Spatial Database Research Articles

Definitions, Classification Schemes for Active Faults, and Their Application

Active faults are generally defined as faults that have moved in the past and will continue to be active in the future. They are expected to cause deformation and potential disasters if they are localized close to human activities. The definition and classification of active faults are important bases for evaluating the risk. This paper summarizes and compares the history, status, and progress of their definition and classification schemes used in representative countries and regions, as well as in some relevant standards, in active fault mapping, in the construction of spatial databases, and in some other aspects. It is concluded that the current geodynamic setting, existing technical means, geological operability, application purpose, and social acceptability of active faulting hazard in a specific area comprehensively determine the selection of the definition and classification. The key parameter in defining active faults is the time limit. It usually involves four time scales, i.e., Neotectonic (post-Neogene), Quaternary, Late Quaternary, and Holocene. The definition using a short time scale, such as Late Quaternary and Holocene, is usually suitable for the plate boundary zone, which has a high strain rate, but active faults in the intraplate deformation region and stable continental region should be defined with a long time scale, such as the Quaternary and Neotectonics. In addition, the magnitude standard can determine the activity intensity of active faults, which most generally includes three classes, namely, M ≥ 5.0 damaging earthquakes, M ≥ 6.0 strong earthquakes, and M ≥ 6.5 earthquakes that may produce surface displacement or deformation. The M ≥ 5.0 earthquake is generally applicable to regional earthquake prevention and risk mitigation in many countries or regions, but the M ≥ 6.5 earthquake magnitude benchmark is generally used as the standard in rules or regulations regarding active fault avoidance. The most common classification schemes in many countries or regions are based on fault activity, which is reflected mainly by the fault slip rate and fault recurrence interval (FRI), as well as by the last activation time. However, when determining the specific quantitative parameters of the different activity levels of faults, it is necessary to comprehensively consider the differences in activity and ages of the faults in the study region, as well as the amount and validity of existing data for the purpose of classifying different active levels of faults effectively.

ПРИКЛАДНАЯ ЛИНГВИСТИКА В ОРДЕНА ЗНАК ПОЧЕТА ИНСТИТУТЕ ИСТОРИИ, ЯЗЫКА И ЛИТЕРАТУРЫ УФИЦ РАН: ОСНОВНЫЕ ВЕХИ

The article analyzes the development of applied linguistics within the framework of Bashkir linguistics, as well as the formation of this field. Most researchers working in the field of applied linguistics consider it to be a multidisciplinary field that encompasses all existing research. However, there is still no clear definition of what constitutes this term. In the article, applied linguistics is defined as referring to areas that involve the use of mathematical methods, computer-aided text processing, and the creation and analysis of linguistic databases. These areas have been active fields of research at the Institute of History, Language and Literature of the Ufa Federal Research Center of the Russian Academy of Sciences for over 30 years. The first steps towards this goal in the Bashkir linguistics were taken by the group “Automation of Lexicography”, which was founded in 1991. During its 11-year existence, the team developed frequency dictionaries for the language in the works of classical Bashkir literature by D. Yulty, as well as frequency dictionaries on different styles of Bashkir, primary school textbooks, and other materials. Due to the widespread adoption of computer technologies, which required the creation of standards for software, localization, support for operating systems, and promotion of the Bashkir language online, a laboratory for linguistics and information technology has been established on the basis of this group. The laboratory successfully completed these tasks: they presented standards for keyboard layouts and code tables; they participated in the localization of Lexicon, FineReader, Mozilla, Disco Commander and Chameleon programs; and they created national fonts and implemented language support for Windows and Linux operating systems. These works were the foundation for the full functionality of the language in the digital world. On their basis, the laboratory developed a terminological database operating on the internet, an information system for the Machine Fund of the Bashkir language, and corpus projects on prose, journalist and folklore texts in the Bashkir language. Based on these latter projects, certain issues regarding the syntactic structures of proverbs and sayings in the national language have been investigated. In order to continue dialectological research and to create a database of dialects of the national language, the laboratory was transformed into the Department of Applied Linguistics and Dialectology in 2022. Today, the department continues to work on corpus projects of the Bashkir language and collects expedition materials for a geographic information database on regional dialects. Based on these materials, a great deal of scientific work is carried out to clarify problems of the function of oral Bashkir speech within the media, as well as to determine phonetic and lexico-grammatical characteristics of the Northwest dialect.

