This study aimed to develop a deep neural network model for predicting the soil water content and bulk density of soil based on features extracted from in situ soil surface images. Soil surface images were acquired using a Canon EOS 100d camera. The camera was installed in the vertical direction above the soil surface layer. To maintain uniform illumination conditions, a dark room and LED lighting were utilized. Following the acquisition of soil surface images, soil samples were collected using a metal cylinder to obtain measurements of soil water content and bulk density. Various features were extracted from the images, including color, texture, and shape features, and used as inputs for both a multiple regression analysis and a deep neural network model. The results show that the deep neural network regression model can predict soil water content and bulk density with root mean squared error of 1.52% and 0.78 kN/m³. The deep neural network model outperformed the multiple regression analysis, achieving a high accuracy for predicting both soil water content and bulk density. These findings suggest that in situ soil surface images, combined with deep learning techniques, can provide a fast and reliable method for predicting important soil properties.

For appropriate managing fields and crops, it is essential to understand soil properties. There are drawbacks to the conventional methods currently used for collecting a large amount of data from agricultural lands. Convolutional neural network is a deep learning algorithm that specializes in image classification, and developing soil property prediction techniques using this algorithm will be extremely beneficial to soil management. We present the convolution neural network models for estimating water content and dry density using soil surface images. Soil surface images were taken with a conventional digital camera. The range of water content and dry density were determined considering general upland soil conditions. Each image was divided into segmented images and used for model training and validation. The developed model confirmed that the model can learn soil features through appropriate image argumentation of few of original soil surface images. Additionally, it was possible to predict the soil water content in a situation where various soil dry density conditions were considered.

The objective of this study is to monitor the water content of soil quickly and accurately using a UAV. Because UAVs have higher spatial and temporal resolution than satellites, they are currently becoming more useful in remote sensing areas. We developed a water content estimation equation using the color of the soil and suggested a calibration method for field application. Since the resolution of the images taken by the UAV is different according to the altitude, the water content estimation formula is developed by using the images taken at each altitude. In order to calibrate the color difference according to lighting conditions, the calibration method using field data were proposed. The results of the study showed an altitude‐specific estimation equation using RGB values of the UAV image through linear regression. The appropriate number of field data needed for calibration for site application of the estimation equation was found between 4 and 10. On‐site application results of the proposed calibration method showed RMSE accuracy of 1.8 to 2.9%. Thus, the water content estimation and calibration method proposed in this study can be used in effectively monitoring the water content of soil using UAVs.

Digital image processing (DIP) is used to measure shape properties and settling velocity of soil particles. Particles with diameters of 1 to 10 mm are arbitrarily sampled for the test. The size of each particle is also measured by a Vernier caliper for comparison with the classification results using the shape classification table. The digital images were taken with a digital camera (Canon EOS 100d). Shape properties are calculated by image analysis software. Settling velocity of soil particles is calculated by displacement and time difference of images during settling. The fastest settling particles are spherical shaped. Shape factors well explain the difference of settling velocity by a particle shape. In particular, the aspect ratio has a high negative correlation with residual of settling velocity versus mean diameter. Especially, DIP has a higher applicability than classification using the shape classification table because it can measure a number of particles at once. The settling velocity of soil particles is expressed as a function of mean diameter and aspect ratio.

In probabilistic slope stability analysis, soil depth has been treated as a deterministic variable, although it is a highly variable parameter. This study aims to identify soil depth variability using seismic refraction survey data and to analyze its impact on probabilistic analysis of slope stability. Seismic refraction survey data were collected from 70 slopes in South Korea and employed to identify the variability of soil depth within natural slopes. As a result, the average soil depth across 70 slopes was 2.5 m, with an average coefficient of variation (COV) of 29%, indicating high variability. To investigate the influence of soil depth variability on the probability of slope failure, probabilistic slope stability analysis was conducted by considering the shear strength parameters of soil and soil depth as random variables. Accordingly, the influences of the variability of soil depth on the probabilistic analysis of slope stability were evaluated by comparing the probability of slope failure and distribution of the failure occurrence frequency by depth. Additionally, global sensitivity analysis was conducted to understand the relative contribution of input parameters on the probability of slope failure. Consequently, the probability of slope failure can vary significantly depending on soil depth variability, emphasizing the importance of considering this factor in probabilistic slope stability analysis.