14 December 2022 in Atmospheric Measurement Techniques
Accurate automatic volcanic cloud detection by means of satellite data is a challenging task and is of great concern for both the scientific community and aviation stakeholders due to well-known issues generated by strong eruption events in relation to aviation safety and health impacts. In this context, machine learning techniques applied to satellite data acquired from recent spaceborne sensors have shown promising results in the last few years. This work focuses on the application of a neural-network-based model to Sentinel-3 SLSTR (Sea and Land Surface Temperature Radiometer) daytime products in order to detect volcanic ash plumes generated by the 2019 Raikoke eruption. A classification of meteorological clouds and of other surfaces comprising the scene is also carried out. The neural network has been trained with MODIS (Moderate Resolution Imaging Spectroradiometer) daytime imagery collected during the 2010 Eyjafjallajökull eruption. The similar acquisition channels of SLSTR and MODIS sensors and the comparable latitudes of the eruptions permit an extension of the approach to SLSTR, thereby overcoming the lack in Sentinel-3 products collected in previous mid- to high-latitude eruptions. The results show that the neural network model is able to detect volcanic ash with good accuracy if compared to RGB visual inspection and BTD (brightness temperature difference) procedures. Moreover, the comparison between the ash cloud obtained by the neural network (NN) and a plume mask manually generated for the specific SLSTR images considered shows significant agreement, with an F-measure of around 0.7. Thus, the proposed approach allows for an automatic image classification during eruption events, and it is also considerably faster than time-consuming manual algorithms. Furthermore, the whole image classification indicates the overall reliability of the algorithm, particularly for recognition and discrimination between volcanic clouds and other objects.
7 October 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The need for enhancing image spatial resolution has motivated the researchers to propose numerous super-resolution techniques, including those developed specifically for hyperspectral data. Despite significant advancements in this field attributed to deep learning, little attention has been given to evaluating the practical value of super-resolved images in specific applications. Most methods are validated in application-independent scenarios, often using simulated low-resolution images, resulting in overly optimistic conclusions. In this paper, we propose task-based evaluation strategies for hyperspectral image super-resolution and we present results obtained with various approaches that include pansharpening, multispectral–hyperspectral data fusion, and single-image super-resolution. We demonstrate that the proposed framework allows us to highlight both benefits and limitations of each method and can therefore guide the development of super-resolution techniques suitable for real-world applications.
17 October 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
In this work we address the Bidirectional Reflectance Distribution Function (BRDF) characterization of homogeneous surfaces by means of multi-angular datasets acquired with an Unmanned Aerial System (UAS) carrying a multispectral sensor (MAIA) replicating the spectral characteristics of the MultiSpectral Instrument (MSI) onboard Copernicus Sentinel-2 satellite. The UAS field campaign was performed in clear-sky conditions over two different test sites, a vegetation cover and an asphalted area, exhibiting different behaviors in terms of surface reflectance anisotropy. A dual angular approach for the processing of the reflectance measurements is examined: a conical configuration considering a cone angle of 10° (HC-RD) and a directional configuration (HD-RD) considering a cone angle of 3°. Afterwards, the retrieval of the parameters of the Ross-Li-Maignan BRDF model was implemented by a least squared fitting of the UAS reflectance measurements for each MAIA bands. The accuracy of the modelled reflectances was evaluated and the overall relative RMSE between measured and modelled reflectances was less than 10% for both test sites. The outcomes of the present study go towards the definition of a standard approach for UAS-based measurements with high angular resolution features for BRDF modelling, avoiding the well-known issues related to the use of ground-based and satellite-based instruments, and proving the UAS effectiveness in supporting calibration and validation activities of satellite missions.
10 June 2022 in EGUsphere
The accurate automatic volcanic cloud detection by means of satellite data is a challenging task and of great concern for both scientific community and stakeholder due to the well-known issues generated by a strong eruption event in relation to aviation safety and health impact. In this context, machine learning techniques applied to recent spaceborne sensors acquired data have shown promising results in the last years. This work focuses on the application of a neural network based model to Sentinel-3 SLSTR (Sea and Land Surface Temperature Radiometer) daytime products in order to detect volcanic ash plumes generated by the 2019 Raikoke eruption. The classification of the clouds and of the other surfaces composing the scene is also carried out. The neural network has been trained with MODIS (MODerate resolution Imaging Spectroradiometer) daytime imagery collected during the 2010 Eyjafjallajökull eruption. The similar acquisition channels of SLSTR and MODIS sensors and the events comparable latitudes foster the robustness of the approach, which allows overcoming the lack in SLSTR products collected in previous mid-high latitude eruptions. The results show that the neural network model is able to detect volcanic ash with good accuracy if compared with RGB visual inspection and BTD (Brightness Temperature Difference) procedure. Moreover, the comparison between the ash cloud obtained by neural network and a plume mask manually generated for the specific SLSTR considered images, shows significant agreement. Thus, the proposed approach allows an automatic image classification during eruption events, which it is also considerably faster than time-consuming manually algorithms (e.g. find the best BTD product-specific threshold). Furthermore, the whole image classification indicates an overall reliability of the algorithm, in particular for meteo-clouds recognition and discrimination from volcanic clouds. Finally, the results show that the NN developed for the SLSTR nadir view is able to properly classify also the SLSTR oblique view images.