Multilayer perceptron with local constraint as an emerging method in spatial data analysis

The use of Geographic Information Systems has revolutionalized the handling and the visualization of geo-referenced data and has underlined the critic role of spatial analysis. The usual tools for such a purpose are geostatistics which are widely used in Earth science. Geostatistics are based upon several hypothesis which are not always verified in practice. On the other hand, Artificial Neural Network (ANN) a priori can be used without special assumptions and are known to be flexible. This paper proposes to discuss the application of ANN in the case of the interpolation of a geo-referenced variable.

Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

A geoprocessing approach for studying and controlling schistosomiasis in the state of Minas Gerais, Brazil

Geographical information systems (GIS) are tools that have been recently tested for improving our understanding of the spatial distribution of disease. The objective of this paper was to further develop the GIS technology to model and control schistosomiasis using environmental, social, biological and remote-sensing variables. A final regression model (R² = 0.39) was established, after a variable selection phase, with a set of spatial variables including the presence or absence of Biomphalaria glabrata, winter enhanced vegetation index, summer minimum temperature and percentage of houses with water coming from a spring or well. A regional model was also developed by splitting the state of Minas Gerais (MG) into four regions and establishing a linear regression model for each of the four regions: 1 (R² = 0.97), 2 (R² = 0.60), 3 (R² = 0.63) and 4 (R² = 0.76). Based on these models, a schistosomiasis risk map was built for MG. In this paper, geostatistics was also used to make inferences about the presence of Biomphalaria spp. The result was a map of species and risk areas. The obtained risk map permits the association of uncertainties, which can be used to qualify the inferences and it can be thought of as an auxiliary tool for public health strategies.

Uncertainty Quantification Of A Semi-Supervised Support Vector Regression Reservoir Model

Uncertainty quantification of petroleum reservoir models is one of the present challenges, which is usually approached with a wide range of geostatistical tools linked with statistical optimisation or/and inference algorithms. Recent advances in machine learning offer a novel approach to model spatial distribution of petrophysical properties in complex reservoirs alternative to geostatistics. The approach is based of semisupervised learning, which handles both ?labelled? observed data and ?unlabelled? data, which have no measured value but describe prior knowledge and other relevant data in forms of manifolds in the input space where the modelled property is continuous. Proposed semi-supervised Support Vector Regression (SVR) model has demonstrated its capability to represent realistic geological features and describe stochastic variability and non-uniqueness of spatial properties. On the other hand, it is able to capture and preserve key spatial dependencies such as connectivity of high permeability geo-bodies, which is often difficult in contemporary petroleum reservoir studies. Semi-supervised SVR as a data driven algorithm is designed to integrate various kind of conditioning information and learn dependences from it. The semi-supervised SVR model is able to balance signal/noise levels and control the prior belief in available data. In this work, stochastic semi-supervised SVR geomodel is integrated into Bayesian framework to quantify uncertainty of reservoir production with multiple models fitted to past dynamic observations (production history). Multiple history matched models are obtained using stochastic sampling and/or MCMC-based inference algorithms, which evaluate posterior probability distribution. Uncertainty of the model is described by posterior probability of the model parameters that represent key geological properties: spatial correlation size, continuity strength, smoothness/variability of spatial property distribution. The developed approach is illustrated with a fluvial reservoir case. The resulting probabilistic production forecasts are described by uncertainty envelopes. The paper compares the performance of the models with different combinations of unknown parameters and discusses sensitivity issues.

Detection of Optimal Models in Parameter Space with Support Vector Machines

The paper proposes an approach aimed at detecting optimal model parameter combinations to achieve the most representative description of uncertainty in the model performance. A classification problem is posed to find the regions of good fitting models according to the values of a cost function. Support Vector Machine (SVM) classification in the parameter space is applied to decide if a forward model simulation is to be computed for a particular generated model. SVM is particularly designed to tackle classification problems in high-dimensional space in a non-parametric and non-linear way. SVM decision boundaries determine the regions that are subject to the largest uncertainty in the cost function classification, and, therefore, provide guidelines for further iterative exploration of the model space. The proposed approach is illustrated by a synthetic example of fluid flow through porous media, which features highly variable response due to the parameter values' combination.

