Sensor Integration and ARIMA-Based Forecasting in WAQMS for Environmental Monitoring in Riau Province, Indonesia

Abstract

Purpose: This study aims to develop an integrated solution for real-time environmental monitoring in Riau Province, Indonesia, where air and water quality are increasingly impacted by industrial, agricultural, and climatic factors. Existing monitoring systems are often limited by their lack of real-time capabilities and predictive analytics.

Methods: To address this, we designed the Water and Air Quality Monitoring System (WAQMS), which integrates sensor-based data acquisition with the Autoregressive Integrated Moving Average (ARIMA) model for forecasting. Sensor units were deployed across three pilot locations—Kampar, Siak, and Pekanbaru—to continuously collect environmental data. The ARIMA model was applied to historical datasets to predict future trends in air and water quality, while a web-based dashboard was developed to visualize real-time data and forecasts.

Result: Calibration results showed a system accuracy of 85%, surpassing the national threshold of 75% set by the Indonesian Ministry of Environment and Forestry. This validates the use of WAQMS for Air Pollution Standard Index (ISPU) classification.

Novelty: The novelty of this study lies in the seamless integration of AQMS and WQMS within a unified predictive monitoring system, combined with a user-friendly interface for stakeholders. The results demonstrate the system's potential as a decision-support tool for local governments, offering timely insights and enabling more effective and sustainable environmental management.