Spatial Database of Planted Trees (SDPT Version 2.0)

This paper describes the methods for updating the Spatial Database of Planted Trees (SDPT) in three areas: boundaries, to spatially differentiate planted forests and tree crops from natural and seminatural forests on a global scale; tree species information, to help screen for the illegal exportation of timber products; and carbon sequestration rates, or removal factors, to improve maps of atmospheric carbon dioxide sequestration by planted trees.

MANAGEMENT OF DISASTER THROUGH KNOWLEDGE MANAGEMENT SYSTEM: A CASE STUDY ON SAMBALPUR DISTRICT, ODISHA

Odisha is one of the hazard-prone state and suffers both natural and man-made hazards extensively threatening millions of lives and causing large-scale losses. Disaster management in India also saw a paradigm shift after 2002 from-the humanitarian relief and rehabilitation of victims to the holistic management of disasters viewpoint. The present research addressed this absence of information related to hazards and disasters affecting the district-level Sambalpur. This research aimed to find out some aid in the management of disasters at the district level by collecting and synthesizing all related information about disasters that occur in Sambalpur using an integrated approach. The research used publicly available tools as well as data from credible sources (e.g., government reports). To full-fill the aim, the research compiled information about disasters in the Sambalpur district and prepares a spatial database. Based on socio-economic factors-population density and working population, exposure of the blocks was calculated. Risk and exposure to it assisted in making a vulnerability map of the district at the block level. Based on vulnerability, blocks were prioritized for the policy-makers to ease their management in pre-during and post-disaster situations. The result of this paper would assist policy makers to take proper and quick decisions for the management of the blocks making their management efficient and effective and it could be replicated for other districts of Odisha and India.

GEOWEALTH-US: Spatial wealth inequality data for the United States, 1960–2020

Wealth inequality has been sharply rising in the United States and across many other high-income countries. Due to a lack of data, we know little about how this trend has unfolded across locations within countries. Examining the subnational geography of wealth is crucial because, from one generation to the next, it shapes the distribution of opportunity, disadvantage, and power across individuals and communities. By employing machine-learning-based imputation to link national historical surveys conducted by the U.S. Federal Reserve to population survey microdata, the data presented in this article addresses this gap. The Geographic Wealth Inequality Database (“GEOWEALTH-US”) provides the first estimates of the level and distribution of wealth at various geographical scales within the United States from 1960 to 2020. The GEOWEALTH-US database enables new lines of investigation into the contribution of spatial wealth disparities to major societal challenges including wealth concentration, income inequality, social mobility, housing unaffordability, and political polarization.

High rate of species misidentification reduces the taxonomic certainty of European biodiversity databases of ivies (Hedera L.)

The digitization of natural history specimens and the popularization of citizen science are creating an unprecedented availability of large amounts of biodiversity data. These biodiversity inventories can be severely affected by species misidentification, a source of taxonomic uncertainty that is rarely acknowledged in biodiversity data management. For these reasons, taxonomists debate the use of online repositories to address biological questions at the species level. Hedera L. (ivies) provides an excellent case study as it is well represented in both herbaria and online repositories with thousands of records likely to be affected by high taxonomic uncertainty. We analyze the sources and extent of taxonomic errors in the identification of the European ivy species by reviewing herbarium specimens and find a high misidentification rate (18% on average), which varies between species (maximized in H. hibernica: 55%; H. azorica: 48%; H. iberica: 36%) and regions (maximized in the UK: 38% and Spain: 27%). We find a systematic misidentification of all European ivies with H. helix behind the high misidentification rates in herbaria and warn of even higher rates in online records. We compile a spatial database to overcome the large discrepancies we observed in species distributions between online and morphologically reviewed records.