Spatial variability of the chemical, physical and biological properties in lowland cultivated with irrigated rice

In the areas where irrigated rice is grown in the south of Brazil, few studies have been carried out to investigate the spatial variability structure of soil properties and to establish new forms of soil management as well as determine soil corrective and fertilizer applications. In this sense, this study had the objective of evaluating the spatial variability of chemical, physical and biological soil properties in a lowland area under irrigated rice cultivation in the conventional till system. For this purpose, a 10 x 10 m grid of 100 points was established, in an experimental field of the Embrapa Clima Temperado, in the County of Capão do Leão, State of Rio Grande do Sul. The spatial variability structure was evaluated by geostatistical tools and the number of subsamples required to represent each soil property in future studies was calculated using classical statistics. Results showed that the spatial variability structure of sand, silt, SMP index, cation exchange capacity (pH 7.0), Al3+ and total N properties could be detected by geostatistical analysis. A pure nugget effect was observed for the nutrients K, S and B, as well as macroporosity, mean weighted diameter of aggregates, and soil water storage. The cross validation procedure, based on linear regression and the determination coefficient, was more efficient to evaluate the quality of the adjusted mathematical model than the degree of spatial dependence. It was also concluded that the combination of classical with geostatistics can in many cases simplify the soil sampling process without losing information quality.

Spatial variability of soil chemical properties after coffee tree removal

Assessing the spatial variability of soil chemical properties has become an important aspect of soil management strategies with a view to higher crop yields with minimal environmental degradation. This study was carried out at the Centro Experimental of the Instituto Agronomico, in Campinas, São Paulo, Brazil. The aim was to characterize the spatial variability of chemical properties of a Rhodic Hapludox on a recently bulldozer-cleaned area after over 30 years of coffee cultivation. Soil samples were collected in a 20 x 20 m grid with 36 sampling points across a 1 ha area in the layers 0.0-0.2 and 0.2-0.4 m to measure the following chemical properties: pH, organic matter, K+, P, Ca2+, Mg2+, potential acidity, NH4-N, and NO3-N. Descriptive statistics were applied to assess the central tendency and dispersion moments. Geostatistical methods were applied to evaluate and to model the spatial variability of variables by calculating semivariograms and kriging interpolation. Spatial dependence patterns defined by spherical model adjusted semivariograms were made for all cited soil properties. Moderate to strong degrees of spatial dependence were found between 31 and 60 m. It was still possible to map soil spatial variability properties in the layers 0-20 cm and 20-40 cm after plant removal with bulldozers.

Spatial and temporal variability of crop yield and some Rhodic Hapludox properties under no-tillage

Soil properties are closely related with crop production and spite of the measures implemented, spatial variation has been repeatedly observed and described. Identifying and describing spatial variations of soil properties and their effects on crop yield can be a powerful decision-making tool in specific land management systems. The objective of this research was to characterize the spatial and temporal variations in crop yield and chemical and physical properties of a Rhodic Hapludox soil under no-tillage. The studied area of 3.42 ha had been cultivated since 1985 under no-tillage crop rotation in summer and winter. Yield and soil property were sampled in a regular 10 x 10 m grid, with 302 sample points. Yields of several crops were analyzed (soybean, maize, triticale, hyacinth bean and castor bean) as well as soil chemical (pH, Soil Organic Matter (SOM), P, Ca2+, Mg2+, H + Al, B, Fe, Mn, Zn, CEC, sum of bases (SB), and base saturation (V %)) and soil physical properties (saturated hydraulic conductivity, texture, density, total porosity, and mechanical penetration resistance). Data were analyzed using geostatistical analysis procedures and maps based on interpolation by kriging. Great variation in crop yields was observed in the years evaluated. The yield values in the Northern region of the study area were high in some years. Crop yields and some physical and soil chemical properties were spatially correlated.

