Logistic regression (LR) is widely used in land change modelling; however, its traditional form assumes independent input variables, which is often not realistic. Although the improved models offer better fitting capabilities, it is unclear whether this leads to more accurate land change simulations. To address this gap, we compared the basic LR model with five classic improved models using Lhasa as a case study, comparing the receiver-operating characteristic (ROC) values of each model and further evaluating the performance of the land change models generated by coupling each LR model with the CLUE-s model using six evaluation metrics (Kno, Klocation, Kquantity and the divergence indices (D, A and Q)). The results show that the improved LR models exhibit significantly enhanced ROC values. Specifically, the combined LR achieved the highest average ROC value of 0.941 across different neighbourhood sizes, and the average ROC values of all improved regressions exceeded 0.9, which is significantly higher than that of the ordinary LR (0.872), which remains unaffected by changes in neighbourhood size. However, concerning the land change simulation accuracy, ordinary LR demonstrated a clear advantage, consistently achieving the best performance across all six evaluation metrics regardless of neighbourhood size. Conversely, the improved regressions performed worse, and the combined logistic regression (CL), despite having the highest ROC, performed the poorest in four out of the six evaluation metrics. This finding indicates that there is no inherent link between higher ROC values and improved land change model accuracy. This study further explores the underlying causes of this phenomenon and suggests directions for improvement.
The aim of this study was to assess the quality of images from different UAV sensors in terms of their optical resolution, expressed by the MTF10 parameter. The study was conducted for four cameras: Mavic 3E, Matrice 4E, Phantom 4 RTK and Zenmuse P1, under different weather and lighting conditions, with varying flight altitudes and ISO settings. The Siemens Star pattern and ResolvingPower software provided by The German Aerospace Center (DLR) were used in the analysis. The results showed a significant effect of flight altitude, time of day and ISO sensitivity on image quality. A decrease in sharpness (MTF10) was observed with increasing distance from the image centre and at higher ISO values. The conclusions of the study may be helpful in planning photogrammetric missions using UAVs, enabling better-quality image data.
At the COP28 UN climate change conference, pivotal initiatives spotlighted the potential of digital financial inclusion (DFI) in mitigating carbon emissions. However, the impact of DFI on CO2 emissions and its underlying mechanisms remain insufficiently explored. Leveraging county-level panel datasets, we employ a spatiotemporal econometric model to examine the spatially uneven effects of DFI on CO2 emissions, while controlling for diverse natural and socioeconomic factors. Results show a significant mitigation effect of DFI on CO2 emissions, which is consistent across various model specifications. Specifically, a 0.1-unit increase in DFI is associated with an approximate 41% reduction in CO2 emissions, with 2.1% attributable to direct effects and 38.9% resulting from indirect or spatial spillover effects. Furthermore, we identify substantial heterogeneities in the effects of DFI across geography and developmental stages of DFI, highlighting the importance of context-specific dynamics. Key mediators in the DFI – CO2 emissions link include economic growth, industrial restructuring, and progress in environmental technology. These findings provide valuable insights for the design of financial instruments to advance sustainable development goals and combat climate change.
Road network pattern recognition plays a vital role in traffic prediction, route planning, and the development of intelligent transportation systems. However, most existing approaches are limited to single-pattern recognition and often yield suboptimal accuracy. This study introduces TransRoadNet, a multimodal hybrid framework that combines geographic spatial relationship theory with a Transformer-based architecture. The method decomposes OpenStreetMap vector data into seven representative structural categories, including grid, radial, and irregular patterns. It constructs a ten-dimensional feature vector capturing road segment characteristics at the macro, meso, and micro levels. These features are embedded and processed through a multi-head self-attention mechanism to model cross-scale spatial dependencies. Experimental results on road data from Chengdu indicate that TransRoadNet achieves an accuracy of 0.97 ± 0.01, significantly outperforming conventional models, including CNNs, GCNs, SVMs, and random forests. Additional validation on Berlin and Shanghai road networks demonstrates the model’s strong generalization across different urban environments. Due to its modular design and compatibility with parallel computing, TransRoadNet exhibits strong scalability for large-scale deployments. Compared to pixel-based image segmentation methods, the model emphasizes topological and semantic structure modeling, offering enhanced adaptability for urban systems and supporting downstream applications such as traffic control, navigation, and infrastructure planning.
