Search

Highlights • Inappropriate image segmentation parameters often lead to sub-optimal results. • The new SegOptim R package allows to optimize image segmentation parameters. • SegOptim was tested in very high - high spatial resolution images in six test sites. • Genetic Algorithms optimization improves Geographic Object-based Image Analysis. • Integration between image segmentation and supervised classification is improved. Abstract Geographic Object-based Image Analysis (GEOBIA) is increasingly used to process high-spatial resolution imagery, with applications ranging from single species detection to habitat and land cover mapping. Image segmentation plays a key role in GEOBIA workflows, allowing to partition images into homogenous and mutually exclusive regions. Nonetheless, segmentation techniques require a robust parameterization to achieve the best results. Frequently, inappropriate parameterization leads to sub-optimal results and difficulties in comparing distinct methods. Here, we present an approach based on Genetic Algorithms (GA) to optimize image segmentation parameters by using the performance scores from object-based classification, thus allowing to assess the adequacy of a segmented image in relation to the classification problem. This approach was implemented in a new R package called SegOptim , in which several segmentation algorithms are interfaced, mostly from open-source software (GRASS GIS, Orfeo Toolbox, RSGISLib, SAGA GIS , TerraLib), but also from proprietary software (ESRI ArcGIS). SegOptim also provides access to several machine-learning classification algorithms currently available in R, including Gradient Boosted Modelling, Support Vector Machines, and Random Forest. We tested our approach using very-high to high spatial resolution images collected from an Unmanned Aerial Vehicle (0.03 – 0.10 m), WorldView-2 (2 m), RapidEye (5 m) and Sentinel-2 (10 – 20 m) in six different test sites located in northern Portugal with varying environmental conditions and for different purposes, including invasive species detection and land cover mapping. The results highlight the added value of our novel comparison of image segmentation and classification algorithms. Overall classification performances (assessed through cross-validation with the Kappa index) ranged from 0.85 to 1.00. Pilot-tests show that our GA-based approach is capable of providing sound results for optimizing the parameters of different segmentation algorithms, with benefits for classification accuracy and for comparison across techniques. We also verified that no particular combination of an image segmentation and a classification algorithm is suited for all the tasks/objectives. Consequently, it is crucial to compare and optimize available methods to understand which one is more suited for a certain objective. Our approach allows a closer integration between the segmentation and classification stages, which is of high importance for GEOBIA workflows. The results from our tests confirm that this integration has benefits for comparing and optimizing both processes. We discuss some limitations of the SegOptim approach (and potential solutions) as well as a future roadmap to expand its current functionalities. [ABSTRACT FROM AUTHOR]

In this study, hyperspectral reflectance (HySR) data derived from a handheld spectroradiometer were used to assess the water status of three grapevine cultivars in two sub-regions of Douro wine region during two consecutive years. A large set of potential predictors derived from the HySR data were considered for modelling/predicting the predawn leaf water potential (Ψ pd ) through different statistical and machine learning techniques. Three HySR vegetation indices were selected as final predictors for the computation of the models and the in-season time trend was removed from data by using a time predictor. The vegetation indices selected were the Normalized Reflectance Index for the wavelengths 554 nm and 561 nm (NRI 554;561 ), the water index (WI) for the wavelengths 900 nm and 970 nm, and the D1 index which is associated with the rate of reflectance increase in the wavelengths of 706 nm and 730 nm. These vegetation indices covered the green, red edge and the near infrared domains of the electromagnetic spectrum. A large set of state-of-the-art analysis and statistical and machine-learning modelling techniques were tested. Predictive modelling techniques based on generalized boosted model (GBM), bagged multivariate adaptive regression splines (B-MARS), generalized additive model (GAM), and Bayesian regularized neural networks (BRNN) showed the best performance for predicting Ψ pd , with an average determination coefficient (R 2 ) ranging between 0.78 and 0.80 and RMSE varying between 0.11 and 0.12 MPa. When cultivar Touriga Nacional was used for training the models and the cultivars Touriga Franca and Tinta Barroca for testing (independent validation), the models performance was good, particularly for GBM (R 2 = 0.85; RMSE = 0.09 MPa). Additionally, the comparison of Ψ pd observed and predicted showed an equitable dispersion of data from the various cultivars. The results achieved show a good potential of these predictive models based on vegetation indices to support irrigation scheduling in vineyard. [ABSTRACT FROM AUTHOR]

Abstract: Water and energy balance interactions with vegetation in mountainous terrain are influenced by topographic effects, spatial variation in vegetation type and density, and water availability. This is the case for the mountainous areas of northern Portugal, where ancestral irrigated meadows (lameiros) are a main component of a complex vegetation mosaic. The widely used surface energy balance model METRIC was applied to four Landsat images to determine the spatial and temporal distribution of the energy balance terms in the identified land cover types (LCT). A discussion on the variability of evapotranspiration (ET) through the various vegetation types was supported by a comparison between the respective crop coefficients and those available in the literature corresponding to the LCT, which has shown the appropriateness of METRIC estimates of ET. METRIC products derived from images of May and June – NDVI, surface temperature, net radiation, soil heat flux, sensible heat flux, and ET – were used to characterize the LCTs, through application of principal component analysis. Three principal components explained the variance of observed variables and their varimax rotated loadings allowed a good explanation of the behaviour of the explanatory variables in association with the LCTs. Information gained contributes to improve the characterization of the study area and may further support conservation and management of these mountain landscapes. [Copyright &y& Elsevier]

Abstract: Image data from Earth Observation Satellites (EOS) were used to analyse mountain landscape changes in Northeast Portugal. Three Landsat images, from April 30th 1979, March 14th 1989 and May 29th 2002 were used. A supervised classification was performed for each image based on the radiometric information and the Normalised Difference Vegetation Index (NDVI). Eleven classes were selected considering the main land cover types in the region. The classification results showed high overall accuracy (above 92.5%) and kappa coefficient (above 0.91). Broadly, the range of dates of the Landsat images used allowed for the differentiation between classes. Nevertheless, some problems occurred in differentiating between classes of forest and shrub vegetation due to similar characteristics and vegetation conditions in some periods of the year, and also due to the effects of topographic shadows associated to mountain areas. Meadows and annual crops were the classes having greater changes from 1979 to 2002: meadows area increased 60% while annual crops decreased 43.5%. The increase in meadows area was likely due to policies supporting agroenvironmental conservation and autochthon bovine livestock production. Differently, the decrease in annual crops was likely due to the loss of economical competitiveness of main annual crops and to the rural population decrease and ageing, which favoured the replacement of arable lands by permanent meadows. These results may help developing policies and measures for sustainable management of traditional mountain rural landscapes. [Copyright &y& Elsevier]