The automated analysis of historical documents, particularly maps, has drastically benefited from advances in deep learning and its success across various computer vision applications. However, most deep learning-based methods heavily rely on large amounts of annotated training data, which are typically unavailable for historical maps, especially for those belonging to specific, homogeneous cartographic domains, also known as corpora. Creating high-quality training data suitable for machine learning often takes a significant amount of time and involves extensive manual effort. While synthetic training data can alleviate the scarcity of real-world samples, it often lacks the affinity (realism) and diversity (variation) necessary for effective learning. By transferring the cartographic style of a historical map corpus onto modern vector data, we bootstrap an effectively unlimited number of synthetic historical maps suitable for tasks such as land-cover interpretation of a homogeneous historical map corpus. We propose an automatic deep generative approach and an alternative manual stochastic degradation technique to emulate the visual uncertainty and noise, also known as aleatoric uncertainty, commonly observed in historical map scans. To quantitatively evaluate the effectiveness and applicability of our approach, the bootstrapped training datasets were employed for domain-adaptive semantic segmentation on a homogeneous map corpus using a Self-Constructing Graph Convolutional Network, enabling a comprehensive assessment of the impact of our data bootstrapping methods.

doi:10.1007/s10032-026-00582-w

@article{arzoumanidis2026Bootstrapping,
    abstract = {The automated analysis of historical documents, particularly maps, has drastically benefited from advances in deep learning and its success across various computer vision applications. However, most deep learning-based methods heavily rely on large amounts of annotated training data, which are typically unavailable for historical maps, especially for those belonging to specific, homogeneous cartographic domains, also known as corpora. Creating high-quality training data suitable for machine learning often takes a significant amount of time and involves extensive manual effort. While synthetic training data can alleviate the scarcity of real-world samples, it often lacks the affinity (realism) and diversity (variation) necessary for effective learning. By transferring the cartographic style of a historical map corpus onto modern vector data, we bootstrap an effectively unlimited number of synthetic historical maps suitable for tasks such as land-cover interpretation of a homogeneous historical map corpus. We propose an automatic deep generative approach and an alternative manual stochastic degradation technique to emulate the visual uncertainty and noise, also known as aleatoric uncertainty, commonly observed in historical map scans. To quantitatively evaluate the effectiveness and applicability of our approach, the bootstrapped training datasets were employed for domain-adaptive semantic segmentation on a homogeneous map corpus using a Self-Constructing Graph Convolutional Network, enabling a comprehensive assessment of the impact of our data bootstrapping methods.},
    author = {Arzoumanidis, Lukas and Knechtel, Julius and Haunert, Jan-Henrik and Dehbi, Youness},
    doi = {10.1007/s10032-026-00582-w},
    journal = {International Journal on Document Analysis and Recognition (IJDAR)},
    number = {},
    pages = {},
    title = {Automatic uncertainty-aware synthetic data bootstrapping for historical map segmentation},
    volume = {},
    year = {2026}
}

Soil moisture is a fundamental environmental variable essential for applications in agriculture, drought assessment, hydrological modeling, and climate research. In recent decades, numerous Soil Moisture Content (SMC) datasets have been produced from in-situ measurements, airborne and spaceborne observations, and model simulations. However, information about these datasets is fragmented across disparate repositories, publications, and portals, making data discovery, comparison, and integration a significant challenge for researchers. This study introduces the University of Bonn Soil Moisture Data Catalog (UB-SMDC), a unified, standards-compliant metadata portal designed to overcome this fragmentation. Two primary objectives drove the project: first, centralizing information on publicly available SMC datasets into a single, user-friendly, web-based interface; and second, conducting a comprehensive statistical analysis of SMC datasets to characterize the global SMC data landscape. The UB-SMDC was developed using a structured, three-phase methodology: (1) comprehensive data discovery, (2) catalog design and implementation, and (3) metadata creation and analysis. Built on the open-source GeoNetwork platform, the catalog aligns with the Geographic information, ISO19139 metadata standard, to ensure consistency and interoperability. To harmonize key attributes, a controlled keyword taxonomy was developed to standardize terms for spatial and temporal resolution, measurement depth, data format, processing level, and data version. Each metadata record is enriched with links to initial data sources and access, and includes map-based previews to visualize dataset coverage. By assessing 373 metadata records, the UB-SMDC streamlines the data discovery and selection process, supports transparent and reproducible research, and facilitates cross-dataset comparison and integration.

