An accurate and reliable extraction of building structures from high-resolution (HR) remote sensing images is an important research topic in 3D cartography and smart city construction. However, despite the strong overall performance of recent deep learning models, limitations remain in handling significant variations in building scales and complex architectural forms, which may lead to inaccurate boundaries or difficulties in extracting small or irregular structures. Therefore, the present study proposes MSA-UNet, a reliable semantic segmentation framework that leverages multiscale feature aggregation and attentive skip connections for an accurate extraction of building footprints. This framework is constructed based on the U-Net architecture, incorporating VGG16 as a replacement for the original encoder structure, which enhances its ability to capture low-discriminative features. To further improve the representation of image buildings with different scales and shapes, a serial coarse-to-fine feature aggregation mechanism was used. Additionally, a novel skip connection was built between the encoder and decoder layers to enable adaptive weights. Furthermore, a dual-attention mechanism, implemented through the convolutional block attention module, was integrated to enhance the focus of the network on building regions. Extensive experiments conducted on the WHU and Inria building datasets validated the effectiveness of MSA-UNet. On the WHU dataset, the model demonstrated a state-of-the-art performance with a mean Intersection over Union (mIoU) of 94.26%, accuracy of 98.32%, F1-score of 96.57%, and mean Pixel accuracy (mPA) of 96.85%, corresponding to gains of 1.41% in mIoU over the baseline U-Net. On the more challenging Inria dataset, MSA-UNet achieved an mIoU of 85.92%, indicating a consistent improvement of up to 1.9% over the baseline U-Net. These results confirmed that MSA-UNet markedly improved the accuracy and boundary integrity of building extraction from HR data, outperforming existing classic models in terms of segmentation quality and robustness.
As global climate change accelerates, the need for precise and high-resolution carbon emission inventories becomes increasingly urgent, particularly in rapidly developing regions. This study introduces an advanced methodology for constructing regional-scale gridded anthropogenic CO2 emission inventories, integrating the latest energy consumption data and remote sensing technologies. By systematically calculating emissions across various sectors and energy types, and utilizing Geographic Information System (GIS) for spatial distribution, we have generated a high-resolution emission map with a 1 km × 1 km grid. The accuracy of the map was validated through regression analysis with the Multi-resolution Emission Inventory for China (MEIC) dataset, ensuring its reliability. This work provides critical insights for targeted emission reduction strategies, contributing to the formulation of sustainable development policies that align with global climate objectives.
Стаття досліджує питання інтелектуалізації електронних геодезичних інструментів у контексті систем публічного просторового менеджменту, акцентуючи трансформацію від автоматизованих процедур до адаптивних самонавчальних технологічних рішень з інтеграцією принципів цифрової етики. Реалізовано алгоритмічний аналіз із залученням розширеного фільтра Калмана (EKF) та рекурентних нейромережевих архітектур довгої короткочасної пам'яті (LSTM) для адаптивної фільтрації інформаційних потоків, а також методів геопросторової статистики та ГІС-візуалізації для верифікації координатної консистентності. Отримані наукові результати свідчать, що інтелектуалізація детермінує трансформацію до когнітивних систем із сенсорною інтеграцією (GNSS, IMU, EDM), досягаючи міліметрової точності через застосування алгоритмів штучного інтелекту, зокрема EKF та LSTM, для прогностичного моделювання похибок та автокорекції. Встановлено, що хмарна інфраструктура та інтероперабельність із ГІС-платформами (ArcGIS, QGIS) формують уніфіковане цифрове середовище з механізмами валідації даних, що підвищує метрологічну стабільність та етичну підзвітність систем.
Практична значущість дослідження визначається вдосконаленням систем публічного управління, зокрема урбаністичного планування, земельно-кадастрового обліку та інфраструктурного моніторингу, де інтелектуалізовані прилади забезпечують оновлення даних у режимі реального часу та превентивне управління ризиками. Дослідження сприяє підвищенню транспарентності державних реєстрів через цифрові паспорти вимірювань, редукуючи похибки та юридичні колізії в геоінформаційному середовищі. Перспективи подальших наукових розвідок передбачають розробку етичних стандартів для штучного інтелекту в геодезії та інтеграцію з технологіями Інтернету речей (IoT) для створення глобальних мереж моніторингу.
