Victor F. Rodriguez-Galiano

Downscaling Landsat 7 ETM+ thermal imagery using land surface temperature and NDVI images

Thermal infrared (TIR) satellite images and derived land surface temperature (LST) are variables of great interest in many remote sensing applications. However, the TIR band has a spatial resolution which is coarser than the other multispectral bands for a given satellite sensor (visible, near and shortwave infrared bands); therefore, the spatial resolution of the retrieved LST from available satellite-borne sensors is not accurate enough to be used in certain applications. The application of a method is shown here for obtaining LST images with enhanced spatial resolution using the LST at a coarser resolution and the Normalized Difference Vegetation Index (NDVI) of the same scene using Downscaling Cokriging (DCK). A LST image with perfect coherence was obtained by applying this method to a Landsat 7 ETM+ image. This implies that, if the downscaled LST image is degraded to its original resolution, the degraded image obtained is identical to the original. Hence high spatial resolution LST images were obtained without altering the original radiometry with the inclusion of artefacts. Moreover, the performance of DCK was compared with global and local TSHARP methods. The RMSE of the sharpened images were 0.85, 0.92 and 1.1 K, respectively.

Predictive modelling of gold potential with the integration of multisource information based on random forest: a case study on the Rodalquilar area, Southern Spain

Mineral 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 considered.

Categorical Indicator Kriging for assessing the risk of groundwater nitrate pollution: The case of Vega de Granada aquifer (SE Spain)

Groundwater nitrate pollution associated with agricultural activity is an important environmental problem in the management of this natural resource, as acknowledged by the European Water Framework Directive. Therefore, specific measures aimed to control the risk of water pollution by nitrates must be implemented to minimise its impact on the environment and potential risk to human health. The spatial probability distribution of nitrate contents exceeding a threshold or limit value, established within the quality standard, will be helpful to managers and decision-makers. A methodology based on non-parametric and non-linear methods of Indicator Kriging was used in the elaboration of a nitrate pollution categorical map for the aquifer of Vega de Granada (SE Spain). The map has been obtained from the local estimation of the probability that a nitrate content in an unsampled location belongs to one of the three categories established by the European Water Framework Directive: CL. 1 good quality [Min - 37.5 ppm], CL. 2 intermediate quality [37.5-50 ppm] and CL. 3 poor quality [50 ppm - Max]. The obtained results show that the areas exceeding nitrate concentrations of 50 ppm, poor quality waters, occupy more than 50% of the aquifer area. A great proportion of the areas municipalities are located in these poor quality water areas. The intermediate quality and good quality areas correspond to 21% and 28%, respectively, but with the highest population density. These results are coherent with the experimental data, which show an average nitrate concentration value of 72 ppm, significantly higher than the quality standard limit of 50 ppm. Consequently, the results suggest the importance of planning actions in order to control and monitor aquifer nitrate pollution.

Intercomparison of satellite sensor land surface phenology and ground phenology in Europe

Land 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 interannual variation. LSP obtained from the whole time series of Medium-Resolution Imaging Spectrometer data was compared to thousands of deciduous tree ground phenology records of the Pan European Phenology network (PEP725). Correlations observed between the interannual 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 spatiotemporal 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 nonlinear multivariate models, providing, for the first time, the ability to predict accurately the date of leaf unfolding (autumn coloring) across Europe (root-mean-square error of 5.97 days (6.75 days) over 365 days).

Evaluation of different machine learning methods for land cover mapping of a Mediterranean area using multi-seasonal landsat images and digital terrain models

Land cover monitoring using digital Earth data requires robust classification methods that allow the accurate mapping of complex land cover categories. This paper discusses the crucial issues related to the application of different up-to-date machine learning classifiers: classification trees (CT), artificial neural networks (ANN), support vector machines (SVM) and random forest (RF). The analysis of the statistical significance of the differences between the performance of these algorithms, as well as sensitivity to data set size reduction and noise were also analysed. 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 cover categories in south Spain. Overall, statistically similar accuracies of over 91% were obtained for ANN, SVM and RF. However, the findings of this study show differences in the accuracy of the classifiers, being RF the most accurate classifier with a very simple parameterization. SVM, followed by RF, was the most robust classifier to noise and data reduction. Significant differences in their performances were only reached for thresholds of noise and data reduction greater than 20% (noise, SVM) and 25% (noise, RF), and 80% (reduction, SVM) and 50% (reduction, RF), respectively.

