Historical Maps Research Articles

Evaluating Convolutional Neural Network Architecture for Historical Topographic Hardcopy Maps Analysis: A Study on Training and Validation Accuracy Variation

Convolutional Neural Networks (CNN) are widely used for image analysis tasks, including object detection, segmentation, and recognition. Given the advanced capability, this study evaluates the effectiveness and performance of CNN architecture for analysing Historical Topographic Hardcopy Maps (HTHM) by assessing variations in training and validation accuracy. The lack of research specifically dedicated to CNN’s application in analysing topographic hardcopy maps presents an opportunity to explore and address the unique challenges associated with this domain. While existing studies have predominantly focused on satellite imagery, this study aims to uncover valuable insights, patterns, and characteristics inherent to HTHM through customised CNN approaches. This study utilises a standard CNN architecture and tests the model’s performance with different epoch settings (20, 40, and 60) using varying dataset sizes (288, 636, 1144, and 1716 images). The results indicate that the optimal operation point for training and validation accuracy is achieved at epoch 40. Beyond epoch 40, the widening gap between training and validation accuracy suggests overfitting. Hence, adding more epochs does not significantly improve accuracy beyond the optimum phase. The experiment also shows that the CNN model obtains a training accuracy of 98%, validation accuracy of 67%, and F1-score overall performance of 77%. The analysis demonstrates that the CNN model performs reasonably well in classifying instances from the HTHM dataset. These findings contribute to a better understanding of the strengths and limitations of the model, providing valuable insights for future research and refinement of classification approaches in the context of topographic hardcopy map analysis.

Why I Paint Thousands of Circles

Why I paint Thousands of Circles explores psychological barriers and multilayered themes that stem from a single horrific event that involved Moran’s father and his brother. The artist collates information, photos and constructs an ar(t)chaeological archive where family photos, product imagery, together with newspaper clips to form units of a historical and psychological mind map. The exposition becomes an auto-ethnographical exploration of mid 90's working class North West London. The repetitive painting process, exposed and documented in the exposition, functions as transformative method, where ambiguous feelings of a violent upbringing are directed towards the creation of a visual system with an inherent logic – “creating some kind of beauty out of ugliness.”

Explore to Mantai, the Ancient Port-city and the International Trade-hub of Maritime Silk Road in Northern Coast of Sri Lanka

Abstract. Mantai Ancient Port City is located in Mannar, Northern Coast of Sri Lanka, archeological reserves declared by the Department of Archeology in Sri Lanka. In concern with historical international trades for almost 2000 years, Mantai had been an excellent port city as discovered by 1980s investigations. Today, this historically valued archeology reserves are being covered by various unauthorized constructions. The artifacts found in 1980s excavations figured out in further research directives to unveil the ancient cultural and social relations that had been experienced over two millennium around the globe. This research paper elaborates change detection of temporal aspects of unauthorized constructions within the respective geographical domain. Change detection researches are based on the historical maps, aerial photographs, satellite images and recent spatial data sources played over the application software. The investigation mission deployed in 1980 had unveiled evidences of civilization history and artifacts from many countries. However the archeological research and investigations were disrupted in 1983 with escalation of civil war in Northern Province. The Research elaborates visual facts and figures of the constructions erected after 1980 against their chronological measures. The research team further discusses about the tremendous variety of fields that Mantai opens to collaborate with the international research organizations.

Marginal Mounds and Maritime Shepherding. A Landscape Archaeological Survey of a Late Medieval Sheep Mound in the Belgian Coastal Plain

ABSTRACT The ‘Scaperie’ site in Knokke-Heist (Belgium), identified through a topographic analysis of a sixteenth-century map and located in a maritime sedimentary environment, serves as the focal point for this research. Employing a landscape archaeological approach, this study integrates multiple data sources including ceramics, historical maps, aerial photographs, LiDAR-data, geophysical surveys, and a coring survey. The dataset revealed the remnants of a anthropogenic sheep mound, evidenced by a localised microtopographic elevation, subsoil anomalies and surface artifacts associated with dairy production. More generally, this paper contributes to the understanding of the dynamic interplay between humans, sheep, and the coastal environment, offering new insights into historic land use and the archaeological characteristics of coastal mounded features. The study introduces a tripartite pattern of spatial organisation of animal husbandry, encompassing parent farms, droveways and satellite dwelling mounds. Encroached by the advancing embankments, this sheep-related taskscape was gradually marginalised both socio-economically and spatially.

