1,720,965 research outputs found
Inter-comparison of satellite sensor land surface phenology and ground phenology in Europe
No full textLand surface phenology (LSP) and ground phenology (GP) are both important sources of information for monitoring terrestrial ecosystem responses to climate changes. Each measures different vegetation phenological stages and has different sources of uncertainties, which make comparison in absolute terms challenging, and therefore, there has been limited attempts to evaluate the complementary nature of both measures. However, both LSP and GP are climate-driven and, therefore, should exhibit similar inter-annual variation. LSP obtained from the whole time-series of MERIS data were compared to thousands of deciduous tree ground phenology records of the Pan European Phenology network (PEP725). Correlations observed between the inter-annual time-series of the satellite sensor estimates of phenology and PEP725 records revealed a close agreement (especially for Betula Pendula and Fagus Sylvatica species). In particular, 90% of the statistically significant correlations between LSP and GP were positive (mean R2?=?0.77). A large spatio-temporal correlation was observed between the dates of the start of season (end of season) from space and leaf unfolding (autumn coloring) at the ground (pseudo R2 of 0.70 (0.71)) through the application of non-linear multivariate models, providing, for the first time, the ability to predict accurately the date of leaf unfolding (autumn coloring) across Europe (RMSE of 5.97?days (6.75?days) over 365?days
Regression trees for modelling geochemical data- an application to Late Jurassic carbonates (Ammonitico Rosso)
No full textResearch based on ancient carbonate geochemical records is often assisted by multivariate statistical analysis, among others, used for data mining. This contribution reports a complementary approach that can be applied to paleoenvironmental research. The choice to use a machine learning method, here regression trees (RT), relied in the ability to learn complex patterns, integrating multiple types of data with different statistical distributions to obtain a knowledge model of geochemical behaviour along a paleo-platform.The Late Jurassic epioceanic deposits under scope are represented by six stratigraphic sections located in SE Spain and on the Majorca Island. The used database comprises a total of 1960 data points corresponding to eight variables (stable C and O isotopes, the elements Ca, Mg, Sr, Fe, Mn and skeletal content). This study uses RT models in which the predictive variables are the geochemical proxies, whilst skeletal content is used as a target variable. The resulting model is data driven, explaining variations in the target variable and providing additional information on the relative importance of each variable to each prediction, as well as its corresponding threshold values.The obtained RT revealed a structured distribution of samples, organized either by stratigraphic section or sets of nearby sections. Averaged estimated skeletal abundance confirmed the initial observations of higher skeletal content for the most distal sections with estimated values from 18 to 27%. In contrast, lower skeletal abundance from 5 to 15% is proposed for the remaining sections. The geochemical variable that best discriminates this major trend is δ18O, at a threshold value of -0.2‰, interpreted as evidence for separation of water-mass properties across the studied areas. Other four variables were considered relevant by the obtained decision tree: C isotopes, Ca, Sr and Mn, providing new insights for further differentiation between sets of samples
Dastaset for: "Rodriguez-Galiano, V.F., Sanchez-Castillo, M., Dash, J., Atkinson, P. and Ojeda-Zujar, J. (2016). Modelling interannual variation in the spring and autumn land surface phenology of the European forest, Biogeosciences, 13
No full text<p>Dastaset for: "Rodriguez-Galiano, V.F., Sanchez-Castillo, M., Dash, J., Atkinson, P. and Ojeda-Zujar, J. (2016). Modelling interannual variation in the spring and autumn land surface phenology of the European forest, Biogeosciences, 13</p>
Predictive modelling of gold potential with the integration of multisource information based on random forest: a case study on the Rodalquilar area, Southern Spain
No full textMineral exploration activities require robust predictive models that result in accurate mapping of the probability that mineral deposits can be found at a certain location. Random forest (RF) is a powerful machine data-driven predictive method that is unknown in mineral potential mapping. In this paper, performance of RF regression for the likelihood of gold deposits in the Rodalquilar mining district is explored. The RF model was developed using a comprehensive exploration GIS database composed of: gravimetric and magnetic survey, a lithogeochemical survey of 59 elements, lithology and fracture maps, a Landsat 5 Thematic Mapper image and gold occurrence locations. The results of this study indicate that the use of RF for the integration of large multisource data sets used in mineral exploration and for prediction of mineral deposit occurrences offers several advantages over existing methods. Key advantages of RF include: (1) the simplicity of parameter setting; (2) an internal unbiased estimate of the prediction error; (3) the ability to handle complex data of different statistical distributions, responding to nonlinear relationships between variables; (4) the capability to use categorical predictors; and (5) the capability to determine variable importance. Additionally, variables that RF identified as most important coincide with well-known geologic expectations. To validate and assess the effectiveness of the RF method, gold prospectivity maps are also prepared using the logistic regression (LR) method. Statistical measures of map quality indicate that the RF method performs better than LR, with mean square errors equal to 0.12 and 0.19, respectively. The efficiency of RF is also better, achieving an optimum success rate when half of the area predicted by LR is considere