ABSTRACTSpatial interaction imputation aims to compensate for missing stable connections in geographical space, bolstering interaction network integrity and accuracy. Graph neural networks excel in graph-structured interaction data. However, existing research often focuses on homogeneous networks, neglecting the impact of heterogeneous interaction relationships influenced by distance decay on interaction imputation. Neglecting edge heterogeneity constrains the ability to effectively model the network structure, consequently leading to suboptimal performance in interaction imputation. This study introduces an interaction imputation graph convolutional network model. It constructs a heterogeneous interaction network with multi-distance relationships, considering distance decay. The model performs graph embedding based on interaction relationships between nodes. It comprehensively incorporates multiple interaction modes, topological structures, and node attributes to enhance spatial interaction imputation accuracy. Empirically validated using Beijing taxi travel data, our model outperforms existing models, improving imputation accuracy by approximately 8.70%. Our model consistently maintains superior accuracy in interaction networks of various sizes, demonstrating the stable superiority of our model. We also demonstrated that the variation in the number of interaction relationships affects imputation accuracy. A reasonable number of relationships and a larger feature dimension of geographical units yield better interaction imputation results.
Krzysztof Lipka, Dariusz Gotlib, Kamil Choromański
The development and popularization of navigation applications are increasing expectations for their quality and functionality. Users need continuous navigation not only outdoors, but also indoors. In this case, however, the perception of space and movement is somewhat different than it is outside. One potential method of meeting this need may be the use of so-called geo-descriptions—multi-level textual descriptions relating to a point, line or area in a building. Currently, geo-descriptions are created manually. However, this is a rather time-consuming and complex process. Therefore, this study undertook to automate this process as much as possible. The study uses classical methods of spatial analysis from GIS systems and text generation methods based on artificial intelligence (AI) techniques, i.e., large language models (LLM). In this article, special attention will be paid to the second group of methods. As part of the first stage of the research, which was aimed at testing the proposed concept, the possibility of LLMs creating a natural description of space based on a list of features of a given place obtained by other methods (input parameters for AI), such as coordinates and categories of rooms around a given point, etc., was tested. The focus is on interior spaces and a few selected features of a particular place. In the next stages, it is planned to extend the research to spaces outside buildings. In addition, artificial intelligence can be used to provide the input parameters mentioned above.
Understanding environmental disease risk factor analysis at the district level is essential for gaining valuable insights into regional disease variations, offering a broader perspective compared to individual-level studies. Recently, explainable artificial intelligence (XAI) has received increasing attention in the analysis of factors affecting public health. However, previous purely data-driven XAI-based risk factor analyses faced challenges in capturing regional effect of environmental variables, leading to confusion regarding key spatiotemporal risk factors. Therefore, this study proposes a framework that includes two complementary XAI-based risk factor analyses following two assumptions. Regionally rescaled environmental variables must account for the unequal effects on environmental factors, which are likely influenced by variations in adaptation capacity to weather conditions and differences in exposure-response relationships to air pollutants. District-level disease distribution highlights geographic disparity in sociodemographic vulnerability, whereas temporal variation in diseases by district underscores temporal environmental impacts. Based on these two hypotheses, we rescaled environmental variables using two complementary schemes: one that employs the district-level disease distribution as the target variable, and another that utilizes the temporal residual of the disease within each district. We evaluated this framework by analyzing the association between cardiovascular age-standardized mortality rate (CVD-ASMR) and various risk factors in South Korea from 2010 to 2019, using high-performing random forest and light gradient boosting models with additive Shapley explanation. Compared to previous purely data-driven XAI-based analyses, the proposed schemes achieved significantly better results in capturing regional exposure-response relationships. In two complementary schemes, the most explainable factor to districts with high CVD-ASMR was low education level related to sociodemographic vulnerability, whereas the most explainable factors to high temporal CVD-ASMR patterns were low greenness and high air pollution levels. In addition, the two complementary schemes enabled us to reasonably analyze the interaction effect of the two risk factors, i.e. temperature and air pollutants. Furthermore, high CVD-ASMR and its high temporal variation were observed in situations of high sociodemographic vulnerability with poor air quality. These findings provide insightful public health planning for sustainable cities and society by pinpointing high-risk areas and tailoring strategies to address regional environmental challenges.
