Search

Remote sensing products are typically assessed using a single accuracy estimate for the entire map, despite significant variations in accuracy across different map areas or classes. Estimating per-pixel uncertainty is a major challenge for enhancing the usability and potential of remote sensing products. This paper introduces the dataDriven open access tool, a novel statistical design-based approach that specifically addresses this issue by estimating per-pixel uncertainty through a bootstrap resampling procedure. Leveraging Sentinel-2 remote sensing data as auxiliary information, the capabilities of the Google Earth Engine cloud computing platform, and the R programming language, dataDriven can be applied in any world region and variables of interest. In this study, the dataDriven tool was tested in the Rincine forest estate study area—eastern Tuscany, Italy—focusing on volume density as the variable of interest. The average volume density was 0.042, corresponding to 420 m3 per hectare. The estimated pixel errors ranged between 93 m3 and 979 m3 per hectare and were 285 m3 per hectare on average. The ability to produce error estimates for each pixel in the map is a novel aspect in the context of the current advances in remote sensing and forest monitoring and assessment. It constitutes a significant support in forest management applications and also a powerful communication tool since it informs users about areas where map estimates are unreliable, at the same time highlighting the areas where the information provided via the map is more trustworthy. In light of this, the dataDriven tool aims to support researchers and practitioners in the spatially exhaustive use of remote sensing-derived products and map validation. [ABSTRACT FROM AUTHOR]

On 13 January 2012, the Italian vessel Costa Concordia wrecked on the shore of Giglio Island, about 15 km off the coast of southern Tuscany (Italy), causing the loss of 32 lives. It is considered one of the worst disasters in maritime history. Salvage operations started immediately after the wreck with the coordination of the Italian National Civil Protection Department and the technological support of several Research Centers, which were activated for the management of the consequent emergency phase. A multi-parametric and multiplatform monitoring system was promptly implemented, involving several advanced remote sensing techniques, among which was Infrared Thermography (IRT). In this framework, IRT monitoring was performed during a 35-day period (25 January–1 March 2012), using a terrestrial, hand-held thermal camera. Six different thermal images were acquired daily from the island's coastline in three different positions, both in daylight and night times. The aim was to detect thermal anomalies connected to possible deformations of the vessel and oil spills. Between 3–4 February, IRT successfully revealed on oil spill drifting from the stern of the wreck towards the island harbor. Furthermore, the wreck's thermal dilatation was also analyzed during a 24-day close-range monitoring, providing interesting insights for the interpretation of the deformation monitoring results. This paper presents the outcomes of these innovative and experimental monitoring activities, with the aim of testing the potential of IRT as a versatile and operative tool to be used in maritime and environmental disaster response. [ABSTRACT FROM AUTHOR]

In this paper litho-sedimentological and morphodynamic maps of the coastal sector belonging to the Pisa Province are presented as an example of how increasing the accessibility to data on lithology, sedimentology, and morphodynamics may lead to a better approach to coastal management. The database used to build the maps includes an original rendering of remote sensing data (aerial imagery) and new field data (geologic survey), as well as data retrieved from the scientific literature (grain-size and past coastline positions). The maps show that the geometry of beach ridges is an indication of the evolution of the Arno River delta in the last 3000 years, highlighting the relationships between geological aspects and morphodynamic features. The maps represent the synthesis of different data available in the database, and they may be a useful support to coastal management as they are more easily understandable and straightforward than the database from which are created. [ABSTRACT FROM AUTHOR]