Land Cover Mapping in West Africa: A Collaborative Process

The availability of current land cover and land use (LCLU) information for monitoring the status of land resources has considerable value in ensuring sustainable land use planning and development. Similarly, the need to provide updated information on the extent of LCLU change in West Africa has become apparent, given the increasing demand for land resources driven by rapid population growth. Over the past decade, multiple projects have been undertaken to produce regional and national land cover maps. However, using different classification systems and legends has made updating and sharing land cover information challenging. This has resulted in the inefficient use of human and financial resources. The development of the Land Cover Meta Language (LCML) based on International Organization for Standardization (ISO) standards offers an opportunity to create a standardized classification system. This system would enable easier integration of regional and national data, efficient management of information, and better resource utilization in West Africa. This article emphasizes the process and the need for multistakeholder collaboration in developing a standardized land cover classification system for West Africa, which is currently nonexistent. It presents the survey data collected to evaluate historical, current, and future land cover mapping projects in the region and provides relevant use cases as examples for operationalizing a standardized land cover classification legend for West Africa.

Letter to the editor: historical maps and violent extremism in Wolkait, Western Tigray, Ethiopia

Letter to the editor: historical maps and violent extremism in Wolkait, Western Tigray, Ethiopia

Deep mapping Uncertain Historical Sources

This article navigates through the challenge of preserving and presenting uncertainties in digital maps, which are used to reconstruct practical knowledge in early modern artists’ businesses. It introduces a novel methodology—deep mapping—as a multi-layered spatial visualization within the Geographical Information Systems (GIS). This method adeptly facilitates the processing and visualization of complex art historical data, offering a nuanced approach that addresses the dual need of managing large-scale spatial analysis and maintaining the precision requisite in scholarly work. To operationalize the concept of deep mapping in knowledge production, this research has collected and integrated location-related descriptions of early modern addresses from various sources, translating them into geo-referenced areas and visualizing them on historical maps with varying levels of uncertainties. Applying deep mapping to visualize painters’ distribution patterns in seventeenth-century Amsterdam as an example, this article discusses two ways of presenting uncertainties in digital maps to facilitate historical observation. It shows that uncertainty is most effectively presented as fuzzy heat maps in the background to accentuate painters’ choices of locations for their painting businesses. The deep maps demonstrate that painters in early seventeenth-century Amsterdam pragmatically practiced their business knowledge by making clustering decisions following market conditions.

Urban Historiography and Graphic Reconstruction of a Historic Area in Valencia, Spain

The conservation of cultural heritage is a well-established fact recognized by public administrations, the scientific community, and society at large. Understanding this heritage strengthens the historical memory of communities. However, there is a type of heritage that, as it disappears or evolves over time, cannot be physically recovered: the urban fabric of historic cores. This article aims to implement a system for integrating historical urban data into a Geographic Information System (GIS) to enable the graphic recovery of urban evolution within a territory. This system facilitates the storage of alphanumeric and graphic data in a centralized database, providing a holistic view of the transformation process of a historic center’s landscape. This case study focuses on an area in the historic center of Valencia, a territory influenced by multiple cultures since the city was founded by the Romans. Each culture has altered the spatial structures within the area. Georeferenced documents from historical archives, historical cartography, and the scientific literature were utilized for this study. The results have been integrated into the current cartography of Valencia in the GIS, producing plans of successive urban stages through the overlay of historical maps and current cartography.