Ключові слова: інтелектуалізація, геодезичні прилади, сенсорна інтеграція, штучний інтелект, геоінформаційні системи, публічне просторове управління.
Fernando Carlos Lopes, Anabela Martins Ramos, Pedro Miguel Callapez
et al.
The EN280 Leba Road is a mountain road that runs along the western slope of Serra da Leba (Humpata Plateau) and its outstanding escarpments, connecting the hinterland areas of the Province of Huila to the coastal Atlantic Province of Namibe, in Southwest Angola. In the Serra da Leba ranges, as in Humpata Plateau, a volcano-sedimentary succession of Paleo-Mesoproterozoic age known as the Chela Group outcrops extensively. This main unit records a pile of sediments with a thickness over 600 m, overlying a cratonic basement with Eburnean and pre-Eburnean granitoids. This sequence is overlain in unconformity by the Leba Formation, which consists of weakly deformed cherty dolostones rich in stromatolites. Along the EN280 Leba Road, in the downward direction, were inventoried and characterized eight sites that, by their exceptional geological content and the singularity of their geoforms, are worth being defined and formalized as geosites: (1) traditional mining clay pit in the Humpata Plateau (post-Eburnean Paleo-Mesoproterozoic claystones); (2) old lime oven of Leba (post-Eburnean Meso-Neoproterozoic cherty dolostones with stromatolites); (3) viewpoint of the Serra da Leba (post-Eburnean Paleo-Mesoproterozoic volcano-sedimentary formations and Eburnean Paleoproterozoic granitoids); (4) vertical beds at the beginning of the descent (post-Eburnean Paleo-Mesoproterozoic volcano-sedimentary formations); (5) slope of the fault propagation fold (post-eburnean Paleo-Mesoproterozoic volcano-sedimentary formations); (6) reverse fault in granitoid rocks (Eburnean Paleoproterozoic granitoids); (7) Dolerite Curve (Eburnean Paleoproterozoic granitoids and dolerites); (8) ductile simple shear zone (Eburnean Paleoproterozoic granitoids and mylonites). These sites were primarily selected using the results of fieldwork (observations, measurements, reproduction of representations, and creation of models), interpretation of remote sensing data, and data from previously published bibliographies and cartography. A quantitative assessment of the selected sites to be preserved through their classification as geosites (integration in a geoconservation strategy) was proposed. The first position in the numerical assessment is occupied by the landscape dimension geosite “Viewpoint of the Serra da Leba”. This position is conferred, mainly, by its high geological, use, and Management values, being therefore considered the place with the highest geoheritage value in the studied area. Based on the previous characterization and evaluation, several field activities were proposed to be included in a guidebook, highlighting aspects such as landscapes, outcrops, rocks, structures, fossils, and georesources. The high scientific, didactic, and aesthetic values of these geological contexts and their high degree of geodiversity justify their integration into a geoeducational transect, contributing to the appreciation and awareness of the geological heritage of Serra da Leba, as well as to its promotion and scientific and educational dissemination.
ABSTRACTThe presence of airborne allergenic pollen causes a variety of immune reactions and respiratory diseases, threatening human life in severe cases. Climate change is exacerbating the allergenic pollen-induced health risks and adding a significant economic burden to societies. Despite the pressing threats, vital health-related information is not available to the public to date, and the reshaping of future geographic allergenic pollen patterns remains unknown. To help establish a critical allergenic pollen forecasting capacity, a systematic review was conducted and three promising future directions were identified: (1) resolving heterogeneous urban plant species distribution and phenology using fine-resolution satellite constellations; (2) acquiring ancillary information about allergenic pollen and patient symptoms from emerging geospatial big data, such as social media; (3) deciphering the coupled effect of climate change and urbanization on future geographic patterns and phenology of allergenic species. On this basis, we recommend an optimized workflow that combines real-time pollen monitoring networks with high-resolution vegetation information and weather forecast systems, comprehensively considering the production and diffusion process of pollen to establish advanced prediction models. By focusing on critical knowledge gaps, this review provides much needed insight to propel the allergenic pollen forecasting research and eventually benefit the management of urban public health.
