Cutchan, Marvin Mc; Giannopoulos, Ioannis
In: Remote Sensing, vol. 14, no. 12, 2022, ISSN: 2072-4292.
Geospatial vector data with semantic annotations are a promising but complex data source for spatial prediction tasks such as land use and land cover (LULC) classification. These data describe the geometries and the types (i.e., semantics) of geo-objects, such as a Shop or an Amenity. Unlike raster data, which are commonly used for such prediction tasks, geospatial vector data are irregular and heterogenous, making it challenging for deep neural networks to learn based on them. This work tackles this problem by introducing novel encodings which quantify the geospatial vector data allowing deep neural networks to learn based on them, and to spatially predict. These encodings were evaluated in this work based on a specific use case, namely LULC classification. We therefore classified LULC based on the different encodings as input and an attention-based deep neural network (called Perceiver). Based on the accuracy assessments, the potential of these encodings is compared. Furthermore, the influence of the object semantics on the classification performance is analyzed. This is performed by pruning the ontology, describing the semantics and repeating the LULC classification. The results of this work suggest that the encoding of the geography and the semantic granularity of geospatial vector data influences the classification performance overall and on a LULC class level. Nevertheless, the proposed encodings are not restricted to LULC classification but can be applied to other spatial prediction tasks too. In general, this work highlights that geospatial vector data with semantic annotations is a rich data source unlocking new potential for spatial predictions. However, we also show that this potential depends on how much is known about the semantics, and how the geography is presented to the deep neural network.
Cutchan, Marvin Mc; Comber, Alexis J.; Giannopoulos, Ioannis; Canestrini, Manuela
In: Remote Sensing, vol. 13, no. 16, 2021, ISSN: 2072-4292.
The classification of land use and land cover (LULC) is a well-studied task within the domain of remote sensing and geographic information science. It traditionally relies on remotely sensed imagery and therefore models land cover classes with respect to their electromagnetic reflectances, aggregated in pixels. This paper introduces a methodology which enables the inclusion of geographical object semantics (from vector data) into the LULC classification procedure. As such, information on the types of geographic objects (e.g., Shop, Church, Peak, etc.) can improve LULC classification accuracy. In this paper, we demonstrate how semantics can be fused with imagery to classify LULC. Three experiments were performed to explore and highlight the impact and potential of semantics for this task. In each experiment CORINE LULC data was used as a ground truth and predicted using imagery from Sentinel-2 and semantics from LinkedGeoData using deep learning. Our results reveal that LULC can be classified from semantics only and that fusing semantics with imageryâ€”Semantic Boostingâ€”improved the classification with significantly higher LULC accuracies. The results show that some LULC classes are better predicted using only semantics, others with just imagery, and importantly much of the improvement was due to the ability to separate similar land use classes. A number of key considerations are discussed.
Cutchan, Marvin Mc; Özdal-Oktay, Simge; Giannopoulos, Ioannis
Semantic-based urban growth prediction Journal Article
In: Transactions in GIS, vol. n/a, no. n/a, 2020.
Abstract Urban growth is a spatial process which has a significant impact on the earth’s environment. Research on predicting this complex process makes it therefore especially fruitful for decision-making on a global scale, as it enables the introduction of more sustainable urban development. This article presents a novel method of urban growth prediction. The method utilizes geospatial semantics in order to predict urban growth for a set of random areas in Europe. For this purpose, a feature space representing geospatial configurations was introduced which embeds semantic information. Data in this feature space was then used to perform deep learning, which ultimately enables the prediction of urban growth with high accuracy. The final results reveal that geospatial semantics hold great potential for spatial prediction tasks.
McCutchan, Marvin; Özdal-Oktay, Simge; Giannopoulos, Ioannis
Urban Growth Predictions with Deep Learning and Geosemantics Inproceedings
In: Ehrmann, Katharina; Khosravi, Hamid Reza Mansouri; others, (Ed.): VIENNA Young Scientists Symposium (VSS 2019), pp. 30–31, Book-of-Abstracts.com, Gumpoldskirchen, 2019, ISBN: 978-3-9504017-9-0, (Vortrag: VIENNA Young Scientists Symposium (VSS 2019), Wien; 2019-06-13 -- 2019-06-14).
This work outlines a novel approach for the prediction of urban growth. The method extracts semantic information of geospatial data and predicts if urban and non-urban areas are going to change in the future, using a deep neural network. The scored prediction accuracy is higher than any other urban growth prediction model. This superiority is based on two novelties: (1) The effective modeling of the geospatial configurations using semantics, (2) the use of deep learning. The proposed method is therefore an effective tool to predict one of the global challenges of urban sprawl and support the future development strategies.