Accurate prediction of future urban land demand is essential for effective urban management and planning. However, existing studies often focus on predicting total demand within an administrative region, neglecting the spatiotemporal heterogeneities and interrelationships within its subregions, such as grids. This study introduces a dynamic spatiotemporal rolling prediction model (STRM) that integrates historical trends, neighborhood status, and spatial proximity for spatially explicit prediction of urban land demand at a grid level within an administrative region. STRM leverages historical urban land demand and proximity information from neighborhood grids to predict future demand of the foci grid. By integrating history and neighborhood information into a deep forest model, STRM provides an approach for rolling predictions of grid‐level urban land demand. Parameter sensitivity and structural sensitivity analyses of STRM reveal the impact of historical lags, neighborhood size, and spatial proximity on urban land demand predictions. Application of STRM in Wuhan demonstrated the performance of STRM over a 17‐year period (2000–2017), with an average adjusted R2 of 0.89, outperforming other urban land demand prediction models. By predicting demand on a year‐by‐year basis, STRM effectively captures spatiotemporal heterogeneity and enhances the resolution of urban land demand prediction. STRM represents a shift from static macroscopic to dynamic microscopic prediction of urban land demand, offering valuable insights for future urban development and planning decisions.
{"title":"Multidimensional effects of history, neighborhood, and proximity on urban land growth: A dynamic spatiotemporal rolling prediction model (STRM)","authors":"Yingjian Ren, Jianxin Yang, Yang Shen, Lizhou Wang, Zhong Zhang, Zibo Zhao","doi":"10.1111/tgis.13224","DOIUrl":"https://doi.org/10.1111/tgis.13224","url":null,"abstract":"Accurate prediction of future urban land demand is essential for effective urban management and planning. However, existing studies often focus on predicting total demand within an administrative region, neglecting the spatiotemporal heterogeneities and interrelationships within its subregions, such as grids. This study introduces a dynamic spatiotemporal rolling prediction model (STRM) that integrates historical trends, neighborhood status, and spatial proximity for spatially explicit prediction of urban land demand at a grid level within an administrative region. STRM leverages historical urban land demand and proximity information from neighborhood grids to predict future demand of the foci grid. By integrating history and neighborhood information into a deep forest model, STRM provides an approach for rolling predictions of grid‐level urban land demand. Parameter sensitivity and structural sensitivity analyses of STRM reveal the impact of historical lags, neighborhood size, and spatial proximity on urban land demand predictions. Application of STRM in Wuhan demonstrated the performance of STRM over a 17‐year period (2000–2017), with an average adjusted <jats:italic>R</jats:italic><jats:sup>2</jats:sup> of 0.89, outperforming other urban land demand prediction models. By predicting demand on a year‐by‐year basis, STRM effectively captures spatiotemporal heterogeneity and enhances the resolution of urban land demand prediction. STRM represents a shift from static macroscopic to dynamic microscopic prediction of urban land demand, offering valuable insights for future urban development and planning decisions.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"33 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141740954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Belén Pedregal, Gabriel Orozco, Joaquin Osorio, Pilar Díaz‐Cuevas
In this article, we compile and characterize a total of 43 collaborative web map projects by a set of parameters that enable the understanding and comparability of current and future projects. We then develop a comprehensive methodological framework to explore volunteered geographic information (VGI) and spatial data infrastructure (SDI) convergence based on this review. The main results show the dominance of citizen science projects, followed by initiatives promoting sustainability values, local development, and governance. Although values remain low, the potential to achieve convergence in VGI–SDI features is very high in citizen science projects, where the presence of experts and the funding of these projects by governments and decision‐making entities enable quality standards in the collection and distribution of the contributed information. The work concludes by addressing two major challenges facing current VGI projects: firstly, accessing affordable technological solutions that allow the creation of collaborative web maps with SDI‐like functions. Secondly, guaranteeing the project's sustainability and the preservation of the information gathered.
