文献类型： 外文期刊

作者： Wang, Zhuangji ¹ ; Hua, Shan ³ ; Timlin, Dennis ¹ ; Kojima, Yuki ⁴ ; Lu, Songtao ⁵ ; Sun, Wenguang ¹ ; Fleisher, David ¹ ; Horton, Robert ⁷ ; Reddy, Vangimalla R. ¹ ; Tully, Katherine ² ;

作者机构： 1.USDA ARS, Adapt Cropping Syst Lab, Beltsville, MD 20705 USA

2.Univ Maryland, Dept Plant Sci & Landscape Architecture, College Pk, MD USA

3.Zhejiang Acad Agr Sci, Inst Agr Equipment, Hangzhou, Peoples R China

4.Gifu Univ, Dept Civil Engn, Gifu, Japan

5.Thomas J Watson Res Ctr, IBM Res, Yorktown Hts, NY USA

6.Univ Nebraska, Nebraska Water Ctr, Lincoln, NE USA

7.Iowa State Univ, Dept Agron, Ames, IA USA

关键词： time domain reflectometry (TDR); soil relative permittivity (epsilon(r)); convolutional neural network (CNN); deep machine learning

期刊名称：WATER RESOURCES RESEARCH （ 影响因子：5.4； 五年影响因子：6.1 ）

ISSN： 0043-1397

年卷期： 2023 年 59 卷 2 期

页码：

收录情况： SCI

摘要： Interpreting time domain reflectometry (TDR) waveforms obtained in soils with non-uniform water content is an open question. We design a new TDR waveform interpretation model based on convolutional neural networks (CNNs) that can reveal the spatial variations of soil relative permittivity and water content along a TDR sensor. The proposed model, namely TDR-CNN, is constructed with three modules. First, the geometrical features of the TDR waveforms are extracted with a simplified version of VGG16 network. Second, the reflection positions in a TDR waveform are traced using a 1D version of the region proposal network. Finally, the soil relative permittivity values are estimated via a CNN regression network. The three modules are developed in Python using Google TensorFlow and Keras API, and then stacked together to formulate the TDR-CNN architecture. Each module is trained separately, and data transfer among the modules can be facilitated automatically. TDR-CNN is evaluated using simulated TDR waveforms with varying relative permittivity but under a relatively stable soil electrical conductivity, and the accuracy and stability of the TDR-CNN are shown. TDR measurements from a water infiltration study provide an application for TDR-CNN and a comparison between TDR-CNN and an inverse model. The proposed TDR-CNN model is simple to implement, and modules in TDR-CNN can be updated or fine-tuned individually with new data sets. In conclusion, TDR-CNN presents a model architecture that can be used to interpret TDR waveforms obtained in soil with a heterogeneous water content distribution.