Giorgio Licciardi

In this article, we elaborate on the scientific outcomes of the 2021 Data Fusion Contest (DFC2021), which was organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society, on the subject of geospatial artificial intelligence for social good. The ultimate objective of the contest was to model the state and changes of artificial and natural environments from multimodal and multitemporal remotely sensed data towards sustainable developments. DFC2021 consisted of two challenge tracks: Detection of settlements without electricity (DSE) and multitemporal semantic change detection. We focus here on the outcome of the DSE track. This article presents the corresponding approaches and reports the results of the best-performing methods during the contest.

Recent works have demonstrated that particulate matter (PM) and specific meteorological conditions played an important role in the airborne transmission of the SARS-CoV-1 and MERS-CoV. These studies suggest that these parameters could influence the transmission of SARS-CoV-2. In the present investigation, we sought to investigate the association between air pollution, meteorological data, and the Lombardy region COVID-19 outbreak caused by SARS-CoV-2. We considered the number of detected infected people at the regional and provincial scale from February to March 2020. Air pollution data were collected over the Lombardy region, nominally, sulphur dioxide, ammonia, nitrogen dioxide, nitrogen monoxide, carbon monoxide, ozone, and suspended particulate matter measuring less than 10 μm (PM10) and less than 2.5 μm (PM2.5). Meteorological data have been collected over the same region for temperature, relative humidity, and wind speed. In this work, we evaluated the combined impact of environmental pollutants and climate conditions on the COVID-19 outbreak. The analysis evidenced a positive correlation between spatial distribution of COVID-19 infection cases with high concentrations of suspended particulate matter and a negative relationship with ozone. Moreover, suspended particulate matter concentration peaks in February correlated positively with infection peaks according to the virus incubation period. The obtained results suggested that seasonal weather conditions and concentration of air pollutants seemed to influence COVID-19 epidemics in Lombardy region.

Hyperspectral analysis is a well-established technique that can be suitably implemented in several application fields, including materials science. This approach allows us to deal with data samples containing spatial and spectral information at very high resolution, thus enabling us to evaluate materials properties at a nanoscale level. As a proof of concept, hyperspectral imaging was here considered to investigate 3D printed polymer matrix composites, considering graphene oxide (GO) as a nanofiller. Commercial polycaprolactone and polylactic acid filaments were firstly treated with GO to be then printed into testing specimens. Raman analysis was performed to assess the GO distribution on samples surface by mapping different regions of interest and the collected data were the input of a custom-made algorithm for hyperspectral image analysis, tailored to detect the GO signature. Findings showed a valuable matching to Raman maps and were also characterized by the positive feature of avoiding to set specific conditions to perform the investigation as GO Raman distribution was carried out by fixing the wavenumber at 1580 cm⁻¹, which is representative of the G band of the nanofiller. This occurrence might lead to an uneven intensity representation related to possible peak shifts which can bias the acquired results. Differently, hyperspectral imaging needs a minimal set of data input, i.e., the spectral signatures of neat materials, to directly identify the searched nanomaterial. More in-depth investigations need to be performed to fully validate the proposed approach, but the here presented results already show the potential and versatility of hyperspectral analysis in the materials science field.

Hyperspectral remote sensing is based on measuring the scattered and reflected electromagnetic signals from the Earth’s surface emitted by the Sun. The received radiance at the sensor is usually degraded by atmospheric effects and instrumental (sensor) noises which include thermal (Johnson) noise, quantization noise, and shot (photon) noise. Noise reduction is often considered as a preprocessing step for hyperspectral imagery. In the past decade, hyperspectral noise reduction techniques have evolved substantially from two dimensional bandwise techniques to three dimensional ones, and varieties of low-rank methods have been forwarded to improve the signal to noise ratio of the observed data. Despite all the developments and advances, there is a lack of a comprehensive overview of these techniques and their impact on hyperspectral imagery applications. In this paper, we address the following two main issues; (1) Providing an overview of the techniques developed in the past decade for hyperspectral image noise reduction; (2) Discussing the performance of these techniques by applying them as a preprocessing step to improve a hyperspectral image analysis task, i.e., classification. Additionally, this paper discusses about the hyperspectral image modeling and denoising challenges. Furthermore, different noise types that exist in hyperspectral images have been described. The denoising experiments have confirmed the advantages of the use of low-rank denoising techniques compared to the other denoising techniques in terms of signal to noise ratio and spectral angle distance. In the classification experiments, classification accuracies have improved when denoising techniques have been applied as a preprocessing step.

Managing transmission and storage of hyperspectral (HS) images can be extremely difficult. Thus, the dimensionality reduction of HS data becomes necessary. Among several dimensionality reduction techniques, transform-based have found to be effective for HS data. While spatial transformation techniques provide good compression rates, the choice of the spectral decorrelation approaches can have strong impact on the quality of the compressed image. Since HS images are highly correlated within each spectral band and in particular across neighboring bands, the choice of a decorrelation method allowing to retain as much information content as possible is desirable. From this point of view, several methods based on PCA and Wavelet have been presented in the literature. In this paper, we propose the use of NLPCA transform as a method to reduce the spectral dimensionality of HS data. NLPCA represents in a lower dimensional space the same information content with less features than PCA. In these terms, aim of this research is focused on the analysis of the results obtained through the spectral decorrelation phase rather than taking advantage of both spectral and spatial compression. Experimental results assessing the advantage of NLPCA with respect to standard PCA are presented on four different HS datasets.

In image processing, it is commonly assumed that the model ruling spectral mixture in a given hyperspectral pixel is linear. However, in many real life cases, the different objects and materials determining the observed spectral signatures overlap in the same scene, resulting in nonlinear mixture. This is particularly evident in volcanoes-related imagery, where both airborne plumes of effluents and surface deposit of volcanic ejecta can be mixed in the same observation line of sight. To tackle this intrinsic complexity, in this paper, we perform a pilot test using Nonlinear Principal Component Analysis (NLPCA) as a nonlinear transformation, that projects a hyperspectral image onto a reduced-dimensionality feature space. The use of NLPCA is twofold: (1) it is used to reduce the dimensionality of the original spectral data and (2) it performs a linearization of the information, thus allowing the effective use of successive linear approaches for spectral unmixing. The proposed method has been tested on two different hyperspectral datasets, dealing with active volcanoes at the time of the observation. The dimensionality of the spectroscopic problem is reduced of up to 95% (ratio of the elements of compressed nonlinear vectors and initial spectral inputs), by the use of NLPCA. The selective use of an atmospheric correction pre-processing is applied, demonstrating how individual plume and volcanic surface deposit components can be discriminated, paving the way to future application of this method.

This letter presents a novel technique for the forecast of the ground horizontal irradiance (GHI) from satellite-based images. To enhance the forecast accuracy, spatial information in addition to temporal information has been considered. This produced an increase in the computational load of the forecast process. Dimensionality reduction techniques based on nonlinear principal component analysis (PCA) are used to project the original data set into low-dimension feature space. A multilayer feedforward neural network classifier is used to model the signal through a training operation involving past history of the considered spatiotemporal signal. Experiments have been carried out on two different data sets. Comparisons with classical forecasting techniques demonstrate that the introduction of the spatial information permits to obtain better short-term forecast measurements for all types of sky conditions. Moreover, further analysis demonstrates that, compared with linear PCA, the nonlinear PCA is more appropriate for dimensionality reduction of spatiotemporal GHI data set.