Soil Moisture Sensor Information Enhanced by Statistical Methods in a Reclaimed Water Irrigation Framework

Area of Science:

• Agricultural Science
• Environmental Science
• Data Science

Background:

• Understanding soil water content and salinity is crucial for water resource management and irrigation.
• Semi-arid environments face challenges with water scarcity and soil health, especially when using reclaimed water.

Purpose of the Study:

• To develop a 48-hour forecast model for soil water content and salinity.
• To assess the impact of reclaimed water irrigation on soil parameters in semi-arid conditions.

Main Methods:

• Utilized time series data of soil water content and salinity (15-min resolution) at 50 cm depth.
• Incorporated hourly atmospheric data and daily irrigation amounts into statistical models.
• Performed exploratory data analysis and pre-processing before model construction.

Main Results:

• Developed statistical models demonstrating good forecasting accuracy for soil water content and salinity.
• The models provided interpretable results, enhancing understanding of soil dynamics.
• Successfully forecasted soil parameters for a 48-hour period.

Conclusions:

• Time series modeling effectively predicts soil water content and salinity under reclaimed water irrigation.
• Accurate forecasting supports optimized irrigation and fertilization strategies in water-scarce regions.
• The study highlights the importance of integrated data for environmental and agricultural management.