In order to cope with the situation where the frequency and severity of floods have been increasing in recent years

[

1

1

]

. Based on the hydrological data monitored by the Lijin Hydrological Station of the Yellow River and the China Water Pattern Data Center

this paper uses the traditional neural network model as the benchmark model

[

2

2

]

then prunes the model to reduce the channels

and establishes a convolutional neural network mode to predict the flood occurrence probability

[

3

3

]

. Finally

it compares the prediction accuracy with that of the traditional neural network model

calculates the accuracy indicators

and judges the adaptability and stability of the model. The convolutional neural network model exhibits superior performance in predicting the probability of flood occurrence compared to the traditional neural network model. Compared with the traditional neural network model

the MSE of this model has decreased by 81.04%

the

<math id="M1"><mi mathvariant="normal">R</mi><mi mathvariant="normal">M</mi><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=79447957&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=79448011&type=

7.36600018

2.37066650

has decreased by 56.58%

and

<math id="M2"><msup><mrow><mi mathvariant="normal">R</mi></mrow><mrow><mn mathvariant="normal">2</mn></mrow></msup></math>

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=79448005&type=

https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=79448004&type=

2.70933342

2.28600001

has increased by 0.665. Therefore

he adoption of convolutional neural network model can effectively enhance the prediction performance of neural networks. Compared with the traditional neural network model

the convolutional neural network model performs better in the accuracy of flood prediction and is more adaptable in flood prevention and disaster reduction work.