doi:10.1080/20964471.2026.2652079

@article{Mohseni13042026,
    abstract = {Soil moisture is a fundamental environmental variable essential for applications in agriculture, drought assessment, hydrological modeling, and climate research. In recent decades, numerous Soil Moisture Content (SMC) datasets have been produced from in-situ measurements, airborne and spaceborne observations, and model simulations. However, information about these datasets is fragmented across disparate repositories, publications, and portals, making data discovery, comparison, and integration a significant challenge for researchers. This study introduces the University of Bonn Soil Moisture Data Catalog (UB-SMDC), a unified, standards-compliant metadata portal designed to overcome this fragmentation. Two primary objectives drove the project: first, centralizing information on publicly available SMC datasets into a single, user-friendly, web-based interface; and second, conducting a comprehensive statistical analysis of SMC datasets to characterize the global SMC data landscape. The UB-SMDC was developed using a structured, three-phase methodology: (1) comprehensive data discovery, (2) catalog design and implementation, and (3) metadata creation and analysis. Built on the open-source GeoNetwork platform, the catalog aligns with the Geographic information, ISO19139 metadata standard, to ensure consistency and interoperability. To harmonize key attributes, a controlled keyword taxonomy was developed to standardize terms for spatial and temporal resolution, measurement depth, data format, processing level, and data version. Each metadata record is enriched with links to initial data sources and access, and includes map-based previews to visualize dataset coverage. By assessing 373 metadata records, the UB-SMDC streamlines the data discovery and selection process, supports transparent and reproducible research, and facilitates cross-dataset comparison and integration.},
    author = {Farzane Mohseni and Jan-Henrik Haunert},
    doi = {10.1080/20964471.2026.2652079},
    journal = {Big Earth Data},
    number = {0},
    pages = {1--33},
    publisher = {Taylor \& Francis},
    title = {Publicly available soil moisture datasets: an overview and the {UB-SMDC} portal},
    volume = {0},
    year = {2026}
}

Establishing sustainable agricultural systems while ensuring food security has become a global priority. Meeting this goal requires contributions from different fields of agricultural science, many of which depend on detailed information on crops. Recent advancements in deep learning and the transnational harmonization of administrative data have led to the availability of ever-larger datasets of agricultural field polygons. These datasets, however, vary in quality and level of detail. To achieve synergies between different information sources through data fusion and to evaluate the quality of model outputs, it is essential to efficiently identify correspondences in spatially overlapping datasets. We address this challenge by leveraging a state-of-the-art matching algorithm that we adapt by redesigning its connected-component decomposition to handle large-scale datasets of agricultural field polygons. We demonstrate the algorithm’s suitability through two case studies. First, we show how automatically delineated field polygons can be validated against ground truth in terms of their spatial quality. Second, we explore how two established reference datasets align both thematically and spatially. We discuss the dataset comparisons using different evaluation metrics and provide an interactive map viewer that enables the exploration of spatial patterns of the datasets’ alignment by visualizing matching qualities in the geographic context.

doi:10.1080/17538947.2026.2632420

@article{naumann2026aggMatching,
    abstract = {Establishing sustainable agricultural systems while ensuring food security has become a global priority. Meeting this goal requires contributions from different fields of agricultural science, many of which depend on detailed information on crops. Recent advancements in deep learning and the transnational harmonization of administrative data have led to the availability of ever-larger datasets of agricultural field polygons. These datasets, however, vary in quality and level of detail. To achieve synergies between different information sources through data fusion and to evaluate the quality of model outputs, it is essential to efficiently identify correspondences in spatially overlapping datasets. We address this challenge by leveraging a state-of-the-art matching algorithm that we adapt by redesigning its connected-component decomposition to handle large-scale datasets of agricultural field polygons.
We demonstrate the algorithm’s suitability through two case studies. First, we show how automatically delineated field polygons can be validated against ground truth in terms of their spatial quality. Second, we explore how two established reference datasets align both thematically and spatially.
We discuss the dataset comparisons using different evaluation metrics and provide an interactive map viewer that enables the exploration of spatial patterns of the datasets’ alignment by visualizing matching qualities in the geographic context.},
    author = {Naumann, Alexander and Gedicke, Sven and Haunert, Jan-Henrik},
    doi = {10.1080/17538947.2026.2632420},
    journal = {International Journal of Digital Earth},
    number = {1},
    pages = {2632420},
    title = {A {S}calable {M}atching {A}pproach for the {C}omparison of {A}gricultural {L}and {U}se {M}aps {B}ased on {C}orresponding {F}ield {P}olygons},
    volume = {19},
    year = {2026}
}