Predictive modeling of groundwater nitrate pollution using Random Forest and multisource variables related to intrinsic and specific vulnerability: a case study in an agricultural setting (Southern Spain)
No full textWatershed management decisions need robust methods, which allow an accurate predictive modeling of pollutant occurrences. Random Forest (RF) is a powerful machine learning data driven method that is rarely used in water resources studies, and thus has not been evaluated thoroughly in this field, when compared to more conventional pattern recognition techniques key advantages of RF include: its non-parametric nature; high predictive accuracy; and capability to determine variable importance. This last characteristic can be used to better understand the individual role and the combined effect of explanatory variables in both protecting and exposing groundwater from and to a pollutant.In this paper, the performance of the RF regression for predictive modeling of nitrate pollution is explored, based on intrinsic and specific vulnerability assessment of the Vega de Granada aquifer. The applicability of this new machine learning technique is demonstrated in an agriculture-dominated area where nitrate concentrations in groundwater can exceed the trigger value of 50 mg/L, at many locations. A comprehensive GIS database of twenty-four parameters related to intrinsic hydrogeologic proprieties, driving forces, remotely sensed variables and physical–chemical variables measured in “situ”, were used as inputs to build different predictive models of nitrate pollution. RF measures of importance were also used to define the most significant predictors of nitrate pollution in groundwater, allowing the establishment of the pollution sources (pressures).The potential of RF for generating a vulnerability map to nitrate pollution is assessed considering multiple criteria related to variations in the algorithm parameters and the accuracy of the maps. The performance of the RF is also evaluated in comparison to the logistic regression (LR) method using different efficiency measures to ensure their generalization ability. Prediction results show the ability of RF to build accurate models with strong predictive capabilitie
Random Forest classification of Mediterranean land cover using multi-seasonal imagery and multi-seasonal texture
No full textA Random Forest (RF) classifier was applied to spectral as well as mono- and multi-seasonal textural features extracted from Landsat TM imagery to increase the accuracy of land cover classification over a complex Mediterranean landscape, with a large number of land cover categories and low inter-class separability. Five different types of geostatistical textural measure for three different window sizes and three different lags were applied creating a total of 972 potential input variables. Madograms, rodograms and direct variograms for the univariate case and cross- and pseudo-cross variograms for the multivariate case, together with multi-seasonal spectral information, were used in a RF classifier to map the landcover types. The pseudo-cross and cross variograms were used specifically to incorporate important seasonal/temporal information. Incorporating multi-scale textural features into the RF models led to an increase in the overall index of 10.71% and, for the most accurate classification, the increase was up to 30% in some classes. The differences in the kappa coefficient for the textural classification models were evaluated statistically using a pairwise Z-test, revealing a significant increase in per-class classification accuracy compared to GLCM-based texture measures. The pseudo-cross variogram between the visible and near-infrared bands was the most important textural features for general classification, and the multi-seasonal pseudo-cross variogram had an outstanding importance for agricultural classes. Overall, the RF classifier applied to a reduced subset of input variables composed of the most informative textural features led to the highest accuracy. Highly reliable classification results were obtained when the 16 most important textural features calculated at single scales (window sizes) were selected and used in the classification. The proposed methodology significantly increased the classification accuracy achieved with a spectral maximum likelihood classifier (ML). The kappa values for the textural RF and ML classifications were equal to 0.92 and 0.83, respectively
New insights into geochemical behaviour in ancient marine carbonates (Upper Jurassic Ammonitico Rosso): novel proxies for interpreting sea-level dynamics and palaeoceanography
No full textElemental concentrations in Phanerozoic sea water are known to fluctuate both in time and space. With regard to carbonates precipitated from marine fluids, elemental concentrations in the carbonate crystal lattice are affected by a complex array of equilibrium and non-equilibrium as well as post-depositional alteration processes. To assess the potential of carbonate elemental chemostratigraphy, seven Upper Jurassic sections were investigated along a proximal to distal transect across the south-east Iberian palaeomargin. The aim was to explore stratigraphic and spatial variations in calcium, strontium, magnesium, iron and manganese elemental abundances. The epicontinental geochemical record is influenced by the combination of continental runoff and a significant diagenetic overprint. In contrast, the epioceanic geochemical record agrees with reconstructed open marine sea water values, reflecting a moderate degree of syn-depositional to early marine pore water diagenesis. Establishing a fair degree of preservation of matrix micrite, a thorough statistical approach was applied and elemental associations tested for their environmental significance. Principal component and hierarchical cluster analyses revealed a persistent relation between carbonate magnesium, iron and strontium abundances. Processes related to early diagenetic nodulation in Ammonitico Rosso facies most probably account for the incorporation of these elements in the calcium carbonate lattice. The clear decoupling of carbonate manganese abundance with respect to the remaining elements is documented and related to high sea floor spreading rates and hydrothermal activity during the Late Jurassic. The investigation of potential time-fluctuation of geochemical patterns was approached through variogram computation. The observed temporal behaviour is most likely to be forced by relative sea-level dynamics, reflecting Late Jurassic palaeoceanographic conditions and potential planetary interactions. The data obtained in this study highlight the utility of elemental data from carbonate matrix micrites as geochemical proxies for studying the influence of remote trigger factor
