STGCN-based flood forecast error real-time correction method and system

The invention discloses an STGCN-based flood forecast error real-time correction method and system. The method comprises the steps of constructing a forecast error real-time correction data set; preprocessing the forecast error real-time correction data set, extracting the flowing length from a rela...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG TAO, CHEN YUBIN, LI JIE, YU YUFENG, ZHANG JUN, TIAN YIFEI, ZENG MING, YAN FANGJIA, YANG YANFEI, ZHANG JING, ZHANG XIAO, REN YUFENG, QIN HAO, ZHENG JING, FENG BAOFEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention discloses an STGCN-based flood forecast error real-time correction method and system. The method comprises the steps of constructing a forecast error real-time correction data set; preprocessing the forecast error real-time correction data set, extracting the flowing length from a related rainfall station to a forecast section in forecast model input data, and constructing a spatial adjacency matrix; constructing a space-time diagram convolutional network model STGCN, extracting the time sequence and local space features of the error sequence, and constructing a mapping function reflecting the nonlinear relationship of the error sequence; performing parameter optimization by adopting an improved grey wolf optimization algorithm, and constructing an optimal AGWOSTGCN model; the prediction model M is used for predicting real-time data, the real-time error correction model AGWOSTGCN is used for predicting model prediction errors, and a final prediction value is obtained. The method has better predi