Incorporating the downscaled landsat TM thermal band in land-cover classification using random forest

Thermal information is a key parameter in numerous remote sensing applications and environmental studies. The aim of this study was to assess the improvement that incorporating the TIR band of the Landsat-5 TM sensor has in the classification of a large heterogeneous landscape located in the south of Spain. To incorporate the thermal data into the classification process, the TIR band (with spatial resolution of 120 m) was downscaled by means of a geostatistical method (Downscaling Cokriging) to achieve a spatial resolution of 30 meters. Then, the thermal information was evaluated for contribution to overall and per-class map accuracy using Random Forest classification. The addition of the TIR band to single-season and multi-seasonal Random Forest models leads to an increase in the overall accuracy of 10 percent and 5 percent, and to an increase in the kappa index of 10 percent and 5 percent, respectively. The increase in per-class kappa for the thermal, single-season, Random Forest model ranged from ?3 percent to 47 percent and 0 percent to 12 percent for the thermal, multi-seasonal model.

Characterising the land surface phenology of Europe using decadal MERIS data

Land surface phenology (LSP), the study of the timing of recurring cycles of changes in the land surface using time-series of satellite sensor-derived vegetation indices, is a valuable tool for monitoring vegetation at global and continental scales. Characterisation of LSP and its spatial variation is required to reveal and predict ongoing changes in Earth system dynamics. This study presents and analyses the LSP of the pan-European continent for the last decade, considering three phenological metrics: onset of greenness (OG), end of senescence (EOS), and length of season (LS). The whole time-series of Multi-temporal Medium Resolution Imaging Spectrometer (MERIS) Terrestrial Chlorophyll Index (MTCI) data at 1 km spatial resolution was used to estimate the phenological metrics. Results show a progressive pattern in phenophases from low to high latitudes. OG dates are distributed widely from the end of December to the end of May. EOS dates range from the end of May to the end of January and the spatial distribution is generally the inverse of that of the OG. Shorter growing seasons (approximately three months) are associated with rainfed croplands in Western Europe, and forests in boreal and mountainous areas. Maximum LS values appear in the Atlantic basin associated with grasslands. The LSP maps presented in this study are supported by the findings of a previous study where OG and EOS estimates were compared to those of the pan-European phenological network at certain locations corresponding to numerous observations of deciduous tree plant species. Moreover, the spatio-temporal pattern of the OG and EOS produced close agreement with the dates of deciduous tree leaf unfolding and autumnal colouring, respectively (pseudo R-squared equal to 0.70 and 0.71 and root mean square error of six days (over 365 days)).

Extreme warm temperatures alter forest phenology and productivity in Europe

Recent climate warming has shifted the timing of spring and autumn vegetation phenological events in the temperate and boreal forest ecosystems of Europe. In many areas spring phenological events start earlier and autumn events switch between earlier and later onset. Consequently, the length of growing season in mid and high latitudes of European forest is extended. However, the lagged effects (i.e. the impact of a warm spring or autumn on the subsequent phenological events) on vegetation phenology and productivity are less explored. In this study, we have (1) characterised extreme warm spring and extreme warm autumn events in Europe during 2003-2011, and (2) investigated if direct impact on forest phenology and productivity due to a specific warm event translated to a lagged effect in subsequent phenological events. We found that warmer events in spring occurred extensively in high latitude Europe producing a significant earlier onset of greening (OG) in broadleaf deciduous forest (BLDF) and mixed forest (MF). However, this earlier OG did not show any significant lagged effects on autumnal senescence. Needleleaf evergreen forest (NLEF), BLDF and MF showed a significantly delayed end of senescence (EOS) as a result of extreme warm autumn events; and in the following years spring phenological events, OG started significantly earlier. Extreme warm spring events directly led to significant (p=0.0189) increases in the productivity of BLDF. In order to have a complete understanding of ecosystems response to warm temperature during key phenological events, particularly autumn events, the lagged effect on the next growing season should be considered.

Regression trees for modeling geochemical data-An application to Late Jurassic carbonates (Ammonitico Rosso)

Research 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 behavior 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 ?18O, 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.

A comparative assessment of different methods for Landsat 7/ETM+ pansharpening

This article compares a set of relevant methods, based on different mathematical approaches, for Landsat 7 Enhanced Thematic Mapper Plus (ETM+) pansharpening. These are classical procedures such as principal component analysis and fast intensity hue saturation; methods based on wavelet transforms, such as wavelet à trous, additive wavelet luminance proportional and multidirectional–multiresolution methods; a method of a geostatistical nature, called downscaling cokriging (DCK); and finally, a Bayesian method (1cor). The comparison of the fused images is based on the qualitative and quantitative evaluation of their spatial and spectral characteristics by calculating statistical indices and parameters that measure the quality and coherence of the images. Moreover, the quality of the spectral information is studied indirectly by means of the Iterative Self-Organizing Data Analysis Technique (ISODATA) classification of the products of fusion. The results show that DCK and 1cor methods yielded better results than the wavelet-based methods. Particularly, DCK does not introduce artefacts in the estimation of the digital numbers corresponding with the source multispectral image and, therefore, it can be considered as the most coherent method.