ML Approaches for the Study of Significant Heritage Contexts: An Application on Coastal Landscapes in Sardinia

Remote Sensing (RS) and Geographic Information Science (GIS) techniques are powerful tools for spatial data collection, analysis, management, and digitization within cultural heritage frameworks. Despite their capabilities, challenges remain in automating data semantic classification for conservation purposes. To address this, leveraging airborne Light Detection And Ranging (LiDAR) point clouds, complex spatial analyses, and automated data structuring is crucial for supporting heritage preservation and knowledge processes. In this context, the present contribution investigates the latest Artificial Intelligence (AI) technologies for automating existing LiDAR data structuring, focusing on the case study of Sardinia coastlines. Moreover, the study preliminary addresses automation challenges in the perspective of historical defensive landscapes mapping. Since historical defensive architectures and landscapes are characterized by several challenging complexities—including their association with dark periods in recent history and chronological stratification—their digitization and preservation are highly multidisciplinary issues. This research aims to improve data structuring automation in these large heritage contexts with a multiscale approach by applying Machine Learning (ML) techniques to low-scale 3D Airborne Laser Scanning (ALS) point clouds. The study thus develops a predictive Deep Learning Model (DLM) for the semantic segmentation of sparse point clouds (<10 pts/m2), adaptable to large landscape heritage contexts and heterogeneous data scales. Additionally, a preliminary investigation into object-detection methods has been conducted to map specific fortification artifacts efficiently.

Human-induced landscape modification in the in the last two centuries in the Po delta plain (northern Italy)

Historical maps with high degree of accuracy permit quantitative reconstructions of past land use and land cover (LULC), crucial to assess the impact of human activities on landscape evolution. After georeferencing in a modern reference system, the Carta del Ferrarese commissioned by Napoleon Bonaparte and completed in 1814, has been used to quantify the changes in LULC, occurred in the last two centuries in the Po delta plain. The map depicts a palaeo-landscape dominated by wetlands (49% of the study area) and agricultural areas (41%), whereas forests appear already largely depleted (5%). The Piantata Padana, a traditional agroforestry system with live trees used to support grapevines, is dominant (62% of the agricultural areas). The comparison with the 2014 LULC map highlights a dramatic reduction (85%) of wetland areas and the replacement of the Piantata Padana with bare arable lands, with the consequent removal of 4-40 million trees. Soils of areas formerly occupied by wetlands show high organic-carbon content, highlighting the potential of humid areas in carbon sequestration. Land reclaiming, prompted by the introduction of steam pumps, favoured the economic development of the area, but concurred to CO2 emissions through the oxidation of soil organic substances, energy consumption from pumping stations, and the extensive use of hydrocarbon fuels in agriculture. Although urbanisation is limited in the Po delta plain, this area appears nowadays largely shaped by human activities, with the dominance of lands devoted to agriculture, dissected by a dense network of draining channels. The landscape changes recorded in the last two centuries in the Po coastal plain have been uniquely driven by human activities, like in several coastal plains worldwide.

Mapping South Africa's canopy-forming kelp forests using low-cost, high-resolution Sentinel-2 imagery

Globally, kelp forests play a vital role in providing ecological, social and economic services. They contribute to the livelihoods and resilience of many coastal communities. To date, a gap exists in contemporary, comprehensive and consistent maps of South African kelp forests, since they were last mapped partially in 2006 by covering 900 km of South Africa's coastline. This study addresses this gap by producing a comprehensive remotely sensed high-resolution 2016 map of canopy forming coastal kelp forests. Using the 10m resolution Sentinel-2 A and B spectral bands 4 (RED) and 8 (NIR), an expert derived Normalized Difference Vegetation Index (NDVI) threshold was used to detect surface protruding kelp forests along 1300 km coastline. The results were validated with expert verification and using Google Earth, data from historic maps, remote sensing and biomass estimation of South African kelp resources. Our study demonstrates the aptitude of Sentinel-2 for detecting canopy-forming kelps at low cost along South Africa's west and south coast. We report the encountered drawbacks in mapping an expansive coastline with varied sea conditions including wave activity, tides and turbidity. Comprehensive ground validation, long-term monitoring sites and the use of time series datasets remain a gap towards improving the calibration of remote sensing methods and long-term monitoring of South African kelp forests. Our results provide a foundation for continuous monitoring of South African kelp forests as well as exploring other unmapped kelp/similar habitats to inform research and environmental management.

