Water flow prediction method and device based on machine learning and electronic equipment

Abstract

The invention discloses a water flow prediction method and device based on machine learning, and electronic equipment. The method comprises the steps of obtaining original rainfall data and original flow data of a predetermined drainage basin; carrying out preprocessing to obtain processed rainfall data and processed flow data respectively; constructing input data based on the processed rainfall data, the processed flow data and the known rainfall data of each hydrological station in the future P hours; inputting the input data into a pre-trained flood flow prediction model to perform loop iteration prediction, extracting time sequence features from the input data of the iteration and performing classification prediction during each iteration to obtain a flow prediction value of the targethydrological station in the next hour, and using the obtained flow prediction value in the next hour to reconstruct input data for iteration of the next hour in the future until P times of iterationare completed, and thus obtaining a flow prediction value of the target hydrological station in the next P hours; according to the invention, the flood flow condition in a future time period can be accurately predicted.

Description

technical field [0001] The invention belongs to the field of flood forecasting, and in particular relates to a water flow forecasting method, device and electronic equipment based on machine learning. Background technique [0002] Floods are one of the common natural disasters. Hundreds of millions of people are affected by floods and displaced every year, and the financial and material losses caused by floods are also huge. Effectively predicting flood flow and issuing early warnings is of great significance for flood control and disaster reduction. [0003] The current flood flow forecasting models are mainly divided into traditional physical models and intelligent flood forecasting models. Traditional physical models, such as the Xin'anjiang model, calculate the parameters of the physical process on the premise of fully mining the physical characteristics of the local topography, evaporation, and vegetation coverage, and finally formulate a set of regionally specific pre...

AI Technical Summary

Problems solved by technology

[0004] However, most of the existing flood flow forecasting models belong to single-point forecasting, that is, predicting the flow situation at a point in time in the future. In actual situations, the flow data obtained at a single point in time from the prediction lacks practical application value.

Images