To tackle the challenge of denoising spaceborne photon-counting laser altimeter point clouds with uneven noise density, this study proposes a denoising method based on adaptive parameter density clustering, which utilizes numerical simulations to achieve self-adaptation of key parameters (neighborhood radius [Formula: see text] and minimum number of points [Formula: see text]). First, taking the directional adaptive ellipse DBSCAN (DAE-DBSCAN) as an example, photons with different background photon count rates ([Formula: see text]) are used to traverse [Formula: see text] and [Formula: see text] to calculate their optimal values ([Formula: see text] and [Formula: see text] with the highest denoising accuracy). Then, a mathematical prediction model of [Formula: see text], [Formula: see text] and [Formula: see text] was established. The actual background photon count rates were introduced into the key parameter prediction model to obtain the optimal [Formula: see text] and [Formula: see text]. Finally, a denoising experiment was conducted using the simulated photons and the ATLAS data. The results show that the proposed method had higher accuracy than the constant parameter denoising method, with an [Formula: see text] >0.95. Even for photons of complex mountainous terrain with a high background photon count rate, the denoising accuracy was still higher than 0.9. The proposed method improves the denoising accuracy of photons with different noise densities by adapting density clustering parameters.
The Italian T.A.S. (Applied Topography to Rescue Service) supports the activities of the National Fire Brigade with the use of advanced geographical information referring to the emergency scenario and, in particular, to the scenarios that require the intervention of the National System of civil protection.
The training focuses on the knowledge of the concept of coordinates which then allows to deal with the use of topographic
maps and subsequently that of the GNSS system. A theoreticalpractical course structured on interventional reality and aimed
at making the learner understand the importance of this knowledge for technical rescue and for the safety of the operator
himself.
The gravity recovery and climate experiment (GRACE) and GRACE-Follow on (FO) data provide valuable information about dynamic total water storage (TWS). The complexity of the computational process and the influence of various parameters on TWS changes are complicated in their interpretation. Principal component analysis (PCA) has been used to identify key components to amplify signals and reduce noise in observations. For this purpose, in this research, the Self-organizing map algorithm (SOM) has been used to cluster TWS in 4 categories. The results show that the western regions of Greenland and part of Antarctica are in the critical cluster and have a TWS rate of about –0.2 m/year, which indicates the melting of ice in these regions. The advantage of PCA-SOM is the easy interpretation of TWS, which reduces the impact of seasonal parameters, observation noise and measurement error, and facilitates global policy decisions in the face of climate change.
