• Journal of Biosystems Engineering
• /
• v.34 no.5
• /
• pp.297-304
• /
• 2009

This study was conducted to investigate the adequacy of the representative empirical models which are developed for predicting the tractive performance of the tractor operating in various soil conditions. Four representative empirical models which are widely used in the traction prediction of tractor were selected through literature review. Four models were Wismer-Luth, Brixius, Dwyer and Hernandez model, which were empirical traction models of a single wheel. The efficacy of four models were confirmed via comparison of the tractions of tractor predicted using the four models with those measured from traction tests which were conducted for two different driving type (2WD and 4WD) of the tractor on two different soil conditions. The results showed that tractions predicted by Brixius' model, especially for slip range under 20% which the operating efficiency of a tractor is very high, were well consistent with the ones measured from traction test better than the tractions predicted by models which are proposed by Wismer-Luth, Dwyer and Hernandez.

• Proceedings of the Korea Society of Environmental Toocicology Conference
• /
• 2003.05a
• /
• pp.149-149
• /
• 2003

To understand environmental paths of the transport and accumulation of endocrine disrupting chemicals (EDCs), a single cell multimedia fate model has been constructed and evaluated. The EDCs of concern were PAHs, Organochlorine Pesticides (OCPs), PCBs, Alkyl phenols, and phthalates. An evaluation model was designed for the multimedia distribution, including air, water, soil, sediment and vegetation. This model was verified using reported values and via monitoring data. Based on collected data, the distribution trends of EDCs with respect to environmental media were analyzed. Those results have applied to the model for the prediction of the spatial and temporal distribution of EDCs in Seoul. Especially, phenol compound, phthalates, PAHs, PCBs and organochlorine pesticides were estimated and the model was verified. This model was successfully conducted to environmental media, such as air (vapor and suspended particles), soils (forest soil, bare soil, and cement-concrete covered soil), water (dissolved and suspended solids), sediment, trees (deciduous and coniferous). The discrepancies between the model prediction and the measured data are approximately within or near a factor of 10 for the PAHs of three rings through that of six rings, implying that multimedia distribution of the PAHs could be predicted with a factor of 10. Concerning about the air equilibrium may be assumed, a fugacity at steady state is similar in all environmental media. Considering the uncertainties of this model, the use of equilibrium models may be sufficient for assessing chemical fates. In this study, a suggestion was made that modeling and estimation of chemicals in environmental multimedia be rigorously evaluated using the measured flux data. In addition, these data should be obtained, for example, from the precise and standardized inventory of the target chemicals. The model (EDC Seoul) will be refined in an on-going research effort and will be used to support decision-making concerning the management of EDCs.

• Economic and Environmental Geology
• /
• v.56 no.3
• /
• pp.331-341
• /
• 2023

When creating a soil contamination map using geostatistical techniques, there are various sources that can affect prediction errors. In this study, a grid-based soil contamination map was created from the sampling data of heavy metal concentrations in soil in abandoned mine areas using Ordinary Kriging. Five factors that were judged to affect the prediction error of the soil contamination map were selected, and the variation of the root mean squared error (RMSE) between the predicted value and the actual value was analyzed based on the Leave-one-out technique. Then, using a machine learning algorithm, derived the top three factors affecting the RMSE. As a result, it was analyzed that Variogram Model, Minimum Neighbors, and Anisotropy factors have the largest impact on RMSE in the Standard interpolation. For the variogram models, the Spherical model showed the lowest RMSE, while the Minimum Neighbors had the lowest value at 3 and then increased as the value increased. In the case of Anisotropy, it was found to be more appropriate not to consider anisotropy. In this study, through the combined use of geostatistics and machine learning, it was possible to create a highly reliable soil contamination map at the local scale, and to identify which factors have a significant impact when interpolating a small amount of soil heavy metal data.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.357-360
• /
• 2005

Soil loss is widely recognized as a threat to farm livelihoods and ecosystem integrity worldwide. Soil loss prediction models can help address long-range land management planning under natural and agricultural conditions. Even though it is hard to find a model that considers all forms of erosion, some models were developed specifically to aid conservation planners in identifying areas where introducing soil conservation measures will have the most impact on reducing soil loss. Revised Universal Soil Loss Equation (RUSLE) computes the average annual erosion expected on hillslopes by multiplying several factors together: rainfall erosivity (R), soil erodibility (K), slope length and steepness (LS), cover management (C), and support practice (P). The value of these factors is determined from field and laboratory experiments. This study calculated soil erosion using GIS-based RUSLE model in Imha basin and examined soil erosion source area using SPOT 5 high-resolution satellite image and land cover map. As a result of analysis, dry field showed high-density soil erosion area and we could easily investigate source area using satellite image. Also we could examine the suitability of soil erosion area applying field survey method in common areas (dry field & orchard area) that are difficult to confirm soil erosion source area using satellite image.

