Slope Micrometeorological Analysis and Prediction Based on an ARIMA Model and Data-Fitting System.

Area of Science:

• Civil Engineering
• Environmental Science
• Meteorology

Background:

• Highway engineering advancements necessitate robust slope stability solutions.
• Long-term monitoring of high-slope micrometeorology is crucial for ecological and economic sustainability.
• Existing monitoring methods face challenges in cost-effectiveness and predictive accuracy.

Purpose of the Study:

• To design and implement an innovative slope micrometeorological monitoring and predicting system (SMMPS).
• To enhance existing cloud platform systems with advanced data-fitting and prediction capabilities.
• To improve the timely protection of slopes against severe weather events and ensure infrastructure safety.

Main Methods:

• Development of a novel SMMPS integrating sensor-based data collection.
• Implementation of a data-fitting system to correlate atmospheric and slope micrometeorological data.
• Integration of an Autoregressive Integrated Moving Average (ARIMA) prediction model for trend forecasting.

Main Results:

• The SMMPS successfully integrates sensor data (soil temperature/humidity, slope temperature/humidity, rainfall).
• The data-fitting system effectively links atmospheric conditions with slope micrometeorology.
• ARIMA prediction accurately forecasts trends, enabling proactive slope protection measures.

Conclusions:

• The upgraded SMMPS offers a cost-effective solution for long-term slope monitoring.
• The system significantly enhances slope stability and protects vegetation from weather damage.
• The SMMPS improves the overall safety and reliability of rail and road infrastructure projects.