The rugged geographical relief of Peru determines a particular hydrological regime; this includes our Region, which is also under the effect of meteorological phenomena such as El Niño and La Niña that occur unpredictably and whose effects we feel with heavy rains ans floods in the north of Peru, for which we consider essential to be able to forecast river levels, in particular the river La Leche, for this we use the Black-Sholes-Merton stochastic differential equation of the river level, as an input along with other parameters mesaured by meteorological stations within the area of influence of the La Leche river basin, together with an LSMT Neural Network that was trained with data downloaded but conditioned, making forecasts 6, 12, 18 and 24 hours in advance. The performance tests of the obtained neural networks demostrated a high adaptation of the solution to the hydrological model since the NSE is very close to unity; Besides that, the average error is minimal, RMSE of the order of 0.002, and the absolute error is of the order of 0.007.
|Title of host publication||Proceedings of the 2021 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2021|
|Editors||Manuel Cardona, Vijender Kumar Solanki|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|State||Published - 2021|
|Event||2021 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2021 - Virtual, Soyapango, El Salvador|
Duration: 16 Dec 2021 → 17 Dec 2021
|Name||Proceedings of the 2021 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2021|
|Conference||2021 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2021|
|Period||16/12/21 → 17/12/21|
Bibliographical notePublisher Copyright:
© 2021 IEEE.
- Multilayer perceptron and deep learning
- River level forecast
- long short-term memory (LSTM) Network
- weather station data