Soil Moisture Sensing with UAV-Mounted IR-UWB Radar and Deep Learning

Abstract

Wide-area soil moisture sensing is a key element for smart irrigation systems. However, existing soil moisture sensing methods usually fail to achieve both satisfactory mobility and high moisture estimation accuracy. In this paper, we present the design and implementation of a novel soil moisture sensing system, named as SoilId, that combines a UAV and a COTS IR-UWB radar for wide-area soil moisture sensing without the need of burying any battery-powered in-ground device. Specifically, we design a series of novel methods to help SoilId extract soil moisture related features from the received radar signals, and automatically detect and discard the data contaminated by the UAV's uncontrollable motion and the multipath interference. Furthermore, we leverage the powerful representation ability of deep neural networks and carefully design a neural network model to accurately map the extracted radar signal features to soil moisture estimations. We have extensively evaluated SoilId against a variety of real-world factors, including the UAV's uncontrollable motion, the multipath interference, soil surface coverages, and many others. Specifically, the experimental results carried out by our UAV-based system validate that SoilId can push the accuracy limits of RF-based soil moisture sensing techniques to a 50% quantile MAE of 0.23%.

Design of 6 GHz Variable-Gain Low-Noise Amplifier Using Adaptive Bias Circuit for Radar Receiver Front End

“…From (5), P in and P c are in the same variation, and an increase in P in leads to an increase in V R as a result of the AC-DC converting process of the rectifier [15]. The DC inverse source V i then generates V G with the following relation:…”

“…Therefore, a mechanism of gain control is necessary in the LNA design to achieve both these two objectives simultaneously, which cannot be solved with the common fixed-gain LNAs. In addition, in the case of sensing platforms, variable-gain LNAs (VGLNAs) research is essential because gain problems may occur depending on distance [4][5][6].…”

Proposed Speedy Moisture Test Calibration Chart on Indonesian Road Embankments

“…Several countries have paid attention to this topic and conducted research, especially about device effectiveness comparison for determining field soil moisture content, like Austin [15], the United States [16], and Washington D.C. America [17]. A couple of methods available have recently become popular to estimate moisture content by using machine learning [18] or deep learning [19]. However, the speedy moisture test (SMT) has become Indonesia's most popular tool for measuring field water content.…”