The research behind this paper focuses on the connection between monitoring the environmental quality of a sample building and the corresponding digital model. The data obtained from the sample will be extended to a related typology of buildings, thus generating a method for conscious retrofitting of a large portion of the built environment. To conduct this study, a digital ecosystem comprising the model and a series of environmental sensors has been prepared. Within this digital environment, it is possible to visualize the data acquired from real-life sensors directly into the model. The digital twin method, in which there is a direct cause/effect correspondence between the real artifact and its digital alter ego, is foundational to this experimentation. Environmental data gathered from the building interacts with the digital model and returns to the physical reality as indicators. Once these indicators have been verified on the sample, they can be implemented in other related buildings. Sensors measuring temperature, pressure, humidity, and light radiation were concurrently applied to the building. The data flow is bidirectional, from the sensors to the model and vice versa. In the initial direction, the sensors transmit data to the digital model through a series of steps. The sensors communicate with a digital ecosystem. Once the procedure has been verified to work, it can be replicated easily, since open-source Arduino components were used for the sensor system. These components, besides being easy to find and economically viable, can be adapted and reproduced with extreme simplicity because, according to the Arduino philosophy, both the operating codes and the electronic production diagrams of the individual components are freely available.
The Role of Semi-Automatic Classification Techniques for Mapping Landscape Components. The Case Study of Tratturo Magno in Molise Region
This paper investigates the use of semi-automatic classification techniques applied to multispectral satellite imagery for the mapping and recognition of historical landscape structures. The research focuses on the Tratturo Magno, a traditional transhumance route, aiming to evaluate different image-processing approaches to detect its path and spatial influence within the territory.
The methodology integrates vegetation indices (NDVI, EVI), unsupervised clustering, and supervised machine learning classification (Random Forest), combined with GIS tools and Google Earth Engine for temporal and spatial analysis. Multitemporal Sentinel-2 imagery is analyzed to identify optimal seasonal conditions for feature detection, highlighting the tratturo as a linear green corridor during autumn and winter. Results show that supervised classification methods provide the most reliable identification, although challenges remain in distinguishing the tratturo from similar landscape elements. The study demonstrates the potential of AI-supported geospatial analysis to enhance landscape interpretation, while emphasizing the need for further refinement to achieve precise and unique feature extraction.
Image Segmentation Procedure for Mapping Spatial Quality of Slow Routes
The current research aims at investigating the potential of Image Segmentation (IS) as a data source for mapping, with a bottom-up approach, the spatial quality of slow routes, localized in the territories “in-between” the main cities. The paper analyses two different case studies in Lombardy and Molise regions, where a different territorial configuration and data are available. The IS method, that computes area percentages in the street-level imagery by using Pixellab/TensorFlow digital environment, has been applied for detecting three different environments that are intersected by the selected routes and that are also detectable by using GIS tools: open spaces, built environment and rows of trees. These have been considered as relevant since they affect the users’ perception of the places in a different way. The research points out how the IS method can be complementary to the GIS-based detection method to collect more detailed geo-information about the places, but also a very powerful tool to catch geo-information by the street-level imagery, in the territories where no thematic geospatial data are available.
A Technique to Measure the Spatial Quality of Slow Routes in Fragile Territories Using Image Segmentation
The current research aims at investigating the potential of image segmentation (IS) technology, based on web application, for measuring the spatial quality of slow routes. The big amount of street–level images, publicly available through several applications such as Mapillary, Google Street View, are rele-vant sources of information, that allow virtual explorations of many places around the world. The (IS) technology allows partitioning of a single digital image into sets of pixels in order to read and recognize the visual content within the frame of the image. By applying IS technology to the images taken along a defined route, it has established a method for grouping images in relation to their spatial features. The method has been applied to some stretches of slow–mobility routes, that are localized along the fragile coastal landscape of Trabucchi, south of Italy. A selection of images along the route, both in the outdoor and urban space, has been analyzed, with the aim to test the effectiveness of the method, able to produce useful information to define a Spatial Quality Index.