El pronóstico preciso de los niveles de agua del Lago Titicaca (NALT) es esencial para la seguridad y la gestión eficiente de los recursos hídricos, especialmente en condiciones climáticas extremas. El objetivo de la investigación fue desarrollar modelos de Redes Neuronales Recurrentes (RNN) de memoria a corto y largo plazo (LSTM) para pronosticar niveles de agua a nivel diario y mensual, utilizando diferentes ventanas de tiempo. Se evaluaron los modelos utilizando métricas comunes en recursos hídricos, como el error cuadrático medio (RMSE), la eficiencia de Nash-Sutcliffe (NSE), la eficiencia de Kling-Gupta (KGE) y el sesgo porcentual (PBIAS). Para pronósticos diarios, la ventana de tiempo más efectiva fue de 1 día, con un RMSE de 0.0080 metros y un NSE de 0.9996. Para pronósticos mensuales, la mejor ventana de tiempo fue de 12 meses, con un RMSE de 0.103 metros y un NSE de ...

La presente investigación se realizó en la cuenca del río Ramis, ubicado en la región hidrográfica del Titicaca, Perú, con el objetivo de calibrar y validar el modelo hidrológico Sacramento (SAC-SMA) desde un enfoque semidistribuido. La información hidrometeorológica utilizada de precipitación pluvial, temperatura y caudal, corresponden a una serie de registro 2005 – 2016. La metodología de interpolación espacial de datos meteorológicos en la estación virtual, fue estimada mediante el procedimiento de Shepard y la evapotranspiración potencial por el modelo de Turc, estas metodologías vienen incorporados en la plataforma RS-MINERVE y son estimaciones automatizadas. La fase de calibración y validación del modelo, se realizó de forma aleatoria con el 70% y 30% del total de datos respectivamente. La evaluación estadística de eficiencia y error fueron medidos a través ...

The present research was held in the basin of the river Ramis, located in the hydrographic region of Titicaca, Peru, with the objective of calibrating and validating the Sacramento hydrological model (SAC-SMA) from a semi-distributed approach. The hydrometeorological information used for rainfall, temperature and flow, correspond to a series of records 2005 - 2016. The methodology of spatial interpolation of meteorological data in the virtual station was estimated using the Shepard procedure and potential evapotranspiration by the model Turc, these methodologies are incorporated in the RSMINERVE platform and are automated estimates. The calibration and validation phase of the model was performed randomly with 70% and 30% of the total data respectively. The statistical evaluation of efficiency and error were measured by the Nash coefficient, Nash coefficient for logarithm values and r...

The present research was held in the basin of the river Ramis, located in the hydrographic region of Titicaca, Peru, with the objective of calibrating and validating the Sacramento hydrological model (SAC-SMA) from a semi-distributed approach. The hydrometeorological information used for rainfall, temperature and flow, correspond to a series of records 2005 - 2016. The methodology of spatial interpolation of meteorological data in the virtual station was estimated using the Shepard procedure and potential evapotranspiration by the model Turc, these methodologies are incorporated in the RSMINERVE platform and are automated estimates. The calibration and validation phase of the model was performed randomly with 70% and 30% of the total data respectively. The statistical evaluation of efficiency and error were measured by the Nash coefficient, Nash coefficient for logarithm values and r...

The present research was held in the basin of the river Ramis, located in the hydrographic region of Titicaca, Peru, with the objective of calibrating and validating the Sacramento hydrological model (SAC-SMA) from a semi-distributed approach. The hydrometeorological information used for rainfall, temperature and flow, correspond to a series of records 2005 - 2016. The methodology of spatial interpolation of meteorological data in the virtual station was estimated using the Shepard procedure and potential evapotranspiration by the model Turc, these methodologies are incorporated in the RSMINERVE platform and are automated estimates. The calibration and validation phase of the model was performed randomly with 70% and 30% of the total data respectively. The statistical evaluation of efficiency and error were measured by the Nash coefficient, Nash coefficient for logarithm values and r...

The present research was held in the basin of the river Ramis, located in the hydrographic region of Titicaca, Peru, with the objective of calibrating and validating the Sacramento hydrological model (SAC-SMA) from a semi-distributed approach. The hydrometeorological information used for rainfall, temperature and flow, correspond to a series of records 2005 - 2016. The methodology of spatial interpolation of meteorological data in the virtual station was estimated using the Shepard procedure and potential evapotranspiration by the model Turc, these methodologies are incorporated in the RSMINERVE platform and are automated estimates. The calibration and validation phase of the model was performed randomly with 70% and 30% of the total data respectively. The statistical evaluation of efficiency and error were measured by the Nash coefficient, Nash coefficient for logarithm values and r...