Water Level Prediction Model Based on GRU and CNN

With the aim of accurately predicting river water levels a few hours ahead in the event of a flood, we created a river water level prediction model consisting of a runoff model, a channel model, and data assimilation technique. We also developed a cascade assimilation method that allows us to calculate assimilations of water levels observed at multiple points using particle filters in real-time. As a result of applying the river water level prediction model to Arakawa Basin using the assimilation technique, it was confirmed that reproductive simulations that produce results very similar to the observed results could be achieved, and that we would be able to predict river water levels less affected by the predicted amount of rainfall.

Download Full-text

Water level prediction model using back propagation neural network: Case study: The lower of chao phraya basin

2016 4th International Symposium on Computational and Business Intelligence (ISCBI) ◽

10.1109/iscbi.2016.7743284 ◽

2016 ◽

Cited By ~ 1

Author(s):

Panjaporn Truatmoraka ◽

Narongrit Waraporn ◽

Dhanasite Suphachotiwatana

Keyword(s):

Neural Network ◽

Prediction Model ◽

Water Level ◽

Back Propagation ◽

Back Propagation Neural Network ◽

Water Level Prediction

Download Full-text

MODEL PREDIKSI LEVEL AIR DI LAHAN PERKEBUNAN KELAPA SAWIT DENGAN JARINGAN SARAF TIRUAN BERDASARKAN PENGUKURAN SENSOR RAIN GAUGE DAN ULTRASONIK

Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering) ◽

10.23960/jtep-l.v10i1.104-112 ◽

2021 ◽

Vol 10 (1) ◽

pp. 104

Author(s):

Hasan Al Banna ◽

Bayu Dwi Apri Nugroho

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Prediction Model ◽

Water Level ◽

Rain Gauge ◽

Water Levels ◽

Weather Station ◽

Automatic Weather Station ◽

Artificial Neural ◽

Water Level Prediction

Monitoring and regulating water levels in oil palm swamps has an essential role in providing sufficient water for crops and conserving the land to not easily or quickly deteriorate. Presently, water level is still manual and has weaknesses, one of which is the accuracy of the data taken depending on the observer. Technology such as sensors integrated with artificial neural network is expected to observe and regulate water levels. This study aims to build a prediction model of water levels in oil palm plantations with artificial neural networks based on the rain gauge and ultrasonic sensors installed on Automatic Weather Station (AWS). The obtained results showed that the prediction model runs well with an R2 value of 0,994 and RMSE 1,16 cm. The water level prediction model in this research then tested for accuracy to prove the model's success rate. Testing the water level prediction model's accuracy in the dry season obtained an R2 value of 0,96 and an RMSE of 1,99 cm. Testing the water level prediction model's accuracy in the rainy season obtained an R2 value of 0,85 and an RMSE value of 4,2 cm. Keywords : artificial neural network, automatic weather station, palm oil, water level

Download Full-text