Exploring Mahmud Yunus's Indonesian-Arabic Dictionary: Structure and Significance

Background: This study examines Mahmud Yunus' Arabic-Indonesian dictionary using a library research method. Gap: Limited research exists on the dictionary's structural features and supplementary content. Aim: The research analyzes the dictionary's components and applies Philip Mayring's content analysis. Results: The 14th edition of the dictionary includes linguistic tools like tashrif and wazan but lacks elements such as historical chronology, maps, and compiler details. It does feature visual aids related to everyday objects. Novelty: The study reveals missing supplementary content, suggesting areas for improvement. Implications: Updates could enhance its educational value. Highlights : Library Research Method: Emphasizes the use of primary and secondary data sources for comprehensive analysis. Structural Components: Identifies key elements in the dictionary, such as tashrif and wazan, and highlights missing features like historical chronology. Educational Value: Suggests the need for updates to enhance the dictionary's utility as a linguistic resource. Keywords: Mahmud Yunus, Arabic-Indonesian dictionary, content analysis, linguistic tools, supplementary features

Morfológiai vizsgálatok Magyarország délnyugati határfolyóin = Morphological Studies on South-Western Border Rivers in Hungary

Nowadays, the preservation and sustainable use of our natural values are increasingly coming to the fore, and this has implications not only for economic and field development but also for ecological aspects. In recent years, attention has shifted towards river morphological studies, which were previously relegated to the background. Understanding long-term changes and assessing the current state is essential to estimate future processes. In this article, we present our morphological studies on the Hungarian–Croatian border sections of the Mura and the Drava rivers. Historical changes were analyzed through a comparative study of historical maps from earlier periods, while the evaluation of the current state was conducted based on a detailed terrain model from a recent survey. GIS evaluation was also compared with sediment transport and flow measurement results. This comparison suggests that the morphological status of the river section under study is consistent with the typical parameters of transport processes.

Assessing the Effects of Habitat Loss and Deterioration on a Red Squirrel Translocation Site: Insights for Future Conservation Management.

Translocations, a conservation tool used to conserve and restore dwindling species, are often associated with high failure rates. Inadequate long-term monitoring of both populations and their introduction sites beyond the initial years post-translocation creates a gap in our understanding of the factors that determine translocation success or failure, resulting in less informed projects in the future. This lack of long-term monitoring is partly caused by the absence of a well-defined framework by which the success of the translocation can be measured, leading to premature and sometimes inaccurate assessments of their outcome. We investigated the long-term outcome of a red squirrel translocation in the west of Ireland, specifically assessing the habitat changes in the translocation site since the introduction in 2005, and their impact on the capacity of the forest to sustain a population of a given size. Using digitised historical map data, we showed that the translocation site experienced a 53% reduction in suitable habitat. Additionally, there was a 41%-81% reduction in the total number of red squirrels the forest could support, according to feeding survey data. Clear-felling, a forest fire and a shift in tree species composition collectively contributed to this decline in site suitability. This investigation underscores the complexity of translocation projects and emphasises the pivotal role of habitat quality in their outcomes. We advocate for detailed habitat assessments during the planning phase, avoidance of unstable habitats as translocation sites, and the implementation of long-term monitoring practices.

Individual-Level Exposure to Residential Redlining in 1940 and Mortality Risk.