Allan Gomes, Paulo Sérgio de Oliveira Júnior, Claudia Pereira Krueger
O propósito deste artigo é resgatar o histórico dos meios de se obter a geolocalização em ambientes externos, enfatizando os smartphones com sistema operacional Android e a utilização do receptor GNSS (Global Navigation Satellite System) presente no mesmo. Além disso, são apresentadas as principais ferramentas e tecnologias relacionadas a temática, alguns resultados promissores quanto à qualidade posicional passível de ser obtida atualmente, e ainda, os desafios e perspectivas futuras deste objeto no cenário mundial. Devido aos avanços tecnológicos direcionados aos dispositivos móveis, tais como os smartphones, smartwatches e tablets, surgiram diversas aplicações que movimentam importantes segmentos do mercado global. Atualmente, os dispositivos móveis possuem diversos sensores, os quais possibilitam centenas de aplicações e funcionalidades. Neste sentido, o receptor GNSS presente nestes dispositivos se destaca por dar suporte a geolocalização com uma maior acurácia em ambientes externos. O posicionamento a partir de sensores presentes em dispositivos móveis vem ganhando atualizações e melhorias à medida que inovações tecnológicas surgem. Dentre as inovações nesta temática, destaca-se a possibilidade de aquisição dos dados GNSS brutos a partir de determinados dispositivos com sistema operacional Android igual ou superior a versão Nougat. Dessa forma, o usuário pode obter informações essenciais, como as informações da fase da onda portadora, que corroboram com a obtenção de coordenadas mais acuradas. Do mesmo modo, o surgimento de smartphones que empregam receptores multi-GNSS, como o Xiaomi mi 8, podem contribuir com uma maior qualidade do posicionamento. Aliado a estas inovações e a partir de determinados métodos de posicionamento pode-se, atualmente, obter coordenadas com acurácia ao nível centimétrico a partir de smartphones.
Abstract. The factors causing destruction of natural complexes, degradation of agricultural lands were considered. It was revealed that the crisis phenomena of state institutions also influenced the low resistance of agricultural production to negative impacts of a natural and climatic nature. The necessity of raising the urgent problem of drought, which affects the decrease in yield, and, consequently, the deterioration of the natural conditions of the economy, was proved. This requires a change in the agricultural technology system towards the development of a reclamation complex for the irrigation of agricultural lands, especially on lands of intensive agriculture, in particular, beet growing, vegetable growing, fodder production and the formation of a more drought-resistant farming system. It was noted that the neoliberal regulatory policy of the state and the liberalization of agrarian relations stopped the development of intensive reclaimed agriculture. It was revealed that over the past 30 years, land with reclamation systems fell into the private property of individuals. Lack of responsibility for the proper use of irrigation systems has led to the rupture of technological integrity, to the destruction of their functional properties. There is a need to form a system for organizing the efficient and rational use of agricultural land in production, which will allow us to study the features of the interaction of the components of the system and form ways to ensure a balance between the efficiency (profitability) of production and rational continuous use of agricultural land. On the basis of modeling, the factors of influence on the organization of the effective use of agricultural lands were determined. A graph-model of the system of organizing the efficient and rational use of agricultural lands was formed A structural-logical model of overcoming drought on agricultural lands was proposed.
As a result of the studies, it was concluded that the impact of drought can be overcome by ensuring in Ukraine a full-fledged turnover of agricultural land and effective state mechanisms of regulatory economic policy in agricultural land use.
Keywords: agricultural land, drought, land reclamation, model, system, rational use of land, sustainability of agricultural production.
Bester Tawona Mudereri, Elfatih Mohamed Abdel-Rahman, Timothy Dube
et al.