Infrastructure for 3D Modeling of Historical Fountains in Istanbul with GIS-Based Procedural Approach

Along with the concepts of “smart city” and “digital twin,” the 3D (threedimensional) city models have started to be used as a basis for many studies that have been carried out in recent years. The most important and basic components of 3D city models are the structures that are located in the cities. However, some small structures of historical importance are within the category of the buildings in a city but are often not as large as a building. Historical fountains are some of these structures. For this reason, modeling with existing3D city model-production methods is a little more complicated and requires local measurements and detailed modeling studies.As a result, this study has designed a database scheme design in which the historical city wall fountains in Istanbul can be stored in a spatial database and modeled in three dimensions (with procedural modeling when necessary). In addition, the conveniences that this infrastructure will provide in the production of 3D structure models and some difficulties that were encountered during these studies are also discussed and examined.

Cognitive land cover mapping: A three-layer deep learning architecture for remote sensing data classification

In many application domains, remotely sensed (RS) data are essential for disaster monitoring, climate forecasting, and remote surveillance. It perceives and gathers environmental, sociological, and transitional data on its own, from a distance, in increasing amounts of spatial and temporal details. While urbanization has been continued to be a worldwide phenomenon, the urban management and planning are needed to satisfy the needs of the Earth system. The operations associated with land management, urban planning, and transportation on Earth have been connected to digital maps and geographic databases. Knowledge of land cover is also significant for managing, conserving, and formulating environmental and urban development policies. Therefore, highly accurate Land Use Land Cover (LULC) assessment and monitoring are of the utmost significance for empirical studies and organizational accomplishment. In this study, we leverage remotely sensed data to formulate a sophisticated deep learning system for comprehensive Earth observation. The core of our approach involves the development of a three-layered Convolution-Convolution-Maxpooling Convolutional Neural Network (CCMCNN) model, preceded by a meticulous pre-processing stage. In the pre-processing stage, images extracted from the NWPU-RESISC dataset undergo resizing, division, and augmentation procedures before being fed into the three-layered CCMCNN architecture for the purpose of classifying them into five different LULC categories. The effectiveness of our proposed model undergoes thorough validation through a comparative examination against various pre-trained deep learning models outlined in existing literature. Presenting performance metrics, our model attains a remarkable accuracy rate of 98.4%. This advancement holds significant promise in the realm of Earth surveillance, offering a valuable tool for enhancing situational awareness and environmental monitoring.

Multi-Disaster Hazard Analysis, The Case of Elazığ Province

In this study, a comprehensive assessment of disaster hazards in Elazığ province, where the Eastern Anatolian Fault Zone passes through, was conducted. Hazard maps for earthquakes, floods, landslides, rockfalls, avalanches, desertification, and erosion were integrated to create a multi-hazard map. Various methods, such as the Analytic Hierarchy Process (AHP) and machine learning models, including the Random Forest algorithm, were employed to assess the severity and probability of exposure for each hazard type. Independent variables, including VS30, liquefaction potential, Digital Elevation Model (DEM)-derived data, and climatic data, were selected based on relevant literature and the study area. For earthquake and erosion hazards, intuitive models were used due to the absence of a single dependent variable. The desertification map was obtained from the Ministry of Environment, Urban Planning, and Climate Change. The Random Forest model was used for other disaster hazard maps. All hazard maps were combined using a hierarchical approach with the Weighted Overlay tool. The study generated a spatial synthesis and database intended to offer proactive insights into disaster preparedness, optimizing resource allocation, and expediting recovery efforts post-disaster within the Elazığ Province. Its primary objective is to provide assistance to local authorities and emergency response teams. In the province, a significant portion of urban settlements and the majority of rural areas face high earthquake hazards. Floods pose a considerable risk, particularly in low-lying areas downstream of numerous dams scattered across the province, as well as at the confluence points of seasonal riverbeds. The hazard of landslides is high in the rugged areas along the EAF and in steep terrains eroded by rivers. Moreover, rock falls occur more frequently in mountainous areas along the Hazarbaba-Akdağ axis due to erosion and physical dissolution. Erosion and desertification represent significant slow-moving hazards, with erosion intensifying on steep slopes and barren lands, while desertification notably affects Baskil and its surrounding low-lying areas in the western part of the province. Considering multiple hazards, areas with concentrated settlements and economic activities such as Elazığ, Baskil, Kovancılar, Karakoçan, and Behrimaz plains are categorized as very high and high-risk zones.