Spatial variability of physical attributes of an alfisol under different hillslope curvatures

The influence of relief forms has been studied by several authors and explains the variability in the soil attributes of a landscape. Soil physical attributes depend on relief forms, and their assessment is important in mechanized agricultural systems, such as of sugarcane. This study aimed to characterize the spatial variability in the physical soil attributes and their relationship to the hillslope curvatures in an Alfisol developed from sandstone and growing sugarcane. Grids of 100 x 100 m were delimited in a convex and a concave area. The grids had a regular spacing of 10 x 10 m, and the crossing points of this spacing determined a total of 121 georeferenced sampling points. Samples were collected to determine the physical attributes related to soil aggregates, porosity, bulk density, resistance to penetration and moisture within the 0-0.2 and 0.2-0.4 m depth. Statistical analyses, geostatistics and Student's t-tests were performed with the means of the areas. All attributes, except aggregates > 2 mm in the 0-0.2 m depth and macroporosity at both depths, showed significant differences between the hillslope curvatures. The convex area showed the highest values of the mean weighted diameter, mean geometric diameter, aggregates > 2 mm, 1-2 mm aggregates, total porosity and moisture and lower values of bulk density and resistance to penetration in both depth compared to the concave area. The number of soil attributes with greater spatial variability was higher in the concave area.

Pedotransfer functions related to spatial variability of water retention attributes for lowland soils

The estimation of non available soil variables through the knowledge of other related measured variables can be achieved through pedotransfer functions (PTF) mainly saving time and reducing cost. Great differences among soils, however, can yield non desirable results when applying this method. This study discusses the application of developed PTFs by several authors using a variety of soils of different characteristics, to evaluate soil water contents of two Brazilian lowland soils. Comparisons are made between PTF evaluated data and field measured data, using statistical and geostatistical tools, like mean error, root mean square error, semivariogram, cross-validation, and regression coefficient. The eight tested PTFs to evaluate gravimetric soil water contents (Ug) at the tensions of 33 kPa and 1,500 kPa presented a tendency to overestimate Ug 33 kPa and underestimate Ug1,500 kPa. The PTFs were ranked according to their performance and also with respect to their potential in describing the structure of the spatial variability of the set of measured values. Although none of the PTFs have changed the distribution pattern of the data, all resulted in mean and variance statistically different from those observed for all measured values. The PTFs that presented the best predictive values of Ug33 kPa and Ug1,500 kPa were not the same that had the best performance to reproduce the structure of spatial variability of these variables.

Geomodelling of a fluvial system with semi-supervised support vector regression

Fluvial deposits are a challenge for modelling flow in sub-surface reservoirs. Connectivity and continuity of permeable bodies have a major impact on fluid flow in porous media. Contemporary object-based and multipoint statistics methods face a problem of robust representation of connected structures. An alternative approach to model petrophysical properties is based on machine learning algorithm ? Support Vector Regression (SVR). Semi-supervised SVR is able to establish spatial connectivity taking into account the prior knowledge on natural similarities. SVR as a learning algorithm is robust to noise and captures dependencies from all available data. Semi-supervised SVR applied to a synthetic fluvial reservoir demonstrated robust results, which are well matched to the flow performance

Spatial patterns of preconsolidation pressure and soil moisture along transects in two directions under coffee

Information on the spatial structure of soil physical and structural properties is needed to evaluate the soil quality. The purpose of this study was to investigate the spatial behavior of preconsolidation pressure and soil moisture in six transects, three selected along and three across coffee rows, at three different sites under different tillage management systems. The study was carried out on a farm, in Patrocinio, state of Minas Gerais, in the Southeast of Brazil (18 º 59 ' 15 '' S; 46 º 56 ' 47 '' W; 934 m asl). The soil type is a typic dystrophic Red Latosol (Acrustox) and consists of 780 g kg-1 clay; 110 g kg-1 silt and 110 g kg-1 sand, with an average slope of 3 %. Undisturbed soil cores were sampled at a depth of 0.10-0.13 m, at three different points within the coffee plantation: (a) from under the wheel track, where equipment used in farm operations passes; (b) in - between tracks and (c) under the coffee canopy. Six linear transects were established in the experimental area: three transects along and three across the coffee rows. This way, 161 samples were collected in the transect across the coffee rows, from the three locations, while 117 samples were collected in the direction along the row. The shortest sampling distance in the transect across the row was 4 m, and 0.5 m for the transect along the row. No clear patterns of the preconsolidation pressure values were observed in the 200 m transect. The results of the semivariograms for both variables indicated a high nugget value and short range for the studied parameters of all transects. A cyclic pattern of the parameters was observed for the across-rows transect. An inverse relationship between preconsolidation pressure and soil moisture was clearly observed in the samples from under the track, in both directions.