Correlation Analysis of Soil Moisture Content and Environmental Factors Based on LoRa-RSSI

Soil moisture content (SMC) is influenced by a variety of environmental factors. Recent studies have demonstrated that integrating LoRa-RSSI data with environmental parameters can enhance the accuracy of soil moisture predictions while reducing dependence on soil moisture sensors. However, the diversity of these environmental factors can also increase sensor costs. To analyze the impact of various environmental parameters on soil moisture and to identify key factors that assist RSSI in accurately predicting soil moisture, this study collected data on soil moisture, RSSI, and relevant environmental parameters—including ambient temperature, humidity, light intensity, and wind speed—from a field site in the Songjiang District of Shanghai. Utilizing statistical analysis tools, the study investigated the correlations between LoRa-RSSI data, various environmental factors, and SMC. The findings provide a novel approach to data collection and analysis for employing deep learning techniques to predict soil moisture, offering valuable insights for soil moisture measurement in the Shanghai region.