Methodological Innovations for Establishing Cemetery Spatial Databases—A UAV-Based Workflow Helping Small Communities

Various modern large-scale mapping techniques have already been introduced in earth sciences, cadastral mapping, and the agricultural sector. These methodologies often use remotely sensed data to compile various analogue or digital cartographic products as well as spatial databases. However, the mapping of cemeteries and standards for establishing a spatial database for them have rarely been published, and there is no definite method for this purpose in Hungary yet. We have compiled a methodology based on mapping experiences in three sample areas in the Roman Catholic Archdiocese of Eger in Hungary that are church properties. The initial UAV-based fieldwork orthomosaics were processed with a CV (computer vision)-based script that vectorised grave contours. After fieldwork, which included the recording of the deceased people’s names and their dates of birth and death in the case of all graves, a spatial database was created pairing each polygon with the corresponding personal data. A map was also generated from the results of the survey. The cartographic product and the database fulfil legal requirements and give hints for cemeteries regarding further planning. The developed method is capable of making mapping and database building easier—not just in the case of graves, but with other rectangular objects, too.

Heavy metals concentration in soils across the conterminous USA: Spatial prediction, model uncertainty, and influencing factors

Assessment and proper management of sites contaminated with heavy metals require precise information on the spatial distribution of these metals. This study aimed to predict and map the distribution of Cd, Cu, Ni, Pb, and Zn across the conterminous USA using point observations, environmental variables, and Histogram-based Gradient Boosting (HGB) modeling. Over 9180 surficial soil observations from the Soil Geochemistry Spatial Database (SGSD) (n = 1150), the Geochemical and Mineralogical Survey of Soils (GMSS) (n = 4857), and the Holmgren Dataset (HD) (n = 3400), and 28 covariates (100 m × 100 m grid) representing climate, topography, vegetation, soils, and anthropic activity were compiled. Model performance was evaluated on 20 % of the data not used in calibration using the coefficient of determination (R2), concordance correlation coefficient (ρc), and root mean square error (RMSE) indices. Uncertainty of predictions was calculated as the difference between the estimated 95 and 5 % quantiles provided by HGB. The model explained up to 50 % of the variance in the data with RMSE ranging between 0.16 (mg kg−1) for Cu and 23.4 (mg kg−1) for Zn, respectively. Likewise, ρc ranged between 0.55 (Cu) and 0.68 (Zn), respectively, and Zn had the highest R2 (0.50) among all predictions. We observed high Pb concentrations near urban areas. Peak concentrations of all studied metals were found in the Lower Mississippi River Valley. Cu, Ni, and Zn concentrations were higher on the West Coast; Cd concentrations were higher in the central USA. Clay, pH, potential evapotranspiration, temperature, and precipitation were among the model's top five important covariates for spatial predictions of heavy metals. The combined use of point observations and environmental covariates coupled with machine learning provided a reliable prediction of heavy metals distribution in the soils of the conterminous USA. The updated maps could support environmental assessments, monitoring, and decision-making with this methodology applicable to other soil databases, worldwide.

3D WebGIS for Ephemeral Architecture Documentation and Studies in the Humanities

The documentation and visualization of ephemeral CH, especially for World’s Fairs architecture, remains a neglected endeavor on the global scale. While digital products like 3D models find extensive application in CH, the use of a WebGIS has scarcely been explored in this domain. When a WebGIS is used for CH, it serves to communicate the output of research, not as a tool to support the development of the research itself. Moreover, aspects like procedural development for the creation of a WebGIS platform, its upgrading, and its long-term preservation are key factors for the maintenance of the digital tool, but they have scarcely been considered in the literature. Through the Turin 1911 project, this paper defines a procedure for the creation of a WebGIS for ephemeral architectural documentation, showing how a WebGIS platform can be designed, implemented, tested, and maintained. The novelty of this study lies in the creation of a 2D/3D WebGIS based on a tailored spatial database; the WebGIS is coupled with a dedicated website for the constant updating of the research data documenting the Turin 1911 International Exposition. The discussion emphasizes the transformative role of a WebGIS in not only sharing information but also serving as a dynamic platform for conducting digital humanities studies in 3D environments.

