João Moura Pires

Datasets collecting demographic and socio-economic statistics are widely available. Still, the data are often only released for highly aggregated geospatial areas, which can mask important local hotspots. When conducting spatial analysis, one often needs to disaggregate the source data, transforming the statistics reported for a set of source zones into values for a set of target zones, with a different geometry and a higher spatial resolution. This article reports on a novel dasymetric disaggregation method that uses encoder–decoder convolutional neural networks, similar to those adopted in image segmentation tasks, to combine different types of ancillary data. Model training constitutes a particular challenge. This is due to the fact that disaggregation tasks are ill-posed and do not entail the direct use of supervision signals in the form of training instances mapping low-resolution to high-resolution counts. We propose to address this problem through self-training. Our method iteratively refines initial estimates produced by disaggregation heuristics and training models with the estimates from previous iterations together with relevant regularization strategies. We conducted experiments related to the disaggregation of different variables collected for Continental Portugal into a raster grid with a resolution of 200 m. Results show that the proposed approach outperforms common alternative methods, including approaches that use other types of regression models to infer the dasymetric weights.

Every year, wildfires strike the Portuguese territory and are a concern for public entities and the population. To prevent a wildfire progression and minimize its impact, Fuel Management Zones (FMZs) have been stipulated, by law, around buildings, settlements, along national roads, and other infrastructures. FMZs require monitoring of the vegetation condition to promptly proceed with the maintenance and cleaning of these zones. To improve FMZ monitoring, this paper proposes the use of satellite images, such as the Sentinel-1 and Sentinel-2, along with vegetation indices and extracted temporal characteristics (max, min, mean and standard deviation) associated with the vegetation within and outside the FMZs and to determine if they were treated. These characteristics feed machine-learning algorithms, such as XGBoost, Support Vector Machines, K-nearest neighbors and Random Forest. The results show that it is possible to detect an intervention in an FMZ with high accuracy, namely with an F1-score ranging from 90% up to 94% and a Kappa ranging from 0.80 up to 0.89.

High-resolution population grids built from historical census data can ease the analyses of geographical population changes, at the same time also facilitating the combination of population data with other GIS layers to perform analyses on a wide range of topics. This article reports on experiments with a hybrid spatial disaggregation technique that combines the ideas of dasymetric mapping and pycnophylactic interpolation, using modern machine learning methods to combine different types of ancillary variables, in order to disaggregate historical census data into a 200 m resolution grid. We specifically report on experiments related to the disaggregation of historical population counts from three different national censuses which took place around 1900, respectively in Great Britain, Belgium, and the Netherlands. The obtained results indicate that the proposed method is indeed highly accurate, outperforming simpler disaggregation schemes based on mass-preserving areal weighting or pycnophylactic interpolation. The best results were obtained using modern regression methods (i.e., gradient tree boosting or convolutional neural networks, depending on the case study), which previously have only seldom been used for spatial disaggregation.

Crimes, forest fires, accidents, infectious diseases, human interactions with mobile devices (e.g., tweets) are being logged as spatiotemporal events. For each event, its geographic location, time and related attributes are known with high levels of detail (LoDs). The LoD plays a crucial role when analyzing data, enhancing the user's perception of phenomena. From one LoD to another, some patterns can be easily perceived or different patterns may be detected. Modeling phenomena at different LoDs is needed, as there is no exclusive LoD at which data can be analyzed. Current practices work mainly on a single LoD, driven by the analysts perception, ignoring the fact that the identification of the suitable LoDs is a key issue for pointing relevant patterns. This paper presents a Visual Analytics approach called VAST, that allows users to simultaneously inspect a phenomenon at different LoDs, helping them to see in what LoDs patterns emerge or in what LoDs the perception of the phenomenon is different. In this way, the analysis of vast amounts of spatiotemporal events is assisted, guiding the user in this process. The use of several synthetic and real datasets allowed the evaluation of VAST, which was able to suggest LoDs with different interesting spatiotemporal patterns and the type of expected patterns.