Using remote sensing data within an optimal spatiotemporal model for invasive plant management: the case of Ailanthus altissima in the Alta Murgia National Park.

We tackle the problem of coupling a spatiotemporal model for simulating the spread and control of an invasive alien species with data coming from image processing and expert knowledge. In this study, we implement a spatially explicit optimal control model based on a reaction-diffusion equation which includes an Holling II type functional response term for modeling the density control rate. The model takes into account the budget constraint related to the control program and searches for the optimal effort allocation for the minimization of the invasive alien species density. Remote sensing and expert knowledge have been assimilated in the model to estimate the initial species distribution and its habitat suitability, empirically extracted by a land cover map of the study area. The approach has been applied to the plant species Ailanthus altissima (Mill.) Swingle within the Alta Murgia National Park. This area is one of the Natura 2000 sites under the study of the ongoing National Biodiversity Future Center (NBFC) funded by the Italian National Recovery and Resilience Plan (NRRP), and pilot site of the finished H2020 project ECOPOTENTIAL, which aimed at the integration of modeling tools and Earth Observations for a sustainable management of protected areas. Both the initial density map and the land cover map have been generated by using very high resolution satellite images and validated by means of ground truth data provided by the EU Life Alta Murgia Project (LIFE12 BIO/IT/000213), a project aimed at the eradication of A. altissima in the Alta Murgia National Park.

Satellite monitoring of bio-fertilizer restoration in olive groves affected by Xylella fastidiosa subsp. pauca.

Xylella fastidiosa subsp. pauca (Xfp), has attacked the olive trees in Southern Italy with severe impacts on the olive agro-ecosystem. To reduce both the Xfp cell concentration and the disease symptom, a bio-fertilizer restoration technique has been used. Our study applied multi-resolution satellite data to evaluate the effectiveness of such technique at both field and tree scale. For field scale, a time series of High Resolution (HR) Sentinel-2 images, acquired in the months of July and August from 2015 to 2020, was employed. First, four spectral indices from treated and untreated fields were compared. Then, their trends were correlated to meteo-events. For tree-scale, Very High Resolution (VHR) Pléiades images were selected at the closest dates of the Sentinel-2 data to investigate the response to treatments of each different cultivar. All indices from HR and VHR images were higher in treated fields than in those untreated. The analysis of VHR indices revealed that Oliarola Salentina can respond better to treatments than Leccino and Cellina cultivars. All findings were in agreement with in-field PCR results. Hence, HR data could be used to evaluate plant conditions at field level after treatments, while VHR imagery could be used to optimize treatment doses per cultivar.

A globally relevant change taxonomy and evidence-based change framework for land monitoring.

A globally relevant and standardized taxonomy and framework for consistently describing land cover change based on evidence is presented, which makes use of structured land cover taxonomies and is underpinned by the Driver-Pressure-State-Impact-Response (DPSIR) framework. The Global Change Taxonomy currently lists 246 classes based on the notation 'impact (pressure)', with this encompassing the consequence of observed change and associated reason(s), and uses scale-independent terms that factor in time. Evidence for different impacts is gathered through temporal comparison (e.g., days, decades apart) of land cover classes constructed and described from Environmental Descriptors (EDs; state indicators) with pre-defined measurement units (e.g., m, %) or categories (e.g., species type). Evidence for pressures, whether abiotic, biotic or human-influenced, is similarly accumulated, but EDs often differ from those used to determine impacts. Each impact and pressure term is defined separately, allowing flexible combination into 'impact (pressure)' categories, and all are listed in an openly accessible glossary to ensure consistent use and common understanding. The taxonomy and framework are globally relevant and can reference EDs quantified on the ground, retrieved/classified remotely (from ground-based, airborne or spaceborne sensors) or predicted through modelling. By providing capacity to more consistently describe change processes-including land degradation, desertification and ecosystem restoration-the overall framework addresses a wide and diverse range of local to international needs including those relevant to policy, socioeconomics and land management. Actions in response to impacts and pressures and monitoring towards targets are also supported to assist future planning, including impact mitigation actions.

Comparing Pixel and Object-Based Approaches to Map an Understorey Invasive Shrub in Tropical Mixed Forests.