Historic redlining, the practice by the Home Owners' Loan Corporation (HOLC) of systematically denying credit to borrowers in neighborhoods that were inhabited by primarily African American individuals, has been associated with poor community outcomes, but the association with individual risk of death is not clear. To examine if exposure to residential redlining practices by HOLC in 1940 is associated with increased risk of death later in life. The study linked individuals who resided within HOLC-graded neighborhoods (defined as Census Enumeration Districts) in 1940 with administrative death records data. The study estimated hazard ratios as well as age-specific life expectancy gaps (at age 55, 65, and 75 years) for HOLC grading exposure. This was done using methods that adapted standard parametric survival analysis to data with limited mortality coverage windows and incomplete observations of survivors. The analysis sample consisted of 961 719 individual-level observations across 13 912 enumeration districts within 30 of the largest US cities (based on 1940 population counts) across 23 states. Data were analyzed between December 1, 2023, and September 4, 2024. The exposure was HOLC grade based on historic HOLC maps, with A representing "best" or creditworthy areas; B, "still desirable"; C, "definitely declining"; and D, "hazardous" areas not worthy of credit (ie, redlined), and the main outcome was age at death from the Social Security Numident file. The 961 719-person individual sample had a mean (SD) age of 19.26 (9.26) years in 1940 and a mean (SD) age at death of 76.83 (9.22) years. In a model adjusted for sex (52.48% female; 47.52% male), race and ethnicity (7.36% African American; 92.64% White), and latent place effects, a 1-unit lower HOLC grade was associated with an 8% (hazard ratio, 1.08 [95% CI, 1.07-1.09]) increased risk of death. At age 65 years, these hazard differentials translated into an estimated life expectancy gap of -0.49 (95% CI, -0.56 to -0.43) years for each 1-unit decrease of the HOLC grade. This study found that individuals who resided within redlined neighborhoods in 1940 had lower life expectancy later in life than individuals who resided within other HOLC-graded areas.

Spatial Expansion, Planning, and Their Influences on the Urban Landscape of Christian Churches in Canton (1582–1732 and 1844–1911)

Canton (present-day Guangzhou, China) has a long history as a trading port and serves as a window for studying the history of Sino-Western cultural exchanges. Canton was a city built under Confucian orders, leading to significant differences (when compared to Christian cities) in urban functional zoning, layout, urban landscape, and methods for shaping spatial order. Therefore, the churches constructed by Christian missionary societies in Canton merit particular attention in missionary history research and urban planning history. Based on local gazetteers, historical maps, export paintings, Western travelogues, and archives at that time, from a cultural landscape perspective, this article compares and analyzes the spatial expansion of Christian churches and their influences on the urban landscape in Canton in two stages. In the late Ming and early Qing dynasties, the spatial layout of the churches indicated an active integration into Canton City. After the Opium War, churches were not only used for religious purposes but also served as symbols asserting the presence of Christians and Western powers (which made the situation more complicated). Missionary societies attracted believers through the construction of public facilities, building Christian communities centered around churches, thereby competing with authorities for spatial power and influencing the urban functional system and spatial layout controlled by the authorities. Comparatively, the Roman Catholic Cathedral has profoundly changed the traditional landscape order in Canton, while the Protestant Dongshan Church interacted more closely with the city.

Flow dynamics and channel changes at Yamuna River in Delhi-National Capital Region, India

ABSTRACT The present work was carried out on River Yamuna passing through Delhi-National Capital Region (Delhi-NCR) of India for a stretch of about 125 km to assess the fluvial characteristics in the highly human-dominated region for a period of 200 years with the help of historical maps, topographical maps and satellite data with integration of geographic information system (GIS) environment. Erosion, deposition and channel stability data were analyzed for 1977–1986, 1986–1996, 1996–2006, 2006–2016, and 2016–2022 period. Digital Shoreline Analysis System (DSAS) application was utilized to quantify river channel movement with average channel migration of 22.8 m/year. Westward migration is 4149.2 m maximum in length and eastward migration is about 4083.8 m. The river has migrated a total of 32.26 km2 of area during 1955-2022. The findings indicate that various human activities, such as engineering structures, sand mining, embankments, urbanization, land use/land cover changes, and canal networks, have significantly impacted the river. The DSAS application was also used to predict the position of river channel centerline in future for 2032 and 2042 with channel length of 132.5 and 141.6 km respectively.

Historical landscape structures of the eastern part of upper Medzibodrožie region

Landscape represents a specific part of the earth's surface, while it has its own structure – primary, secondary and tertiary. The secondary landscape structure consists of elements of land use and material creations of man, which currently fill the earth's surface. The aim of the paper is to evaluate, based on the analysis of historical military and topographical maps, the changes in the secondary landscape structure in the area formed by the cadastral territories of selected municipalities in the eastern part of Upper Medzibodrožie Region. On four maps showing selected territories of Upper Medzibodrožie Region, we compare extensive changes that have occurred in the landscape structure mainly as a result of human intervention in the landscape structure. Historical maps show that the use of the Upper Medzibodrožie Region landscape has changed significantly over the past 150 years. River regulation, drainage works, deforestation and also the transformation of agriculture had a major impact on these changes. The results show that the largest decrease in area representation was recorded by forests and the largest increase by arable land.