Copyright of Virtual Archaeology Review is the property of Virtual Archaeology Review and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Monitoring soil organic carbon (SOC) typically assumes conducting a labor-intensive soil sampling campaign, followed by laboratory testing, which is both expensive and impractical for generating useful, spatially continuous data products. The present study leverages the power of machine learning (ML) and, in particular, deep neural networks (DNNs) for segmentation, as well as satellite imagery, to estimate the SOC remotely. We propose a new two-stage pipeline for remote SOC estimation, which relies on using a DNN trained to classify land cover to perform feature extraction, while the SOC estimation is performed by a different ML model. The first stage is an image segmentation DNN with the U-Net architecture, which is trained to estimate the land cover for an observed geographical region, based on multi-spectral images taken by the Sentinel-2 satellite constellation. This estimator is subsequently used to extract the latent feature vector for each of the output pixels, by rolling back from the output (dense) layer of the U-Net and accessing the last available convolutional layer of the same dimension as our desired output. The second stage is trained on a set of feature vectors extracted at the coordinates for which manual SOC measurements exist. We tested a variety of ML models and report on their performance. Using the best extremely randomized trees model, we generated a spatially continuous map of SOC estimations for the region of Tuscany, in Italy, with a resolution of 10 m, to share with the researchers as a means of validating the results and to demonstrate the efficiency of the proposed approach, which can can easily be scaled to create a global continuous SOC map. [ABSTRACT FROM AUTHOR]

The current paper presents the development and testing of a multi-step methodology which integrates remotely sensed and ancillary data to estimate olive (Olea europaea L.) fruit yield in Tuscany (Central Italy). The processing of very high resolution (Ikonos) and high resolution (Landsat ETM+) images provides a map of olive tree canopy cover fraction for all Tuscany olive yards, which is used to extract olive tree NDVI values from MODIS imagery. The combination of these values with standard meteorological data within a modified parametric model (C-Fix) enables the prediction of daily olive tree gross primary production (GPP) for ten years (2000–2009). These GPP estimates are then joint to the respiration estimates of a bio-geochemical model (BIOME-BGC) to simulate olive tree net primary production (NPP). The NPP accumulated over proper periods of the ten growing seasons is finally converted into olive fruit yield, whose accuracy is assessed through comparison with provincial statistics. The methodology is only partly capable of capturing spatial and temporal olive fruit yield variability at province level, but can accurately reproduce inter-year yield variation over the entire region. The paper concludes with a discussion of the results achieved and with considerations on the research prospects. [Copyright &y& Elsevier]

Machine learning-based methodologies have depicted remarkable performance in digital processing of remote sensing imagery. In this work, we propose an integration of hazard susceptibility and vulnerability assessment in flood risk mapping using a CNN—based methodological framework. For this reason, we used nine predictor variables and a flood inventory from past flood events in a part of Tuscany region to train the model. Following a successful learning procedure, the performance of the proposed model was evaluated on a test dataset and depicted a promising prediction accuracy (95%). The analysis of the flood susceptibility map indicated that 4.7 and 2% of the entire study area depict very high and high susceptibility to future flood occurrences, respectively, corresponding to total areas of 44.06 and 19.33 km2. Flood risk map depicts those land cover categories that will be severely affected in a future flood event. Among them, a large part of Livorno and a few industrial buildings were highlighted as areas of very high risk. [ABSTRACT FROM AUTHOR]

• A modelling strategy is applied to estimate net forest carbon fluxes in tuscany. • Forest NPP and NEE are predicted at high spatial resolution (23 m). • NPP is assessed versus ground measurements of GSV current annual increment. • NEE is validated versus integrated eddy covariance flux tower observations. This paper presents the application of a recently proposed modelling strategy to yield high spatial resolution estimates of net forest carbon fluxes in Tuscany (Central Italy). The simulation of forest net primary production (NPP) and net ecosystem production (NEP) is based on the combination of remotely sensed and ancillary data which describe the main characteristics of local environment and vegetation. Distinctively, the methodology is driven by a map of growing stock volume (GSV) having a pixel size of 23 × 23 m2 and can therefore yield correspondingly high spatial resolution estimates of forest NPP and NEP. An advancement of the original methodology is also proposed based on the availability of a recently produced soil organic carbon map of Tuscany informative about biomass decomposition (heterotrophic respiration). The modified modelling strategy is applied over the period 2001–2005 and the obtained estimates are assessed against: i) ground observations of GSV current annual increment (CAI) collected for over 600 plots during the last National Forest Inventory of Italy; ii) a high spatial resolution reference NEP map obtained for a Mediterranean pine forest (San Rossore) by the integration of eddy covariance flux data and local CAI observations. Considering the complexity of the simulated processes and of the examined environment, the estimation accuracy achieved is satisfactory for both NPP and NEP. This supports the possibility of applying the proposed modelling strategy to estimate net carbon fluxes at high spatial resolution in other forest environments. [ABSTRACT FROM AUTHOR]