Mapping Landslide Vulnerability using Machine Learning Approach along the Taba Penanjung-Kepahiang Road, Bengkulu Province

Landslides occur when masses of rock, debris or soil move due to various factors and processes that cause land movement. The Taba Penanjung-Kepahiang route is one of the areas in Bengkulu Province that is highly prone to landslides. This causeway is the only fastest land route connecting the Bengkulu-Kepahiang area. In recent years, the road area has often been cut off due to landslides and fallen trees, which have caused road access to be cut off and obstructed and claimed lives. This study uses a Machine Learning (ML) and GIS approach with Variable Frequency Ratio using 16 independent factors obtained from the spatial database and DEM, which correlate with landslide events. This research aims to gain an in-depth understanding of the factors that cause landslides. In addition, the research focus is the development of a Disaster Mitigation Model to design and implement effective strategies to reduce the risk and impact of landslide disasters through in-depth analysis The dependent factor is the location of the landslide from the historical landslide area for the last five years, with a distribution of 70/30%. Furthermore, frequency ratio is used to analyze the correlation between conditioning factors and historical landslides. Then, the independent and dependent factors were normalized to create a landslide susceptibility map. Frequency Ratio (FR) indicates the likelihood of an event occurring, with drainage density (FR= 0.69), shear wave velocity (Vs30) (FR= 0.66), slope (FR= 0.60), and rainfall (FR= 0.55). The output of the processed data is in the table below.

An open source platform addressing structural stability risk assessment in historical centres

The management of stability risk assessment in historical centres in a project that aims to design and develop an open platform where blocks of buildings and large structures may be represented in damage maps before the event occurs, addressing damage forecasts for seismic movements impacting on the structural stability of the CH. The structural stability is calculated using a Matlab code developed at the National Technical University of Athens, translated to an open source programming language (Python)using the software tool GeoPandas to enable operations that would normally require spatial database software (PostGIS). Furthermore, the use of open source technologies like QGIS desktop software will provide open and free access to view and contribute in the future.

Assessment of Alterations in Settlement Patterns of Agricultural Landscape in the Example of Kashubia in Poland

Traditional agricultural landscapes are heavily exposed to change due to their relatively low agricultural productivity. However, they represent cultural values of great importance in maintaining the resilience of the environment and society. Although their cultural potential is important for sustainable development, it is still insufficiently recognized. The article fills this gap by examining old farmstead buildings as a distinguishing element of the agricultural landscape. The study was conducted in Poland in the area of farm settlements in Kashubia. A spatial database and archival maps were used for comparison of the spatial distribution and the number of farmsteads and buildings in 1937 and 2020. The types of settlements in the selected area of research were recorded and classified. The results obtained from the study may support the spatial planning and local management of agricultural areas for the purpose of preserving rural identity and economy.

Basic types and evolutionary characteristics of the socialist built heritage in China, 1949–1978: bibliometrics analysis of the People’s Daily

The socialist built heritage (SBH) is a product of the great and typical socialist construction and is considered to be one of the unique contemporary legacies. However, due to political controversy and a shorter history, its conservation status is dire. In order to better understand and promote future conservation, this study explored the typology and evolution of SBH, using representative socialist China as an example. Based on the official People’s Daily, the spatial term database of various socialist construction fields was generated by utilizing Python and Excel software. Through qualitative logical induction and quantitative word frequency statistics, the basic types and evolutionary characteristics of SBH were obtained. It was found that (1) the composite, multiscale, and extensive SBH were identified as twenty-six basic types. It was most widespread in the industry and agroforestry fields, while factories and facilities, collective organization buildings, government agencies, and assembly buildings were the most common basic types. (2) Related to social development, the fastest growth stage for SBH was from 1953 to 1960 and vice versa from 1966 to 1975. The evolution of SBH in technology field shifted from a non-significant increase to a sudden increase, while those in the finance and trade, and diplomacy fields fluctuated. The remaining fields were marked by large fluctuations to smoothness. The nature of SBH has become more modernized over time. These results further illustrated the distinctive value of the SBH, and can provide positive targeted support for their conservation.