{"title":"Characterizing collaborative mapping projects. A methodological framework for analyzing volunteered geographic information and spatial data infrastructure convergence","authors":"Belén Pedregal, Gabriel Orozco, Joaquin Osorio, Pilar Díaz‐Cuevas","doi":"10.1111/tgis.13210","DOIUrl":"https://doi.org/10.1111/tgis.13210","url":null,"abstract":"In this article, we compile and characterize a total of 43 collaborative web map projects by a set of parameters that enable the understanding and comparability of current and future projects. We then develop a comprehensive methodological framework to explore volunteered geographic information (VGI) and spatial data infrastructure (SDI) convergence based on this review. The main results show the dominance of citizen science projects, followed by initiatives promoting sustainability values, local development, and governance. Although values remain low, the potential to achieve convergence in VGI–SDI features is very high in citizen science projects, where the presence of experts and the funding of these projects by governments and decision‐making entities enable quality standards in the collection and distribution of the contributed information. The work concludes by addressing two major challenges facing current VGI projects: firstly, accessing affordable technological solutions that allow the creation of collaborative web maps with SDI‐like functions. Secondly, guaranteeing the project's sustainability and the preservation of the information gathered.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"65 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141746078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yilan Liao, Yuanhao Shi, Zhirui Fan, Zhiyu Zhu, Binghu Huang, Wei Du, Jinfeng Wang, Liping Wang
Syndromic surveillance is a type of public health surveillance that utilizes nonspecific indicators or symptoms associated with a particular disease or condition to detect and track disease outbreaks early. However, data completeness has been a significant challenge for syndromic surveillance systems in many countries. Incomplete data may make it difficult to accurately identify anomalies or trends in surveillance data. In this study, a new disease mapping method based on a high‐accuracy, low‐rank tensor completion (HaLRTC) algorithm is proposed to estimate the quarterly positivity rate of the human influenza virus (IFV) based on highly insufficient 2010–2015 respiratory syndromic surveillance data from the subtropical monsoon region of China. The HaLRTC algorithm is a spatiotemporal interpolation method applied to fill in missing or incomplete data using a low‐rank tensor structure. The results show that the accuracy (R2 = 0.880, RMSE = 0.037) of the proposed method is much higher than that of three traditional disease mapping methods: Cokriging, hierarchical Bayesian, and sandwich estimation methods. This study provides a new disease mapping approach to improve the quality and completeness of data in syndrome surveillance or other familiar systems with a large proportion of missing data.
{"title":"A new disease mapping method for improving data completeness of syndromic surveillance with high missing rates","authors":"Yilan Liao, Yuanhao Shi, Zhirui Fan, Zhiyu Zhu, Binghu Huang, Wei Du, Jinfeng Wang, Liping Wang","doi":"10.1111/tgis.13200","DOIUrl":"https://doi.org/10.1111/tgis.13200","url":null,"abstract":"Syndromic surveillance is a type of public health surveillance that utilizes nonspecific indicators or symptoms associated with a particular disease or condition to detect and track disease outbreaks early. However, data completeness has been a significant challenge for syndromic surveillance systems in many countries. Incomplete data may make it difficult to accurately identify anomalies or trends in surveillance data. In this study, a new disease mapping method based on a high‐accuracy, low‐rank tensor completion (HaLRTC) algorithm is proposed to estimate the quarterly positivity rate of the human influenza virus (IFV) based on highly insufficient 2010–2015 respiratory syndromic surveillance data from the subtropical monsoon region of China. The HaLRTC algorithm is a spatiotemporal interpolation method applied to fill in missing or incomplete data using a low‐rank tensor structure. The results show that the accuracy (<jats:italic>R</jats:italic><jats:sup>2</jats:sup> = 0.880, RMSE = 0.037) of the proposed method is much higher than that of three traditional disease mapping methods: Cokriging, hierarchical Bayesian, and sandwich estimation methods. This study provides a new disease mapping approach to improve the quality and completeness of data in syndrome surveillance or other familiar systems with a large proportion of missing data.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"19 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141740955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Landslide‐dammed lakes are potentially hazardous and catastrophic for their possible failures and outburst floods (OFs) that will cause disastrous damage and life‐threatening losses, especially in the alpine areas where seismicity is strong and frequent, such as the eastern margin of the Tibetan Plateau. This study focused on spreading an effective numerical model to reconstruct downstream hazards induced by a giant ancient landslide‐dammed lake outburst flood (LLOF) in the upper Minjiang River valley, eastern Tibetan Plateau based on the integration of the hydraulic characteristics of the upstream dammed lake, dam failure and erosion process, and downstream OF dynamics. The peak discharge levels and paleohydraulics of the LLOF were reconstructed using single‐embankment dam‐break program and one‐dimensional steady hydraulic numerical model. The results reveal that the maximum peak discharge of the Diexi paleo LLOF was 73,060–82,235 m3/s, with an uncertainty bound of 73,000–90,000 m3/s (mean value: 81,500 m3/s). Which inferred that the Diexi paleo LLOF was one of the largest known LLOFs in the view of worldwide scope comparing with other types of floods. Then, the hydraulic characteristics and route evolution of the LLOF were simulated in one‐dimensional unsteady numerical model. The results showed that the Diexi paleo LLOF took 7.47 h to transport from Diexi to Wenchuan within the simulated section of 91.23 km, with an average propagation velocity of 3.39 m/s. At the time of 15.57 h, the simulating section (between Diexi and Wenchuan) reached the maximum extent of inundation which was 664.91 km2, with an average value of 7.29 km2/km. Our modeling supports that the numerical model can be used successfully to reconstruct the hydraulics of a paleo LLOF in deep confined gorge environment. The reconstructed paleo LLOF data are of great significance to enrich the regional megaflood records and provide valuable information for geological hazard controls and OF risk assessment within the upper catchment of Minjiang River at the eastern margin of the Tibetan Plateau.
