. The mean absolute error of wave height isabout 0.11-0.18 m and the maximum error is 1.14-1.95 m, depending on locationand year. For comparison, an unstructured WW3 model was implemented in LakeErie for simulating wind generated waves. The WW3 results were compared withbuoy data from National Data Buoy Center in Lake Erie, the mean absolute errorof wave height is about 0.12-0.48 m and the maximum error is about 1.03-2.93 m.The results show that WW3 underestimates wave height spikes during strong windevents and The XGBoost improves prediction on wave height spikes. The XGBoostruns much faster than WW3. For a model year run on a supercomputer, WW3 needs12 hours with 60 CPUs while XGBoost needs only 10 minutes with 1 CPU. Insummary, the XGBoost provided comparable performance for our simulations inLake Erie wave height and the computational time required was about 0.02 % ofthe numerical simulations.

Predicting Lake Erie Wave Heights using XGBoost