Accurate landslide extraction is significant for landslide disaster prevention and control. Remote sensing images have been widely used in landslide investigation, and landslide extraction methods based on deep learning combined with remote sensing images (such as U-Net) have received a lot of attention. However, because of the variable shape and texture features of landslides in remote sensing images, the rich spectral features, and the complexity of their surrounding features, landslide extraction using U-Net can lead to problems such as false detection and missed detection. Therefore, this study introduces the channel attention mechanism called the squeeze-and-excitation network (SENet) in the feature fusion part of U-Net; the study also constructs an attention U-Net landside extraction model combining SENet and U-Net, and uses Sentinel-2A remote sensing images for model training and validation. The extraction results are evaluated through different evaluation metrics and compared with those of two models: U-Net and U-Net Backbone (U-Net Without Skip Connection). The results show that proposed the model can effectively extract landslides based on Sentinel-2A remote sensing images with an F1 value of 87.94%, which is about 2% and 3% higher than U-Net and U-Net Backbone, respectively, with less false detection and more accurate extraction results.
Nowadays, three-dimensional reconstruction is used in various fields like computer vision, computer graphics, mixed reality and digital twin. The three- dimensional reconstruction of cultural heritage objects is one of the most important applications in this area which is usually accomplished by close range photogrammetry. The problem here is that the images are often noisy, and the dense image matching method has significant limitations to reconstruct the geometric details of cultural heritage objects in practice. Therefore, displaying high-level details in three-dimensional models, especially for cultural heritage objects, is a severe challenge in this field. In this paper, the shape from polarization method has been investigated, a passive method with no drawbacks of active methods. In this method, the resolution of the depth maps can be dramatically increased using the information obtained from the polarization light by rotating a linear polarizing filter in front of a digital camera. Through these polarized images, the surface details of the object can be reconstructed locally with high accuracy. The fusion of polarization and photogrammetric methods is an appropriate solution for achieving high resolution three-dimensional reconstruction. The surface reconstruction assessments have been performed visually and quantitatively. The evaluations showed that the proposed method could significantly reconstruct the surfaces' details in the three-dimensional model compared to the photogrammetric method with 10 times higher depth resolution.
ABSTRACT This paper is a response to the pervasive spread of both cartographic materials related to the COVID-19 pandemic and critical commentaries about such materials. Written by four Italian map-scholars with different theoretical backgrounds but similar socio-cultural and emotional concerns, this paper emerged spontaneously, following the impulse to grasp the rapid movement of coronavirus cartographies, particularly online. Through conversations carried out during the lockdown, the authors collaboratively observed how both scientific and governmental, as well as existential and affective features of the pandemic have been informed by cartographic imaginings. This plurality of cartographic visuals and mapping practices, which appeared soon after the coronavirus outbreak, requires exponential research angles. Approaching the pandemic through and in the proximity of maps, mapping practices, map-like objects and creative cartographies, this paper aims to foreground the speculative, empirical and fast-moving expressions of the pandemic’s cartographic imagery.
Franz-Benjamin Mocnik, Paulo Raposo, W. F. Feringa
et al.
ABSTRACT Epidemics and pandemics are geographical in nature and constitute spatial, temporal, and thematic phenomena across large ranges of scales: local infections with a global spread; short-term decisions by governments and institutions with long-term effects; and diverse effects of the disease on many aspects of our lives. Pandemics pose particular challenges to their visual representation by cartographic means. This article briefly summarizes some of these challenges and outlines ways to approach these. We discuss how to use the information usually available for telling the story of an epidemic, illustrated by the example of the 2019–2020 COVID-19 pandemic. The maps attached to this article demonstrate the discussed cartographic means.
Grant Armstrong, Karlos Arregi, Karen De Clercq
et al.
The Romance Inter-Views are short, multiple Q&A pairs that address key issues, definitions and ideas regarding Romance linguistics. Prominent exponents of different approaches to the study of Romance linguistics are asked to answer some general questions from their viewpoint. The answers are then assembled so that readers can get a comparative picture of what’s going on in the field.
