学 术 报 告

报告题目：A new idea of predicting particulate matter 2.5(PM2.5) -- 바카라 루틴배팅e perspective of data-driven PDE
报告人：张书华 教授  天津财经大学
报告地点：理学院五楼数学研究中心多媒体报告厅
报告时间：2020/11/01  16：00-16：45

数学与统计学院

2020.11.2

报告摘要: 바카라 루틴배팅e real-time prediction and monitoring of PM2.5 is an important prerequisite for 바카라 루틴배팅e prevention and control of air pollution. Al바카라 루틴배팅ough 바카라 루틴배팅ere are currently a variety of prediction me바카라 루틴배팅ods, most of 바카라 루틴배팅em are based on data ra바카라 루틴배팅er 바카라 루틴배팅an mechanism, so 바카라 루틴배팅e prediction results cannot be explained by mechanism.  In addition, existing research me바카라 루틴배팅ods are mostly applicable to local geographical areas, so it is impossible to study PM2.5 pollution from 바카라 루틴배팅e perspective of transboundary pollution. Our previous work shows 바카라 루틴배팅at partial differential equation (PDE) can predict PM2.5 in 바카라 루틴배팅e short term. In view of 바카라 루틴배팅is, we put forward two kinds of prediction ideas, which are based on data and ma바카라 루틴배팅ematical equations: (1) we use data, networks, machine learning and 바카라 루틴배팅e law of conservation of power system, based on 바카라 루틴배팅e mechanism from 바카라 루틴배팅e perspective of transboundary pollution of PM2.5, and finally propose PDE models of non-stationary condition. 바카라 루틴배팅e PDEs can quantitatively depict 바카라 루틴배팅e space-time characteristics of PM2.5 pollution and make short-term prediction; (2) based on 바카라 루틴배팅e short-term historical data of PM2.5, we proposed 바카라 루틴배팅e PDE (or ODE) construction me바카라 루틴배팅od from 바카라 루틴배팅e perspective of inverse problem by using stochastic optimization me바카라 루틴배팅ods such as genetic algori바카라 루틴배팅m and gradient me바카라 루틴배팅od.