Monitoring of destructive invasive weeds such as those from the genus Striga requires accurate, near real-time predictions and integrated assessment techniques to enable better surveillance and consistent assessment initiatives. Thus, in this study, we predicted the potential ecological niche of Striga (Striga asiatica) weed in Zimbabwe, to identify and understand its propagation and map potentially vulnerable cropping areas. Vegetation phenology from remote sensing, bioclimatic and other environmental variables (i.e. cropping system, edaphic, land surface temperature, and terrain) were used as predictors. Six machine learning modeling techniques and the ensemble model were evaluated on their suitability to predict current and future Striga weed distributional patterns. The mentioned predictors (n = 40) were integrated into six models with “presence-only” training and evaluation data, collected in Zimbabwe over the period between the 12th and 28th of March 2018. The area under the curve (AUC) and true skill statistic (TSS) were used to measure the performance of the Striga modeling framework. The results showed that the ensemble model had the strongest Striga occurrence predictive power (AUC = 0.98; TSS = 0.93) when compared to the other modeling algorithms. Temperature seasonality (Bio4), the maximum temperature of the warmest month (Bio5) and precipitation seasonality (Bio15) were determined to be the most dominant bioclimatic variables influencing Striga occurrence. “Start of the season” and “season minimum value” of the “Enhanced Vegetation Index base value” were the most relevant remote sensing-based variables. Based on projected climate change scenarios, the study showed that up to 2050, the suitable area for Striga propagation will increase by ~ 0.73% in Zimbabwe. The present work demonstrated the importance of integrating multi-source data in predicting possible crop production restraints due to weed propagation. The results can enhance national preparedness and management strategies, specifically, if the current and future risk areas can be identified for early intervention and containment
Suraj Shaikh, Masilamani Palanisamy, Abdul Rahaman Sheik Mohideen
Soil erosion and soil loss is one of the common problems threatening the environment. This degrading phenomenon declines the soil fertility and significantly affects the agricultural activity. As a consequence, the productivity of soil is affected unquestionably. In this reason, there is a basic need to take up conservation and management measures which can be applied to check further soil erosion. Even though, soil erosion is a mass process spread cross the watershed, it is not economically viable to implement conservation techniques to the entire watershed. However, a method is a pre-requisite to identify the most vulnerable areas and quantify the soil erosion. In this study, Revised Universal Soil Loss Equation (RUSLE) has been accepted to estimate soil erosion in the Kummattipatti Nadi watershed part of the Coimbatore district of Tamil Nadu, India. This model has several parameters including runoff-rainfall erosivity factor (R), soil erodability Factor (K), topographic factor (LS), cropping management factor (C), and support practice factor (P). All these layers are prepared through geographical information system (GIS) by using various data sources and data preparation methods. The results of the study shows that the annual average soil loss within the watershed is about 6 t/ha/yr (metric ton per hectare per year). Higher soil erosion is observed in the land use classes of gullied wasteland, open scrub forest and degraded plantation. The soil erosion risk is extremely higher on the steep slopes and adjoining foothills. The proper conservation and management strategies has to be implement in this watershed for the development.
Yukimasa Matsuzawa, Kiyoko Iwatsuki-Horimoto, Yoshinori Nishimoto
et al.
Human influenza A(H2N2) viruses emerged in 1957 and were replaced by A(H3N2) viruses in 1968. The antigenicity of human H2N2 viruses has been tested by using ferret antisera or mouse and human monoclonal antibodies. Here, we examined the antigenicity of human H2N2 viruses by using human plasma samples obtained from 50 aged individuals who were born between 1928 and 1933 and from 33 younger adult individuals who were born after 1962. The aged individuals possessed higher neutralization titers against H2N2 viruses isolated in 1957 and 1963 than those against H2N2 viruses isolated in 1968, whereas the younger adults who were born between 1962 and 1968 possessed higher neutralization titers against H2N2 viruses isolated in 1963 than those against other H2N2 viruses. Antigenic cartography revealed the antigenic changes that occurred in human H2N2 viruses during circulation in humans for 11 years, as detected by ferret antisera. These results show that even though aged individuals were likely exposed to more recent H2N2 viruses that are antigenically distinct from the earlier H2N2 viruses, they did not possess high neutralizing antibody titers to the more recent viruses, suggesting immunological imprinting of these individuals with the first H2N2 viruses they encountered and that this immunological imprinting lasts for over 50 years.
