Introduction to the development of an information management system for soil mix technology using artificial neural networks

This paper introduces current work in collating data from different projects using soil mix technology and establishing trends using artificial neural networks (ANNs). Variation in unconfined compressive strength as a function of selected soil mix variables (e.g., initial soil water content and binder dosage) is observed through the data compiled from completed and on-going soil mixing projects around the world. The potential and feasibility of ANNs in developing predictive models, which take into account a large number of variables, is discussed. The main objective of the work is the management and effective utilization of salient variables and the development of predictive models useful for soil mix technology design. Based on the observed success in the predictions made, this paper suggests that neural network analysis for the prediction of properties of soil mix systems is feasible. © ASCE 2011.

Multiple Linear Regression and Artificial Neural Networks to Predict Time and Efficiency of Soil Vapor Extraction

The prediction of the time and the efficiency of the remediation of contaminated soils using soil vapor extraction remain a difficult challenge to the scientific community and consultants. This work reports the development of multiple linear regression and artificial neural network models to predict the remediation time and efficiency of soil vapor extractions performed in soils contaminated separately with benzene, toluene, ethylbenzene, xylene, trichloroethylene, and perchloroethylene. The results demonstrated that the artificial neural network approach presents better performances when compared with multiple linear regression models. The artificial neural network model allowed an accurate prediction of remediation time and efficiency based on only soil and pollutants characteristics, and consequently allowing a simple and quick previous evaluation of the process viability.

Use of an artificial root to examine the influence of 8-hydroxyquinoline on soil microbial activity and bacterial community structure

Invasive plant species have been shown to alter the microbial community composition of the soils they invade and it is suggested that this below-ground perturbation of potential pathogens, decomposers or symbionts may feedback positively to allow invasive success. Whether these perturbations are mediated through specific components of root exudation are not understood. We focussed on 8-hydroxyquinoline, a putative allelochemical of Centaurea diffusa (diffuse knapweed) and used an artificial root system to differentiate the effects of 8-hydroxyquinoline against a background of total rhizodeposition as mimicked through supply of a synthetic exudate solution. In soil proximal (0-10 cm) to the artificial root, synthetic exudates had a highly significant (P < 0.001) influence on dehydrogenase, fluorescein diacetate hydrolysis and urease activity. in addition, 8-hydroxyquinoline was significant (p = 0.003) as a main effect on dehydrogenase activity and interacted with synthetic exudates to affect urease activity (p = 0.09). Hierarchical cluster analysis of 16S rDNA-based DGGE band patterns also identified a primary affect of synthetic exudates and a secondary affect of 8-hydroxyquinoline on bacterial community structure. Thus, we show that the artificial rhizosphere produced by the synthetic exudates was the predominant effect, but, that the influence of the 8-hydroxyquinoline signal on the activity and structure of soil microbial communities could also be detected. (C) 2009 Elsevier Ltd. All rights reserved.

Image sub-segmentation by PFCM and Artificial Neural Networks to detect pore space in 2D and 3D CT soil images

The image by Computed Tomography is a non-invasive alternative for observing soil structures, mainly pore space. The pore space correspond in soil data to empty or free space in the sense that no material is present there but only fluids, the fluid transport depend of pore spaces in soil, for this reason is important identify the regions that correspond to pore zones. In this paper we present a methodology in order to detect pore space and solid soil based on the synergy of the image processing, pattern recognition and artificial intelligence. The mathematical morphology is an image processing technique used for the purpose of image enhancement. In order to find pixels groups with a similar gray level intensity, or more or less homogeneous groups, a novel image sub-segmentation based on a Possibilistic Fuzzy c-Means (PFCM) clustering algorithm was used. The Artificial Neural Networks (ANNs) are very efficient for demanding large scale and generic pattern recognition applications for this reason finally a classifier based on artificial neural network is applied in order to classify soil images in two classes, pore space and solid soil respectively.

Soil disturbance and compaction in wildland management.

"January 1985."