Unveiling Stage Zero Conditions in the New Forest National Park: A UAV‐Based Structure‐From‐Motion Photogrammetry and LiDAR Approach for Reconstructing an Anastomosing Wet Woodland at the Avon Water

ABSTRACTIn recent years, there have been significant technological advances in uncrewed aerial vehicles (UAVs) and in particular the use of lightweight consumer‐grade ‘drones’. This combined with the development of structure‐from‐motion (SfM) technology has provided river restoration practitioners with a new tool that can be used to give an affordable, repeatable and objective assessment of river restoration projects. In this study, a combined SfM photogrammetry and LiDAR approach is utilised on a section of the Avon water, a small watercourse in the New Forest National Park. Victorian‐era straightening and channelisation has significantly altered the ecological and morphological state of the river system, but recent river restoration projects aim to reverse these effects. Whilst historic maps may be used as a guide to reveal the former alignment, changes in river planform occurred much earlier and these maps may not represent the natural course of the river. High‐resolution orthophotos and 3D photogrammetric models of the site are created that reveal a palaeolandscape consisting of a mosaic of anabranching channels. These are interpreted to represent a former anastomosing wet woodland and ‘Stage Zero’ of the river system. It is inferred that early human habitation and associated land clearance altered hydrological and hydrogeological conditions, reducing floodplain connectivity and promoting single‐threaded planform configurations. This was then followed by the most recent Victorian‐era straightening. The palaeolandscape revealed by the study provides a guide for future Stage Zero river restoration in the New Forest and elsewhere, demonstrating an application of low cost, UAV‐derived photogrammetry in river restoration research.

Bidirectional Transmission Mapping of Architectural Styles of Tibetan Buddhist Temples in China from the 7th to the 18th Century

Architecture is the stone book of history, and the evolution of architectural styles showcases a non-verbal history constructed through images. As an important part of China’s historical and cultural heritage, the architectural forms and styles of Tibetan Buddhist temples were initially modeled on Tang dynasty temple architecture and gradually evolved into the most significant architectural types in regions such as Tibet and Qinghai in China. Religious architecture has also played a significant role in shaping regional cultural landscapes. Existing research on Tibetan Buddhist temples is primarily focused on qualitative studies of individual temple buildings. This research takes the spatiotemporal evolution of architectural styles of Tibetan Buddhist temples as an entry point and, for the first time, employs ArcGIS technology to visualize the spatial and geographical distribution of Tibetan Buddhist temples from the 7th to the 18th century, establishing a comprehensive academic vision that encompasses both historical stratification and cross-regional spatial correlations. By analyzing the cultural symbolic features embodied in the construction styles of Tibetan Buddhist temples and the visual characteristics reflected in their decorative arts, we propose two spatiotemporal dimensions for the formation and transmission of Tibetan Buddhist temple architectural styles: “Westward Transmission” and “Eastward Diffusion”. Firstly, from the 7th to the 9th centuries, the architectural style and construction techniques of Tang dynasty Buddhist temples were transmitted westward along the Tang–Tibet ancient road, integrating with local Tibetan elements to form the Tubo architectural style, which was further refined into the “Sino–Tibetan Combined Style” with strong visual characteristics around the 13th century. Subsequently, along with the spread of Tibetan Buddhism, this temple architectural style underwent an eastward diffusion from the 13th to the 18th century, reaching regions, such as Sichuan, Qinghai, Gansu, Inner Mongolia, Hebei, and Beijing, presenting a spatial gradient from west to east in the geographical dimension. On this basis, in this research, we construct a historical evolution mapping of Tibetan Buddhist temple architectural styles based on bidirectional transmission, attempting to elucidate that the intrinsic driving forces are religious and the cultural identity that guided the bidirectional transmission mechanism of these architectural styles under the historical context of the formation and dissemination of Tibetan Buddhism from the 7th to the 18th century.