The establishment of invasive alien species in varied habitats across the world is now recognized as a genuine threat to the preservation of biodiversity. Specifically, plant invasions in understory tropical forests are detrimental to the persistence of healthy ecosystems. Monitoring such invasions using Very High Resolution (VHR) satellite remote sensing has been shown to be valuable in designing management interventions for conservation of native habitats. Object-based classification methods are very helpful in identifying invasive plants in various habitats, by their inherent nature of imitating the ability of the human brain in pattern recognition. However, these methods have not been tested adequately in dense tropical mixed forests where invasion occurs in the understorey. This study compares a pixel-based and object-based classification method for mapping the understorey invasive shrub Lantana camara (Lantana) in a tropical mixed forest habitat in the Western Ghats biodiversity hotspot in India. Overall, a hierarchical approach of mapping top canopy at first, and then further processing for the understorey shrub, using measures such as texture and vegetation indices proved effective in separating out Lantana from other cover types. In the first method, we implement a simple parametric supervised classification for mapping cover types, and then process within these types for Lantana delineation. In the second method, we use an object-based segmentation algorithm to map cover types, and then perform further processing for separating Lantana. The improved ability of the object-based approach to delineate structurally distinct objects with characteristic spectral and spatial characteristics of their own, as well as with reference to their surroundings, allows for much flexibility in identifying invasive understorey shrubs among the complex vegetation of the tropical forest than that provided by the parametric classifier. Conservation practices in tropical mixed forests can benefit greatly by adopting methods which use high resolution remotely sensed data and advanced techniques to monitor the patterns and effective functioning of native ecosystems by periodically mapping disturbances such as invasion.

Detection of changes in semi-natural grasslands by cross correlation analysis with WorldView-2 images and new Landsat 8 data.

Focusing on a Mediterranean Natura 2000 site in Italy, the effectiveness of the cross correlation analysis (CCA) technique for quantifying change in the area of semi-natural grasslands at different spatial resolutions (grain) was evaluated. In a fine scale analysis (2 m), inputs to the CCA were a) a semi-natural grasslands layer extracted from an existing validated land cover/land use (LC/LU) map (1:5000, time T1) and b) a more recent single date very high resolution (VHR) WorldView-2 image (time T2), with T2 > T1. The changes identified through the CCA were compared against those detected by applying a traditional post-classification comparison (PCC) technique to the same reference T1 map and an updated T2 map obtained by a knowledge driven classification of four multi-seasonal Worldview-2 input images. Specific changes observed were those associated with agricultural intensification and fires. The study concluded that prior knowledge (spectral class signatures, awareness of local agricultural practices and pressures) was needed for the selection of the most appropriate image (in terms of seasonality) to be acquired at T2. CCA was also applied to the comparison of the existing T1 map with recent high resolution (HR) Landsat 8 OLS images. The areas of change detected at VHR and HR were broadly similar with larger error values in HR change images.

A multiscale expectation-maximization semisupervised classifier suitable for badly posed image classification.

This paper deals with the problem of badly posed image classification. Although underestimated in practice, bad-posedness is likely to affect many real-world image classification tasks, where reference samples are difficult to collect (e.g., in remote sensing (RS) image mapping) and/or spatial autocorrelation is relevant. In an image classification context affected by a lack of reference samples, an original inductive learning multiscale image classifier, termed multiscale semisupervised expectation maximization (MSEM), is proposed. The rationale behind MSEM is to combine useful complementary properties of two alternative data mapping procedures recently published outside of image processing literature, namely, the multiscale modified Pappas adaptive clustering (MPAC) algorithm and the sample-based semisupervised expectation maximization (SEM) classifier. To demonstrate its potential utility, MSEM is compared against nonstandard classifiers, such as MPAC, SEM and the single-scale contextual SEM (CSEM) classifier, besides against well-known standard classifiers in two RS image classification problems featuring few reference samples and modestly useful texture information. These experiments yield weak (subjective) but numerous quantitative map quality indexes that are consistent with both theoretical considerations and qualitative evaluations by expert photointerpreters. According to these quantitative results, MSEM is competitive in terms of overall image mapping performance at the cost of a computational overhead three to six times superior to that of its most interesting rival, SEM. More in general, our experiments confirm that, even if they rely on heavy class-conditional normal distribution assumptions that may not be true in many real-world problems (e.g., in highly textured images), semisupervised classifiers based on the iterative expectation maximization Gaussian mixture model solution can be very powerful in practice when: 1) there is a lack of reference samples with respect to the problem/model complexity and 2) texture information is considered negligible (i.e., a piecewise constant image model holds).