Artificial pumping errors in the Kool-Parker scaling model of soil moisture hysteresis

Hysteresis models that eliminate the artificial pumping errors associated with the Kool-Parker (KP) soil moisture hysteresis model, such as the Parker-Lenhard (PL) method, can be computationally demanding in unsaturated transport models since they need to retain the wetting-drying history of the system. The pumping errors in these models need to be eliminated for correct simulation of cyclical systems (e.g. transport above a tidally forced watertable, infiltration and redistribution under periodic irrigation) if the soils exhibit significant hysteresis. A modification is made here to the PL method that allows it to be more readily applied to numerical models by eliminating the need to store a large number of soil moisture reversal points. The modified-PL method largely eliminates any artificial pumping error and so essentially retains the accuracy of the original PL approach. The modified-PL method is implemented in HYDRUS-1D (version 2.0), which is then used to simulate cyclic capillary fringe dynamics to show the influence of removing artificial pumping errors and to demonstrate the ease of implementation. Artificial pumping errors are shown to be significant for the soils and system characteristics used here in numerical experiments of transport above a fluctuating watertable. (c) 2005 Elsevier B.V. All rights reserved.

Digital soil mapping using reference area and artificial neural networks.

Digital soil mapping is an alternative for the recognition of soil classes in areas where pedological surveys are not available. The main aim of this study was to obtain a digital soil map using artificial neural networks (ANN) and environmental variables that express soillandscape relationships. This study was carried out in an area of 11,072 ha located in the Barra Bonita municipality, state of São Paulo, Brazil. A soil survey was obtained from a reference area of approximately 500 ha located in the center of the area studied. With the mapping units identified together with the environmental variables elevation, slope, slope plan, slope profile, convergence index, geology and geomorphic surfaces, a supervised classification by ANN was implemented. The neural network simulator used was the Java NNS with the learning algorithm "back propagation." Reference points were collected for evaluating the performance of the digital map produced. The occurrence of soils in the landscape obtained in the reference area was observed in the following digital classification: medium-textured soils at the highest positions of the landscape, originating from sandstone, and clayey loam soils in the end thirds of the hillsides due to the greater presence of basalt. The variables elevation and slope were the most important factors for discriminating soil class through the ANN. An accuracy level of 82% between the reference points and the digital classification was observed. The methodology proposed allowed for a preliminary soil classification of an area not previously mapped using mapping units obtained in a reference area

Below-ground processes in meadow soil under elevated ozone and carbon dioxide : - Greenhouse gas fluxes, N cycling and microbial communities

This thesis focuses on how elevated CO2 and/or O3 affect the below-ground processes in semi-natural vegetation, with an emphasis on greenhouse gases, N cycling and microbial communities. Meadow mesocosms mimicking lowland hay meadows in Jokioinen, SW Finland, were enclosed in open-top chambers and exposed to ambient and elevated levels of O3 (40-50 ppb) and/or CO2 (+100 ppm) for three consecutive growing season, while chamberless plots were used as chamber controls. Chemical and microbiological analyses as well as laboratory incubations of the mesocosm soils under different treatments were used to study the effects of O3 and/or CO2. Artificially constructed mesocosms were also compared with natural meadows with regards to GHG fluxes and soil characteristics. In addition to research conducted at the ecosystem level (i.e. the mesocosm study), soil microbial communities were also examined in a pot experiment with monocultures of individual species. By comparing mesocosms with similar natural plant assemblage, it was possible to demonstrate that artificial mesocosms simulated natural habitats, even though some differences were found in the CH4 oxidation rate, soil mineral N, and total C and N concentrations in the soil. After three growing seasons of fumigations, the fluxes of N2O, CH4, and CO2 were decreased in the NF+O3 treatment, and the soil NH4+-N and mineral N concentrations were lower in the NF+O3 treatment than in the NF control treatment. The mesocosm soil microbial communities were affected negatively by the NF+O3 treatment, as the total, bacterial, actinobacterial, and fungal PLFA biomasses as well as the fungal:bacterial biomass ratio decreased under elevated O3. In the pot survey, O3 decreased the total, bacterial, actinobacterial, and mycorrhizal PLFA biomasses in the bulk soil and affected the microbial community structure in the rhizosphere of L. pratensis, whereas the bulk soil and rhizosphere of the other monoculture, A. capillaris, remained unaffected by O3. Elevated CO2 caused only minor and insignificant changes in the GHG fluxes, N cycling, and the microbial community structure. In the present study, the below-ground processes were modified after three years of moderate O3 enhancement. A tentative conclusion is that a decrease in N availability may have feedback effects on plant growth and competition and affect the N cycling of the whole meadow ecosystem. Ecosystem level changes occur slowly, and multiplication of the responses might be expected in the long run.