@article{knechtel2026kinematicScanPlanning,
    author = {Knechtel, Julius and Kordgholiabad, Mohammad and Haunert, Jan-Henrik},
    journal = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
    note = {Accepted for publication, ISPRS Congress 2026},
    number = { },
    pages = { },
    title = {Optimal Path Planning for Kinematic Laser Scanning},
    volume = { },
    year = {2026}
}

@article{naumann2026footprintAggEdgeOrientation,
    author = {Naumann, Alexander and Bergé, Samuel and Sauer, Jonas and Haunert, Jan-Henrik},
    journal = {ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
    note = {Accepted for publication, ISPRS Congress 2026},
    number = { },
    pages = { },
    title = {Building Footprint Aggregation with Preservation of Edge Orientations},
    volume = { },
    year = {2026}
}

Historical maps represent an invaluable memory which should be preserved. Such kind of maps are, however, mostly scanned and stored as raster graphics which do not contain semantic information in a machine-readable form. To achieve a machine-readable state, an often expensive human intervention is needed in a fully manual or semi-automatic fashion. An automatic interpretation and a feature extraction is then inevitable for a map digitization and vectorization. Automatic approaches showed more and more convincing and promising results on challenging map corpora avoiding human interaction. This paper deals with the semantic segmentation of historical maps based on Graph Convolutional Networks (GCNs) to capture long-range dependencies between image features. This allows for an extension of the receptive field of Convolutional Neural Networks (CNNs) restricted on local dependencies. A Self-Constructing Graph (SCG) module has been applied to automatically induce the structure of the GCN. We performed experiments revealing promising results where our approach achieved an Mean Intersection over Union (mIoU) of 0.68, outperforming a state-of-the-art CNN dedicated to the semantic segmentation of historical maps.

doi:10.1080/15230406.2025.2468304

@article{arzoumanidis2026semSegHistMaps,
    abstract = {Historical maps represent an invaluable memory which should be preserved. Such kind of maps are, however, mostly scanned and stored as raster graphics which do not contain semantic information in a machine-readable form. To achieve a machine-readable state, an often expensive human intervention is needed in a fully manual or semi-automatic fashion. An automatic interpretation and a feature extraction is then inevitable for a map digitization and vectorization. Automatic approaches showed more and more convincing and promising results on challenging map corpora avoiding human interaction. This paper deals with the semantic segmentation of historical maps based on Graph Convolutional Networks (GCNs) to capture long-range dependencies between image features. This allows for an extension of the receptive field of Convolutional Neural Networks (CNNs) restricted on local dependencies. A Self-Constructing Graph (SCG) module has been applied to automatically induce the structure of the GCN. We performed experiments revealing promising results where our approach achieved an Mean Intersection over Union (mIoU) of 0.68, outperforming a state-of-the-art CNN dedicated to the semantic segmentation of historical maps.},
    author = {Lukas Arzoumanidis and Julius Knechtel and Jan-Henrik Haunert and Youness Dehbi},
    doi = {10.1080/15230406.2025.2468304},
    journal = {Cartography and Geographic Information Science},
    number = {2},
    pages = {177--187},
    title = {Semantic segmentation of historical maps using Self-Constructing Graph Convolutional Networks},
    url = {https://www.tandfonline.com/doi/full/10.1080/15230406.2025.2468304},
    volume = {53},
    year = {2026}
}