摘要：Core Ideas We evaluated approaches based on machine learning and soil water dynamic principles. We compared automated analysis of soil moisture sensor time series for estimating field capacity. Approaches accurately estimated field capacity compared with expert values. Automated approaches needed to leverage temporally dynamic field capacity. Vadose zone measurements of volumetric soil water content (θ) using soil moisture sensors (SMSs) have become more common due to advances in technology and reduction of costs. Soil moisture sensor data exhibit a characteristic cyclical pattern reflecting water flux dynamics into and out of the observed soil volume. Expert review of SMS datasets to distinguish valid from corrupt or incomplete soil water cycles is arguably the most precise method for determining field capacity (θ FC ) but is impractically cumbersome and time consuming for increasingly large SMS datasets. We evaluated competing approaches for automated soil water cycles analysis that use widely available R packages based on pattern recognition and machine learning ( findpeaks [R‐FP], symbolic aggregate approximation [R‐SAX], and density histogram [R‐DH]), and a MATLAB code based on soil water dynamic principles (SWDP). These approaches were applied to three SMS datasets. Our empirical results showed superiority of R‐SAX for identifying valid soil water cycles, probably due to benefiting from training sets to calibrate to correct cycles. Two other approaches (SWDP and R‐FP) provided similar results without need of training sets or preprocessing data. Three approaches for estimating field capacity were applied to valid cycles, R‐FP, regression of exponential decay (SWDP‐R), and estimated “knee” of curve (SWDP‐K). Each performed similarly to the expert defined values, with R‐FP and SWDP‐R generally performing best across analyses. Results of this study also show temporal dynamics of θ FC within datasets used here. There is potential for optimizing θ FC and a need for automated, objective analysis to leverage dynamics in irrigation management and modeling.
关键词：CCS; citrus grower orchard with conventional irrigation scheduling; ET; evapotranspiration; MAD; maximum allowable depletion; R-DH; density histogram in R; R-FP; R package findpeaks; R-SAX; symbolic aggregate approximation in R; SAX; symbolic aggregate approximation; SMS; soil moisture sensor; SWDP; soil water dynamic principles; SWDP-K; “knee” of curve for estimating field capacity; SWDP-R; regression of exponential decay for estimating field capacity; TCS; turfgrass with conventional irrigation scheduling; TET; turfgrass with evapotranspiration controller.