For the first Inter-Views we selected (morpho-)syntactic research, and asked 8 syntacticians, representing four approaches to the study of Romance linguistics, to answer our questions. The approaches we selected are Cartography, Distributed Morphology, Minimalism, and Nanosyntax. The scholars we interviewed are listed hereafter.
For Cartography:
Luigi Rizzi, professor of Linguistics at the Collège de France;
Norma Schifano, lecturer in Modern Languages at the University of Birmingham.
For Distributed Morphology:
Karlos Arregi, associate professor in Linguistics at the University of Chicago;
Andrés Saab, associate researcher at CONICET, Buenos Aires and associate professor in Linguistics at the University of Buenos Aires.
For Minimalism:
Grant Armstrong, associate professor of Spanish Linguistics at the University of Wisconsin-Madison;
Caterina Donati, professor of Linguistics at the CNRS Laboratoire de Linguistique formelle, Université de Paris
For Nanosyntax:
Karen De Clercq, CNRS researcher at the Laboratoire de Linguistique formelle (Université de Paris).
Antonio Fábregas, professor of Linguistics at UIT, The Arctic University of Norway
ABSTRACTThe study was undertaken to produce the landslide susceptibility maps by using Dempster–Shafer, Bayesian probability and logistic regression methods for the southern Western Ghats, Kerala, India. A landslide inventory database of 82 landslides is prepared and used for landslide susceptibility modelling. Twelve landslide conditioning factors including lithology, geomorphological features, slope angle, soil texture, distance from stream, distance from road, distance from lineaments, land use/land cover, slope curvature, rainfall, topographic wetness index and relative relief are extracted from the spatial database and used for modelling. Multi-collinearity among the independent variables were tested and landslide susceptibility maps are constructed. The constructed models were validated with sensitivity, specificity, classification accuracy, ROC-AUC, root mean square error (RMSE) and kappa index. The Bayesian probability model obtained highest ROC-AUC (0.833), sensitivity (0.870), specificity (0.800) and kappa index (0.667) with least RMSE (0.4550) in validation phase. In addition, the study reveals that the agricultural areas have 10°–40° slopes falling on the denudational structural hills are extremely susceptible to landslide occurrence with extended influence from distance from roads, distance from streams and soil texture. The predicted model is trustworthy for future land use planning in the southern Western Ghats to mitigate the risk from landslide hazard.
This book is the first monograph on the theme of “new materialism,” an emerging trend in 21st century thought that has already left its mark in such fields as philosophy, cultural theory, feminism, science studies, and the arts. The first part of the book contains elaborate interviews with some of the most prominent new materialist scholars of today: Rosi Braidotti, Manuel DeLanda, Karen Barad, and Quentin Meillassoux. The second part situates the new materialist tradition in contemporary thought by singling out its transversal methodology, its position on sexual differing, and by developing the ethical and political consequences of new materialism.
Carolyne Bueno Machado, Luiz Eduardo Oliveira e Cruz Aragão
O Brasil vem sendo marcado por intensa crise hídrica em diversas regiões, levando a população ao racionamento de água. Os reservatórios do sistema Cantareira, principal sistema de abastecimento da região metropolitana de São Paulo, atingiram níveis críticos em 2014. Este trabalho teve como objetivo geral avaliar a relação entre precipitação acumulada, cobertura florestal e a área superficial do reservatório Jaguari-Jacareí no período chuvoso de 2003 a 2014. Além disso, uma análise de tendência temporal de precipitação foi conduzida nas sub-bacias hidrográficas principais onde o sistema está inserido. Uma avaliação dos padrões espaciais das formações florestais das sub-bacias dos reservatórios também foi realizada. Os índices de precipitação foram relacionados com a área superficial do reservatório Jaguari-Jacareí. 80% da área de contribuição dos reservatórios apresentaram tendências negativas de precipitação. Os baixos índices pluviométricos em 2014 (45% da média para o período) não foram associados com perda de cobertura por vegetação desde 2003, no entanto, as sub-bacias com maior percentual de vegetação demonstraram tendências de precipitação menos negativas, associadas com a capacidade da vegetação em regular o clima, podendo amenizar os períodos de estiagem. O comportamento do reservatório principal possuiu grande correlação (R>0,7) com a precipitação acumulada em dezembro, janeiro e fevereiro. Assim, os baixos índices pluviométricos somados ao abastecimento já insuficiente e ao constante crescimento dos municípios abastecidos causaram a crise dos reservatórios do Cantareira.