Flood Susceptibility Assessment with Random Sampling Strategy in Ensemble Learning (RF and XGBoost)

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data’s positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area’s road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods.

Navigating the Maps: Euclidean vs. Road Network Distances in Spatial Queries

Using spatial data in mobile applications has grown significantly, thereby empowering users to explore locations, navigate unfamiliar areas, find transportation routes, employ geomarketing strategies, and model environmental factors. Spatial databases are pivotal in efficiently storing, retrieving, and manipulating spatial data to fulfill users’ needs. Two fundamental spatial query types, k-nearest neighbors (kNN) and range search, enable users to access specific points of interest (POIs) based on their location, which are measured by actual road distance. However, retrieving the nearest POIs using actual road distance can be computationally intensive due to the need to find the shortest distance. Using straight-line measurements could expedite the process but might compromise accuracy. Consequently, this study aims to evaluate the accuracy of the Euclidean distance method in POIs retrieval by comparing it with the road network distance method. The primary focus is determining whether the trade-off between computational time and accuracy is justified, thus employing the Open Source Routing Machine (OSRM) for distance extraction. The assessment encompasses diverse scenarios and analyses factors influencing the accuracy of the Euclidean distance method. The methodology employs a quantitative approach, thereby categorizing query points based on density and analyzing them using kNN and range query methods. Accuracy in the Euclidean distance method is evaluated against the road network distance method. The results demonstrate peak accuracy for kNN queries at k=1, thus exceeding 85% across classes but declining as k increases. Range queries show varied accuracy based on POI density, with higher-density classes exhibiting earlier accuracy increases. Notably, datasets with fewer POIs exhibit unexpectedly higher accuracy, thereby providing valuable insights into spatial query processing.

Deep convolutional neural networks with Bee Collecting Pollen Algorithm (BCPA)-based landslide data balancing and spatial prediction

Predicting the landslide-prone area is critical for various applications, including emergency response, land planning, and disaster mitigation. There needs to be a thorough landslide inventory in current studies and appropriate sampling uncertainty issues. Landslide risk mapping has expanded significantly as machine learning techniques have developed. However, one of the primary issues in Landslide Prediction is data imbalance (DI). This is problematic since it is challenging or expensive to generate an accurate inventory map of landslides based on previous data. This study proposes a novel landslide prediction method using Generative Adversarial Networks (GAN) for generating the synthetic data, Synthetic Minority Oversampling Technique (SMOTE) for overcoming the data imbalance problem, and Bee Collecting Pollen Algorithm (BCPA) for feature extraction. Combining 184 landslides and ten criteria, including topographic wetness index (TWI), aspect, distance from the road, total curvature, sediment transport index (STI), height, slope, stream, lithology, and slope length, a geographical database was produced. The data was generated using GAN, a Deep Convolutional Neural Network (DCNN) technique to populate the dataset. The proposed DCNN-BCPA approach findings were merged with current machine learning methods such as Random Forests (RF), Artificial Neural Networks (ANN), k-Nearest Neighbours (k-NN), Decision Trees (DT), Support Vector Machine (SVM), logistic regression (LR). The model’s accuracy, precision, recall, f-score, and RMSE were measured using the following metrics: 92.675%, 96.298%, 90.536%, 96.637%, and 45.623%. This study suggests that harmonizing landslide data may have a substantial impact on the predictive capabilities of machine learning models.

Constructing a digital system of historical geographic information from the perspective of digital humanities: a case study of the historical geographic information database of Tibetan Buddhist monasteries

Abstract Digital techniques are critical in the digital age. Research in various disciplines requires the use of digital technology. Extracting and digitizing information from text, particularly historical geographical information, is the most fundamental operation of digital humanities. However, digitizing historical geographical information is a challenging work. This article proposes a framework for constructing a digital system of historical geographic information. The feasibility of the digital system was verified in a case study of Tibetan Buddhist monasteries in Tibetan inhabited areas of China. The results demonstrate that the digital system proposed in this study can be used as a guide for digitizing historical geographic information of Tibetan Buddhist monasteries from the perspective of digital humanities. This study provides a useful reference for the digitalization of historical geographic information in the digital humanities discipline.