滑坡堰塞湖具有潜在的危险性和灾难性,其可能发生的溃决和溃决洪水将造成灾难性破坏和生命损失,尤其是在青藏高原东缘等地震活动频繁的高寒地区。本研究在综合考虑上游堰塞湖水力特征、溃坝和侵蚀过程以及下游 OF 动力的基础上,建立了重建青藏高原东部岷江上游流域巨型古滑坡堰塞湖溃决洪水(LLOF)下游危害的有效数值模型。利用单堤溃坝程序和一维稳定水力数值模型重建了泸沽湖的泄洪峰值和古水力学特征。结果表明,蝶溪古河床的最大泄洪峰值为 73,060-82,235 m3/s,不确定边界为 73,000-90,000 m3/s(平均值为 81,500 m3/s)。由此推断,与其他类型的洪水相比,迭溪古大洪水是已知世界范围内最大的大洪水之一。随后,在一维非稳态数值模型中模拟了蝶溪古溃决洪水的水力特征和路线演化过程。结果表明,蝶溪古LLOF在91.23 km的模拟河段内,从蝶溪到汶川需要7.47 h,平均传播速度为3.39 m/s。在 15.57 h 时,模拟断面(蝶溪至汶川)达到最大淹没范围 664.91 km2,平均值为 7.29 km2/km。我们的建模结果表明,数值模型可成功用于重建深部封闭峡谷环境中的古河套水力学。重建的古LLOF数据对丰富区域特大洪水记录具有重要意义,并为青藏高原东缘岷江上游流域地质灾害防治和OF风险评估提供了宝贵资料。
{"title":"Hydraulic reconstruction of giant paleolandslide‐dammed lake outburst floods in high‐mountain region, eastern Tibetan Plateau: A case study of the Upper Minjiang River valley","authors":"Junxue Ma, Jian Chen, Chong Xu","doi":"10.1111/tgis.13218","DOIUrl":"https://doi.org/10.1111/tgis.13218","url":null,"abstract":"Landslide‐dammed lakes are potentially hazardous and catastrophic for their possible failures and outburst floods (OFs) that will cause disastrous damage and life‐threatening losses, especially in the alpine areas where seismicity is strong and frequent, such as the eastern margin of the Tibetan Plateau. This study focused on spreading an effective numerical model to reconstruct downstream hazards induced by a giant ancient landslide‐dammed lake outburst flood (LLOF) in the upper Minjiang River valley, eastern Tibetan Plateau based on the integration of the hydraulic characteristics of the upstream dammed lake, dam failure and erosion process, and downstream OF dynamics. The peak discharge levels and paleohydraulics of the LLOF were reconstructed using single‐embankment dam‐break program and one‐dimensional steady hydraulic numerical model. The results reveal that the maximum peak discharge of the Diexi paleo LLOF was 73,060–82,235 m<jats:sup>3</jats:sup>/s, with an uncertainty bound of 73,000–90,000 m<jats:sup>3</jats:sup>/s (mean value: 81,500 m<jats:sup>3</jats:sup>/s). Which inferred that the Diexi paleo LLOF was one of the largest known LLOFs in the view of worldwide scope comparing with other types of floods. Then, the hydraulic characteristics and route evolution of the LLOF were simulated in one‐dimensional unsteady numerical model. The results showed that the Diexi paleo LLOF took 7.47 h to transport from Diexi to Wenchuan within the simulated section of 91.23 km, with an average propagation velocity of 3.39 m/s. At the time of 15.57 h, the simulating section (between Diexi and Wenchuan) reached the maximum extent of inundation which was 664.91 km<jats:sup>2</jats:sup>, with an average value of 7.29 km<jats:sup>2</jats:sup>/km. Our modeling supports that the numerical model can be used successfully to reconstruct the hydraulics of a paleo LLOF in deep confined gorge environment. The reconstructed paleo LLOF data are of great significance to enrich the regional megaflood records and provide valuable information for geological hazard controls and OF risk assessment within the upper catchment of Minjiang River at the eastern margin of the Tibetan Plateau.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"70 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141609147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nik Ahmad Faris Nik Effendi, Nurul Ain Mohd Zaki, Zulkiflee Abd Latif, Mohd Faisal Abdul Khanan
The increase in greenhouse gases in the atmosphere is due to carbon dioxide (CO2), which has affected climate change. Therefore, the forest plays an essential role in carbon storage which absorbs the CO2 and releases oxygen (O2) to stabilize the earth's ecosystem. This research aims to estimate aboveground biomass (AGB) using a combination of airborne hyperspectral and LiDAR data with field observation in a tropical forest. The objective of this study is to test the ability of vegetation indices and topographic features derived from hyperspectral and LiDAR data using machine learning for AGB estimation and to identify the best machine learning algorithms for estimating AGB in tropical forest. In this research, artificial neural network (ANN) and random forest (RF) algorithm were used to predict the AGB using different models with different combinations of variables. During model selection, the best model fit was selected by calculating statistical parameters such as the residual of the coefficient of determination (R2) and root mean square error (RMSE). Based on the statistical indicators, the most suitable model is Model 4 using anRF algorithm with mtry = p, and a combination of field observation, LiDAR, hyperspectral, vegetation indices (VIs), and topography. This model produced R2 = 0.997 and RMSE = 30.653 kg/tree. Therefore, using a combination of field observation and remote sensing data with machine learning techniques is reliable in forest management to estimate AGB in tropical forest.