Luis Felipe Mendonça, Ronald Buss de Souza, Rafael Nascimento Reis
et al.
A plataforma continental do sul do Brasil (PCSB) compreende uma importante região econômica do litoral brasileiro. Formada a partir de uma margem continental passiva, apresenta uma baixa declividade com massas d'água e processos dinâmicos com um comportamento sazonal. Este padrão sazonal imprime fortes efeitos no ecossistema e clima da região. No presente trabalho utilizamos o modelo regional oceânico (ROMS) para estudar a distribuição superficial e a variabilidade das massas d'água na PCSB, durante o ano de 2012. Os resultados do modelo foram comparados com as dados de sensoriamento remoto de temperatura superficial do mar (TSM) e altimetria. O modelo foi capaz de reproduzir as principais características de temperatura e salinidade das massas d'água que dominam a PCSB. Identificamos os principais gradientes termohalinos próximo à região da Confluência Brasil-Malvinas, sem identificar gradientes superficiais associados à região da Frente Subtropical de Plataforma. Como consequência da mistura e da oscilação sazonal das águas, a estabilidade da coluna de água dentro da PCSB também muda sazonalmente. O fluxo da Corrente Costeira do Brasil (CCB) para norte, transportando as águas da Pluma do Rio da Prata e da Ãgua Subantártica de Plataforma durante o inverno, concordam com as descrições já realizadas. Mapas sazonais demonstram o comportamento da Corrente do Brasil (CB) e enfatizaram sua importância no fluxo costeiro médio sobre a plataforma continental ao longo do ano. Assim, nossos resultados sugerem que a implementação de um modelo regional oceânico, para a região PCSB, é fundamental para o estudo oceanográfico da região, em series temporais longas.
Salomon Cesar Nguemhe Fils, Carrol Hedwige Bekele Mongo, David Guimolaire Nkouathio
et al.
The potential of Radarsat-1 beam mode Synthetic Aperture Radar (SAR) data processing for geological investigation in an equatorial environment has been evaluated. This approach used textural analysis based on Grey Level Co-occurrence Matrix (GLCM) on our image, followed by Principal Component Analysis (PCA) performed on eight normalized co-occurrence indices created (mean, variance, homogeneity, contrast, dissimilarity, entropy, second moment and correlation) and directional filters for lithological discriminations and lineament investigations. Red-Green-Blue (RGB) color-composite was applied to three of the indices, the mean, variance and homogeneity, highlighting the morphostructure of the study area and facilitate lithology discrimination. The PC1 band was multiplied by itself (as PC1 × PC1 image) to enhance the information contained in this neo-canal and to reduce noise during filtering. Directional filters were then applied to the PC1 × PC1 image at 0°, 45°, 90° and 135° directions and the structure lines were extracted manually in a GIS software. From the results obtained, color-composite produced image map containing lithological units easily identified formations such as continental and coastal deposits, sedimentary stack, micaschists, garnet micaschists, micaceous quartzites, charnockitic orthogneisses, and coincided with those already existing on published geological map from Maurizot et al. (1986) and non-published geological map after IRGM geological field campaign. A total of 572 lineaments features (fractures and major faults) were identified on the filtered images and mapped. Major structures (faults) were considered as those clearly identified in the four directions while minor structures (fractures) were those observed in at least two directions. They are oriented in one of the two main directions: NE-SW (N040–N060) and NNW-SSE (N345–N360). The lineament result showed those that already existed on the reference maps and the newly updated lineaments. Spatial relationships between mapped lineaments and areas of current and historical mining exploration were examined by overall lineament density. GPS points of gold indices existing in the area correlate with areas of high lineament density particularly around the Ngovayang massif within the Paleoproterozoic Nyong unit. This study stresses the usefulness of remote sensing data and methods in field campaign, improvement of published geological maps and mining prospecting in areas with an equatorial climate. Keywords: RADARSAT1, GLCM, PCA, Directional filters, Geological investigation, Equatorial environment