[Eoas-seminar] REMINDER: Special Seminar TODAY 215PM EOA 3067

[eoas-seminar at lists.fsu.edu]

This is just a reminder of the special seminar today, by Professor Shoshiro Minobe, on seasonal prediction of tropical cyclones, at 215pm in EOA 3067. Please see below for details.

Snacks and drinks will be provided. See you then.

________________________________
From: Eoas-seminar <eoas-seminar-bounces at lists.fsu.edu> on behalf of eoas-seminar--- via Eoas-seminar <eoas-seminar at lists.fsu.edu>
Sent: Monday, October 23, 2023 11:42 PM
To: eoas-seminar--- via Eoas-seminar <eoas-seminar at lists.fsu.edu>
Subject: [Eoas-seminar] Special Seminar - Monday October 30th, Professor Shoshiro Minobe, Hokkaido University

Dear all,

Please join for a special short seminar on Monday October 30th, by Professor Shoshiro Minobe from Hokkaido University, Japan, on "Long-term Seasonal Prediction of Tropical Cyclones for East Asia with Machine Learning" (abstract below).

Shoshiro will be joining us in person here in EOAS and is available to meet throughout Monday - please contact me if you would like to meet with him.

DATE: Monday October 30
SEMINAR TIME: Talk 2:15 PM - 3:00 PM.
SEMINAR LOCATION: EOA 3067 (Speaker in person)
SPEAKER: Professor Shoshiro Minobe

TITLE: Long-term Seasonal Prediction of Tropical Cyclones for East Asia with Machine Learning

ABSTRACT: Of all the ocean basins, the western North Pacific (WNP) produces the largest number of tropical cyclones. Significant efforts have been made to predict seasonal tropical cyclone activity for countries or specific land areas in the WNP, which is a more challenging task than forecasting for the basin as a whole. Here, a new seasonal prediction of tropical cyclone activity for the countries of the WNP is presented using a machine learning method. Taking advantage of this machine learning method, ocean heat content is used as the predictor data. It is found that a statistically significant prediction can be made more than a half-year lead time for Japan and China.
Several climate modes in the Indian and Pacific Oceans contribute to the predictability, but rather than using climate mode indices, which are defined mainly using SSTs, prediction using subsurface temperatures exhibit better performance, highlighting the importance of exploiting the ocean's memory stored in the subsurface temperature.

------------------------------------------------
Rhys Parfitt
Assistant Professor, EOAS

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.fsu.edu/pipermail/eoas-seminar/attachments/20231030/b11101c9/attachment.html>
-------------- next part --------------
_______________________________________________
Eoas-seminar mailing list
Eoas-seminar at lists.fsu.edu
https://lists.fsu.edu/mailman/listinfo/eoas-seminar