In the perspective of long and dense time-series analyses for environmental monitoring applications, this paper discusses a cross-comparison analysis between the different instruments of Landsat and Sentinel Missions (TM, ETM+, OLI and MSI). The level-2 Surface Reflectance products were considered (in particular the reprocessed Collection-2 for Landsat). The calibration coefficients for four of the most popular vegetation indexes (NDVI, EVI, SAVI and NDMI) were estimated, with the aim of harmonizing and minimizing radiometric differences for the combined use of these sensors. For this purpose, more than 20,000 pairs of images almost simultaneously acquired (+/- one day tolerance window) were selected over a period of several years (depending on the lifespan overlap of every sensor pair). Vegetation indices (VIs) were computed for each image, and, for each cross-comparison, 100 random extractions of 300,000 sample pixels were performed all over the European continent. Linear transformation functions for each VI and between each sensor couple were computed by regression analyses, also assessing the repeatability of the estimation. Furthermore, the stability over time of the obtained coefficients was assessed when enough years of corresponding observations are available.

The availability of multispectral images, with both high spatial and spectral resolution, makes it possible to obtain valuable information about complex urban environment, reducing the need for more expensive surveying techniques. Here, a methodology is tested for the semi-automatic extraction of buildings and the mapping of the main roofing materials over a urban area of approximately 100 km², including the entire city of Bologna (Italy). The methodology follows an object-oriented approach and exploits a limited number of training samples. After a validation based on field inspections and close-range photos acquired by a drone, the final map achieved an overall accuracy of 94% (producer accuracy 79%) regarding the building extraction and of 91% for the classification of the roofing materials. The proposed approach proved to be flexible enough to catch the strong variability of the urban texture in different districts and can be easily reproducible in other contexts, as only satellite imagery is required for the mapping.

The recent improvement of infrared image quality has increased the use of thermography as a non-destructive diagnostic technique. Amongst other applications, thermography can be used to monitor historic buildings. The present work was carried out within the framework of the Horizon 2020 European project SHELTER, which aims to create a management plan for cultural heritage subject to environmental and anthropogenic risk. Among the chosen case studies is the Santa Croce Complex in Ravenna (Italy), which is exposed to different hazards, including flooding. The church has a peculiar architecture that develops below the street level, so the internal walls are affected by the deterioration caused by rising humidity. In such a case of advanced degradation, passive thermography cannot be used to its full potential. For this reason, an innovative methodology involving active thermography was first developed and validated with laboratory tests. Secondly, we conducted its first application to a real case study. With this purpose, an active thermography survey with forced ventilation was carried out to enhance different stages of material degradation by means of automatic classification of multitemporal data. These experiments have resulted in a method using an active thermal survey in a high moisture content environment to detect masonry degradation.

Classifying crops using satellite data is a challenge, especially since most crops have similar growth cycles. Due to their different characteristics and chlorophyll content, different crops exhibit subtle differences in their reflectance spectra. This study uses a data-driven approach to build a series of deep learning models to classify 36 different land covers in Steele County and Traill Country, North Dakota, US. A Google Earth Engine workflow was implemented to generate a composite layer containing Sentinel 1 and Sentinel 2 satellite data and surface crop data over the study area. 200,000 sample points were generated on this layer, 140,000 for training dataset, 30,000 for validation dataset and 30,000 for testing dataset. Each sample point contains the values of 12 months of SAR and spectral data. In this way, a two-dimensional feature matrix of the time dimension and spectral band dimension (bands refer to specific wavelengths of data in remote sensing imagery and other type of data like NDVI) is generated for each sample point. The training dataset of the model is composed of the feature matrix of these sample points, and the surface crops as labels correspond to the feature matrix. Since this is a dataset with two-dimensional features, this research uses four deep learning models: Dense Neural Network (DNN), Long short-term memory (LSTM), Convolutional neural network (CNN) and Transformer. Among them, the Transformer model based on the self-attention mechanism performed the best, with a comprehensive accuracy rate of 85%, and the classification accuracy rate of crops with more than 2,000 sample points in the training data set reached more than 90%.