• Journal of Soil and Groundwater Environment
• /
• v.21 no.3
• /
• pp.21-34
• /
• 2016

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

• Coupled systems mechanics
• /
• v.7 no.1
• /
• pp.27-42
• /
• 2018

Behavior of soil is usually described with continuum type of failure models such as Mohr-Coulomb or Drucker-Prager model. The main advantage of these models is in a relatively simple and efficient way of predicting the main tendencies and overall behavior of soil in failure analysis of interest for engineering practice. However, the main shortcoming of these models is that they are not able to capture post-peak behavior of soil nor the corresponding failure modes under extreme loading. In this paper we will significantly improve on this state-of-the-art. In particular, we propose the use of a discrete beam lattice model to provide a sharp prediction of inelastic response and failure mechanisms in coupled soil-foundation systems. In the discrete beam lattice model used in this paper, soil is meshed with one-dimensional Timoshenko beam finite elements with embedded strong discontinuities in axial and transverse direction capable of representing crack propagation in mode I and mode II. Mode I relates to crack opening, and mode II relates to crack sliding. To take into account material heterogeneities, we determine fracture limits for each Timoshenko beam with Gaussian random distribution. We compare the results obtained using the discrete beam lattice model against those obtained using the modified three-surface elasto-plastic cap model.

• Journal of Korean Society of Water and Wastewater
• /
• v.18 no.1
• /
• pp.66-72
• /
• 2004

In this study, quantity and quality of collected rainwater by sand, gravel, soil, lawn and concrete surface, as collection materials were investigated and Rainwater Collection Prediction Model was developed to predict the amount of collected rainwater. The quantity of collected rainwater in concrete surface, gravel, sand, soil and lawn collection system was 1,067L(93.2%), 1,006L(87.8%), 902L(78.8%), 800L(69.9%), 788.5L(68.8%) for 8 months period, respectively. The average turbidity of collected rainwater in concrete surface, gravel, sand, soil and lawn collection system was 3.2NTU, 2.2NTU, 1.9NTU, 1.7NTU, 1.5NTU for 8 months period, respectively. For sand collection material, predicted amount by the Model and actual collected amount were 931.5L and 902L, which were very closed. For gravel collection material, predicted amount by Model and actual collected amount were 1,028.21. and 1,006L, which were very closed. To simulate the optimal rainwater storage volume, the rainfall and evaporation data in Dae-jeon city were used. For sand collection system with 30m2 area, the maximum storage volume was $17m^3$ and 62% of the year was secured for use of 240L/day.

• Journal of Korean Society of Water and Wastewater
• /
• v.20 no.5
• /
• pp.737-745
• /
• 2006

The goal of this study is to present an external pit corrosion rate($p_{ecr}$) model with considering both the age of pipe and the soil characteristics. The correlation of nonlinear exponential model among conventional empirical models was a little higher than other empirical models in the prediction of $p_{ecr}$ according to the age of pipe. However, there has been a limit to predict Peer with the model by using only a pipe age since installation as a variable. The soil analysis results from sixty nine samples showed that all of the samples were non corrosive in the assessment of ANSI/AWWA scoring system. The correlation of soil corrosion factors and $p_{ecr}$ was also low. The application result of linear and nonlinear regression models that soil characteristics only showed a low correlation with $p_{ecr}$ Proposed nonlinear regression model in this study, with considering both the age of pipe and the soil characteristics, showed a little higher correlation ($R^2=0.46$) than conventional model.

• Journal of Biosystems Engineering
• /
• v.18 no.3
• /
• pp.209-219
• /
• 1993

A series of soil bin experiment was carried out on sand to investigate if true model theory is applicable to blade-soil system and finally to find mathematical relationship between the dimensionless terms which contain the blade-soil parameters. The following conclusions were derived from the study. 1. It was proved that the draft of the prototype blade can be predicted without distortion by those of model blades with the length scale of 1.2, 2 and 2.4. 2. For the sand, bulk density was found to be a good measure of soil physical properties which are pertinent to predict the draft of the blade-soil system. 3. The mathematical relationship between $D/{\gamma}W$ and d/W, ${\beta}$, and $V^2/Wg$ are as follows ; $$\frac{D}{{\gamma}W^3}=124.98[\frac{d}{W}]^2+7.16[\frac{d}{W}]+0.43 \\ \frac{D}{{\gamma}W^3}=-0.00099{\beta}^2+0.13{\beta}-2.01 \\ \frac{D}{{\gamma}W^3}=0.041[\frac{V^2}{Wg}]^2+0.08[\frac{V^2}{Wg}]+1.3$$

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.601-612
• /
• 2022

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.