Author(s): Takuya Matsumoto; Yusuke Hiraga; Shunsuke Aita

Linked Author(s):

Keywords: Soil moisture; Machine Learning; UAV; Viticulture

Abstract: This study utilized the UAV multispectral imagery and machine learning algorithms to estimate time series and spatial distribution of soil moisture content at vineyards. This study focused on the vineyard of ~3.3 ha with steep slope in Miyagi, Japan (Ryomi Vineyard & Winery). We first measured the soil moisture content at the selected 55 sites using TDR (Time Domain Reflectometry). Then the measurements were augmented to 5,500 pixels of the UAV imagery. Based on such large number of samples, the random forest algorithm was developed to estimate the spatial distribution of soil moisture content with high resolution, resulting in the high accuracy of estimation over the vineyard (R2=0.96). We also developed a random forest model to estimate the daily variation of soil moisture content based on the observed temperature, rainfall, and irradiance. Although the time series prediction model was able to roughly capture the daily variation of soil moisture content, the large variation was not hindcasted well, which needs to be addressed in future studies.

DOI: https://doi.org/10.64697/978-90-835589-7-4_41WC-P1971-cd

Year: 2025