Machine learning predictive models for mineral prospectivity: an evaluation of neural networks, random forest, regression trees and support vector machines
No full textMachine learning algorithms (MLAs) such us artificial neural networks (ANNs), regression trees (RTs), random forest (RF) and support vector machines (SVMs) are powerful data driven methods that are relatively less widely used in the mapping of mineral prospectivity, and thus have not been comparatively evaluated together thoroughly in this field.The performances of a series of MLAs, namely, artificial neural networks (ANNs), regression trees (RTs), random forest (RF) and support vector machines (SVMs) in mineral prospectivity modelling are compared based on the following criteria: i) the accuracy in the delineation of prospective areas; ii) the sensitivity to the estimation of hyper-parameters; iii) the sensitivity to the size of training data; and iv) the interpretability of model parameters. The results of applying the above algorithms to epithermal Au prospectivity mapping of the Rodalquilar district, Spain, indicate that the RF outperformed the other MLA algorithms (ANNs, RTs and SVMs). The RF algorithm showed higher stability and robustness with varying training parameters and better success rates and ROC analysis results. On the other hand, all MLA algorithms can be used when ore deposit evidences are scarce. Moreover the model parameters of RF and RT can be interpreted to gain insights into the geological controls of mineralization.<br/
Image fusion by spatially adaptive filtering using downscaling cokriging
No full textThe aim of this paper was to extend the method of downscaling cokriging for image fusion by making the method spatially adaptive in that the filter parameters (cokriging weights) can change across the image. The method can adapt itself to the usual statistical non-homogeneity (spatially variable mean, variance and correlation length) of a satellite sensor image that covers an area with different spatial patterns of geographical objects or different terrain types. The solution adopted was to estimate the models of covariances and cross-covariances (or semivariograms and cross-semivariograms) by the same procedure as described in Pardo-Iguzquiza et al. (2006) but with the method applied locally instead of globally. The correct implementation of this local estimation is the key for computational feasibility and prediction efficiency. Two parameters to be taken into account are the grid of locations on which a moving window is centred (local modelling is performed inside this window) and the size of this moving window. With respect to the latter parameter, there is a trade-off between a size small enough to make the procedure locally adaptive and large enough to produce reliable statistical estimates. The computational burden will impose limits to the distance between grid points on which the local moving window is centred. A case study with Landsat ETM+ images was used to show the implementation of the method and the result was evaluated using several statistics widely used for assessing the quality of a fused image, apart from its visual appearance
An assessment of the effectiveness of a random forest classifier for land-cover classification
No full textLand cover monitoring using remotely sensed data requires robust classification methods which allow for the accurate mapping of complex land cover and land use categories. Random forest (RF) is a powerful machine learning classifier that is relatively unknown in land remote sensing and has not been evaluated thoroughly by the remote sensing community compared to more conventional pattern recognition techniques. Key advantages of RF include: their non-parametric nature; high classification accuracy; and capability to determine variable importance. However, the split rules for classification are unknown, therefore RF can be considered to be black box type classifier. RF provides an algorithm for estimating missing values; and flexibility to perform several types of data analysis, including regression, classification, survival analysis, and unsupervised learning.In this paper, the performance of the RF classifier for land cover classification of a complex area is explored. Evaluation was based on several criteria: mapping accuracy, sensitivity to data set size and noise. Landsat-5 Thematic Mapper data captured in European spring and summer were used with auxiliary variables derived from a digital terrain model to classify 14 different land categories in the south of Spain. Results show that the RF algorithm yields accurate land cover classifications, with 92% overall accuracy and a Kappa index of 0.92. RF is robust to training data reduction and noise because significant differences in kappa values were only observed for data reduction and noise addition values greater than 50 and 20%, respectively. Additionally, variables that RF identified as most important for classifying land cover coincided with expectations. A McNemar test indicates an overall better performance of the random forest model over a single decision tree at the 0.00001 significance level
- …