Cement stabilised rammed earth. Part A: compaction characteristics and physical properties of compacted cement stabilised soils

Rammed earth is used for load bearing walls of buildings and there is growing interest in this low carbon building material. This paper is focused on understanding the compaction characteristics and physical properties of compacted cement stabilised soil mixtures and cement stabilised rammed earth (CSRE). This experimental study addresses (a) influence of soil composition, cement content, time lag on compaction characteristics of stabilised soils and CSRE and (b) effect of moulding water content and density on compressive strength and water absorption of compacted cement stabilised soil mixes. Salient conclusions of the study are (a) compaction characteristics of soils are not affected by the addition of cement, (b) there is 50% fall in strength of CSRE for 10 h time lag, (c) compressive strength of compacted cement stabilised soil increases with increase in density irrespective of moulding moisture content and cement content, and (d) compressive strength increases with the increase in moulding water content and compaction of CSRE on the wet side of OMC is beneficial in terms of strength.

Machine learning modelling for predicting soil liquefaction susceptibility

This study describes two machine learning techniques applied to predict liquefaction susceptibility of soil based on the standard penetration test (SPT) data from the 1999 Chi-Chi, Taiwan earthquake. The first machine learning technique which uses Artificial Neural Network (ANN) based on multi-layer perceptions (MLP) that are trained with Levenberg-Marquardt backpropagation algorithm. The second machine learning technique uses the Support Vector machine (SVM) that is firmly based on the theory of statistical learning theory, uses classification technique. ANN and SVM have been developed to predict liquefaction susceptibility using corrected SPT (N-1)(60)] and cyclic stress ratio (CSR). Further, an attempt has been made to simplify the models, requiring only the two parameters (N-1)(60) and peck ground acceleration (a(max)/g)], for the prediction of liquefaction susceptibility. The developed ANN and SVM models have also been applied to different case histories available globally. The paper also highlights the capability of the SVM over the ANN models.

Re-examination of compaction characteristics of fine-grained soils

Standard Proctor compaction test data were generated for 3 soils with liquid limit water contents ranging from 48% to 84%. It has been established that by defining a soil by its liquid limit and coarse fraction, the path of compaction for a specific compactive effort can be predicted via a simple density-water content-liquid limit relationship. (Abstract quotes from original text)

Role of soil structure and matric suction in collapse of a compacted clay soil

This paper examines the role of microstructure and matric suction in the collapse behavior of a compacted clay soil from Bangalore District in Karnataka State, India. The microstructure of the compacted specimens was examined by mercury intrusion porosimetry (MIP), and the ASTM Filter Paper Method was used to determine their matric suction. The microstructure and matric suction of the compacted specimens were changed by varying their compaction water content, dry density, and clay content (< 2 mum fraction). Experimental results showed that relative abundance of coarse (60 to 6 mum) pores was mainly affected by increasing the dry density of the specimens from 1.49 to 1.77 g/cm(3). The relative abundance of coarse and fine (0.01 to 0.002 mum) pores was affected by increasing the compaction water content from 10.6 to 26.4%. Variations in dry density, compaction water content, and clay contents notably affected the matric suction of the compacted specimens. The collapse behavior of the compacted specimens is explained from analysis of the MIP and matric suction results.