Artificial intelligence-based fiber optic sensing for soil moisture measurement with different cover conditions. (January 2023)

• Record Type: Journal Article
• Authors: Liu, Xi-Feng; Zhu, Hong-Hu; Wu, Bing; Li, Jie; Liu, Tian-Xiang; Shi, Bin
• Is Part Of: Measurement. Volume 206(2023)
• Publication Date: 2023-01
• Subjects: Actively heated fiber optic (AHFO) -- Artificial neural network (ANN) -- Water content -- Fiber Bragg grating (FBG) -- Geotechnical monitoring; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2022.112312
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Cover conditions have a strong impact on the AH-FBG soil moisture measurements. Artificial neural network is used to correct water content monitoring errors. Four AH-FBG-ANN models can effectively improve monitoring accuracy. Abstract: Actively heated fiber Bragg grating (AH-FBG) can perform quasi-distributed monitoring of soil water content. However, the analysis method needs to be improved to minimize measuring errors. In this study, the artificial intelligence method is proposed and a model test was used to verify its feasibility and to explore the influence of cover conditions. Three cover layers were considered, including bare soil (S), grass (G), and biochar mixed soil (B). The water content measurements based on maximum temperature increase have higher accuracy for G, followed by S, and the worst is B. Fluctuation in the heat power and the longitudinal heat transfer are the main sources of errors. Artificial neural network (ANN) models can effectively improve monitoring accuracy. Cover conditions have a significant influence on the measurements by affecting initial ground temperatures and water content gradients. For field monitoring, the cover layer should be considered when analyzing AH-FBG measurements.