• An operational method to map soil carbon content (SOC) is applied in Tuscany. • It is based on the combination of ground, ancillary and remote sensing datasets. • The method is tested versus all measurements and through a leave-one-out approach. • The final map reproduces the SOC observations and follows main ecosystem features. The organic carbon stored in the topsoil is an essential component of the global carbon cycle which should be quantified for a variety of purposes. The current paper proposes a new approach to map the amount of organic carbon stored in the 0.3 m topsoil (SOC), based on the statistical combination of a large number of ground observations with ancillary and remote sensing data. This approach is applied and tested in Tuscany, a region of Central Italy that is characterised by extremely diversified and heterogeneous environmental features. More than 3500 soil samples were collected and made available for the purpose, together with a soil map, meteorological data, a land use map and MODIS Normalised Difference Vegetation Index (NDVI) imagery. This information was processed by advanced statistical methods to yield a final map which describes the SOC spatial distribution in the region with a spatial resolution of 250 m. The map well reproduces the SOC variability in the region, showing higher SOC values for forests with respect to grasslands and croplands and SOC peaks related to peats and acidic soils. The accuracy assessment, carried out both versus all ground observations and by a leave-one-out cross validation strategy, testifies to the high quality of the SOC map, which has a global RMSE comprised between 17.5 and 32.3 t ha−1. The map is also accompanied by per-pixel estimates of error variance which are informative on the uncertainty of SOC prediction. [ABSTRACT FROM AUTHOR]

Geo‐hydrological phenomena, including gullies, contribute significantly to soil erosion and land degradation. To address this, proper management of basins and hillslopes should consider the mechanism, timing, and location of gully development and how gullies interact with other hillslope processes. Yet, conventional modelling techniques for such processes are rare, frequently being limited to applications of only single processes and typically requiring high‐resolution input data. Further, existing tools for characterizing basins and hillslopes tend to be based on static descriptions of geo‐environmental conditions, and thus are not effective for modelling changes such as the seasonal triggering conditions of gully phenomena over time. This study proposes a method to integrate open remote sensing data (Sentinel‐2) and an existing modelling tool (LANDPLANER) using simplified input data to better predict and forecast gullies' spatial and temporal occurrence. The study investigates the seasonal conditions responsible for the triggering of gullies at the catchment scale using different erosion modelling schema in the Toscana region of Central Italy. Geomorphological gully inventory data were collected and used as benchmarks to test the proposed approach. The results show that the occurrence of gully erosion in the studied region changes seasonally, and the proposed method was able to effectively discriminate spatial and temporal differences of the gully phenomena. The proposed method can be applied to similar regions worldwide, allowing for the investigation of gully erosion over time, even in places with limited data availability. [ABSTRACT FROM AUTHOR]

Remote sensing has become an important mean to assess crop areas, specially for the identification of crop types. Google Earth Engine (GEE) is a free platform that provides a large number of satellite images from different constellations. Moreover, GEE provides pixel-based classifiers, which are used for mapping agricultural areas. The objective of this work is to evaluate the performance of different classification algorithms such as Minimum Distance (MD), Random Forest (RF), Support Vector Machine (SVM), Classification and Regression Trees (CART) and Na¨ıve Bayes (NB) on an agricultural area in Tuscany (Italy). Four different scenarios were implemented in GEE combining different information such as optical and Synthetic Aperture Radar (SAR) data, indices and time series. Among the five classifiers used the best performers were RF and SVM. Integrating Sentinel-1 (S1) and Sentinel-2 (S2) slightly improves the classification in comparison to the only S2 image classifications. The use of time series substantially improves supervised classifications. The analysis carried out so far lays the foundation for the integration of time series of SAR and optical data. [ABSTRACT FROM AUTHOR]