Monitoring of Irrigation Channel Discharge Based on IoT and LoRaWAN Communication with Long Short-Term Memory (LSTM) Predictive Analysis

Toga Aldila Cinderatama (Politeknik Negeri Malang)
Afta Ramadhan Zayn (Politeknik Negeri Malang, 5)Politeknik Negeri Semarang, Indonesia)
Rinanza Zulmy Alhamri (Politeknik Negeri Malang, 5)Politeknik Negeri Semarang, Indonesia)
Yoppy Yunhasnawa (Politeknik Negeri Malang, 5)Politeknik Negeri Semarang, Indonesia)
Kenneth Pinandhito (Politeknik Negeri Semarang, Indonesia)

Sinkron : Jurnal dan Penelitian Teknik Informatika
Vol. 10 No. 3 (2026): Article Research July 2026

This study presents the design and implementation of an Internet of Things (IoT)-based irrigation canal monitoring system that integrates Long Range Wide Area Network (LoRaWAN) communication with a Long Short-Term Memory (LSTM) prediction model. The system is designed to provide real-time monitoring and prediction of water discharge in irrigation canals to support efficient water resource management on agricultural land. The proposed system consists of two IoT sensor nodes, each equipped with a YF-B5 flow sensor, an HC-SR04 ultrasonic sensor, and a DS18B20 temperature sensor, all connected to an ESP32 microcontroller. The collected data are transmitted via the LoRaWAN protocol and stored in Firebase Realtime Database, where they are visualized through an Android application. The predictive component employs an LSTM algorithm to forecast future water discharge based on historical time-series data. Experimental results indicate that the LSTM model achieved a Mean Absolute Error (MAE) of 13.1640 and a Root Mean Squared Error (RMSE) of 23.0630, demonstrating high accuracy and stability in predicting water discharge fluctuations. The integration of IoT, LoRaWAN, and LSTM-based prediction enables real-time monitoring and predictive analysis for smart irrigation management.