Unmanned aerial vehicles are increasingly being used in close range photogrammetry. Real-time observation of the Earth’s surface and the photogrammetric images obtained are used as material for surveying and environmental inventory. The following study was conducted on a small area (approximately 1 ha). In such cases, the classical method of topographic mapping is not accurate enough. The geodetic method of topographic surveying, on the other hand, is an overly precise measurement technique for the purpose of inventorying the natural environment components. The author of the following study has proposed using the unmanned aerial vehicle technology and tying in the obtained images to the control point network established with the aid of GNSS technology. Georeferencing the acquired images and using them to create a photogrammetric model of the studied area enabled the researcher to perform calculations, which yielded a total root mean square error below 9 cm. The performed comparison of the real lengths of the vectors connecting the control points and their lengths calculated on the basis of the photogrammetric model made it possible to fully confirm the RMSE calculated and prove the usefulness of the UAV technology in observing terrain components for the purpose of environmental inventory. Such environmental components include, among others, elements of road infrastructure, green areas, but also changes in the location of moving pedestrians and vehicles, as well as other changes in the natural environment that are not registered on classical base maps or topographic maps.
A general characteristic degradation
processes at regional level. The dependence
between the coefficients of the properties of
agricultural land and soil conservation index value.
Calculated losses of major crops due to the use of
arable land, which belong to the degraded and
unproductive. The measures to restore the
effectiveness ofthe use ofthese lands.
This article contains a short report on the Vth International Bulgarian Forum under the name of “Political and Ethno-Cultural Interaction between States and Peoples in the Post-Golden Horde Space (15th–16th centuries)”. The forum was held in the city of Yalta (the Crimea) at the 6th–11th of November in 2013. Coordinators of the forum were Shigabutdin Marjani Institute of History of Academy of Sciences of the Republic of Tatarstan and the Crimean branch of Archaeology Institute of National academy of Sciences of the Ukraine. The Forum was attended by many well-known experts, whose reports have caused heated debate. The greatest interest was aroused by the following reports: Kradin Nicolay (Vladivostok, Russia). Medieval States of Eurasian Steppes: general and special; Trepavlov Vadim (Moscow, Russia). Institute of Beklyaribekship in the Socio-Political Structure of the Tatar Khanates; Vladimirov Georgi (Sofia, Bulgaria). Earrings in the Form of a Question Mark from Danubian Bulgaria (13th–14th centuries). Origin and area of distribution; Cherkas Boris (Kiev, Ukraine). Crimea and the Middle Dnieper Region in the Context of the Struggle in the Crimean Khanate in the 15th – the first third of the 16th centuries; Rusev Nikolay (Kishinev, Moldova). Tatars in Moldovan Charters of the 15th century; Izmailov Iskander (Kazan, Russia). Ethnocultural Interaction of the Kazan Khanate Population with Adjacent Territories; Ilnur Mirgaleev (Kazan, Russia). “Chingiz-name” of Utemish-Hadji as a Source for the History of the Turko-Tatar States; Matveev Andrey, Tataurov Sergey (Tomsk, Russia). History of Siberian Khanate: chronology and cartography; Brehunenko Viktor (Kiev, Ukraine). Kazak-Crimean Military-Political Alliances of the end of the 16th – middle of the 17th century.
Auxiliary sciences of history, History of Civilization
In the aftermath of the 5th Regional Conference on Cadastre and Spatial Data Infrastructure (Banja Luka and Laktaši, Bosnia and Herzegovina, June 6–8, 2012), the Republic Authority for Geodetic and Property Affairs of the Republic of Srpska and the Federal Administration for Geodetic and Real Property Affairs published the 5th Regional Study on Cadastre and Spatial Data Infrastructure. The study was produced in the frame of the Project INSPIRATION – Spatial Data Infrastructure in the Western Balkans, which is being realized for the benefit and with cooperation of representatives of eight geodetic administrations in the region (Albania, Bosnia and Herzegovina, Montenegro, Croatia, Kosovo, Macedonia, Serbia) by consortium led by German company GFA of Hamburg, in cooperation with GDi GISDATA of Zagreb, experts from the Austrian Environmental Agency and German company con terra GmbH and financed from the European Union IPA funding programme for 2010.