Herein, a recently developed methodology, Support Vector Machines (SVMs), is presented and applied to the challenge of soil moisture prediction. Support Vector Machines are derived from statistical learning theory and can be used to predict a quantity forward in time based on training that uses past data, hence providing a statistically sound approach to solving inverse problems. The principal strength of SVMs lies in the fact that they employ Structural Risk Minimization (SRM) instead of Empirical Risk Minimization (ERM). The SVMs formulate a quadratic optimization problem that ensures a global optimum, which makes them superior to traditional learning algorithms such as Artificial Neural Networks (ANNs). The resulting model is sparse and not characterized by the "curse of dimensionality." Soil moisture distribution and variation is helpful in predicting and understanding various hydrologic processes, including weather changes, energy and moisture fluxes, drought, irrigation scheduling, and rainfall/runoff generation. Soil moisture and meteorological data are used to generate SVM predictions for four and seven days ahead. Predictions show good agreement with actual soil moisture measurements. Results from the SVM modeling are compared with predictions obtained from ANN models and show that SVM models performed better for soil moisture forecasting than ANN models.
When operated properly, in situ soil venting or vapor extraction can be one of the most cost‐effective remediation processes for soils contaminated with gasoline, solvents, or other relatively, volatile compounds. The components of soil‐venting systems are typically off‐the‐shelf items, and the installation of wells and trenches can be done by reputable environmental firms. However, the design, operation, and monitoring of soil‐venting systems are not trivial. In fact, choosing whether or not venting should be applied at a given site is a difficult decision in itself. If one decides to utilize venting, design criteria involving the number of wells, well spacing, well location, well construction, and vapor treatment systems must be addressed. A series of questions must be addressed to decide if venting is appropriate at a given site and to design cost‐effective in situ soil‐venting systems. This series of steps and questions forms a “decision tree” process. The development of this approach is an attempt to identify the limitations of in situ soil venting, and subjects or behavior that are currently difficult to quantify and for which future study is needed.
The efficiency of any soil venting operation will depend significantly on three factors: vapor flowrate, vapor flow path relative to the contaminant distribution, and composition of the contaminant. Simple mathematical models were developed to be used as screening tools to help determine if soil venting will be a viable remediation option at any given spill site. The models relate the applied vacuum, soil permeability, and spill composition to the vapor flowrates, velocities, mass removal rates, and residual composition changes with time. In this report the screening models and some sample calculations are presented. The results illustrate the advantages and limitations of venting as a remediation tool, under both ideal and nonideal conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.