{"title":"Combination of hyperspectral and LiDAR for aboveground biomass estimation using machine learning","authors":"Nik Ahmad Faris Nik Effendi, Nurul Ain Mohd Zaki, Zulkiflee Abd Latif, Mohd Faisal Abdul Khanan","doi":"10.1111/tgis.13214","DOIUrl":"https://doi.org/10.1111/tgis.13214","url":null,"abstract":"The increase in greenhouse gases in the atmosphere is due to carbon dioxide (CO<jats:sub>2</jats:sub>), which has affected climate change. Therefore, the forest plays an essential role in carbon storage which absorbs the CO<jats:sub>2</jats:sub> and releases oxygen (O<jats:sub>2</jats:sub>) to stabilize the earth's ecosystem. This research aims to estimate aboveground biomass (AGB) using a combination of airborne hyperspectral and LiDAR data with field observation in a tropical forest. The objective of this study is to test the ability of vegetation indices and topographic features derived from hyperspectral and LiDAR data using machine learning for AGB estimation and to identify the best machine learning algorithms for estimating AGB in tropical forest. In this research, artificial neural network (ANN) and random forest (RF) algorithm were used to predict the AGB using different models with different combinations of variables. During model selection, the best model fit was selected by calculating statistical parameters such as the residual of the coefficient of determination (<jats:italic>R</jats:italic><jats:sup>2</jats:sup>) and root mean square error (RMSE). Based on the statistical indicators, the most suitable model is Model 4 using anRF algorithm with <jats:italic>mtry</jats:italic> = p, and a combination of field observation, LiDAR, hyperspectral, vegetation indices (VIs), and topography. This model produced <jats:italic>R</jats:italic><jats:sup>2</jats:sup> = 0.997 and RMSE = 30.653 kg/tree. Therefore, using a combination of field observation and remote sensing data with machine learning techniques is reliable in forest management to estimate AGB in tropical forest.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"27 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141609146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the widespread application of multisource data, the identification of urban polycenters faces the challenge of increasing data costs. This study developed a cost‐effective model for identifying urban polycenters by employing a combination of the Random Forest algorithm and Local Moran's I index. Using point‐of‐interest data from Amap, our model was benchmarked against a multisource data model to verify its effectiveness and accuracy. The results indicate that the single‐source model possesses an accuracy comparable to that of the multisource model in determining the centrality and spatial distribution of urban centers, thus offering a substantial capability to reduce reliance on multisource data. The random forest method exhibits a significant accuracy advantage over traditional ordinary least squares regression methods. However, it also exhibited susceptibility to overfitting and variations in data sampling. This suggests that while the model is highly effective for large‐scale urban studies, it requires careful handling of data inputs. This model can be applied to actual urban planning and research, providing a useful instrument for investigating urban polycentric structures at different spatial scales. This will increase the usefulness of the model in real‐world scenarios and lower the expenses related to analyzing urban data.
随着多源数据的广泛应用,城市多中心的识别面临着数据成本增加的挑战。本研究采用随机森林算法和本地莫兰 I 指数相结合的方法,开发了一种经济高效的城市多中心识别模型。利用 Amap 的兴趣点数据,我们的模型与多源数据模型进行了基准测试,以验证其有效性和准确性。结果表明,单源模型在确定城市中心的中心性和空间分布方面具有与多源模型相当的准确性,从而大大减少了对多源数据的依赖。与传统的普通最小二乘回归方法相比,随机森林方法在准确性方面具有显著优势。不过,它也表现出易受过度拟合和数据采样变化的影响。这表明,虽然该模型在大规模城市研究中非常有效,但需要谨慎处理数据输入。该模型可应用于实际的城市规划和研究,为研究不同空间尺度的城市多中心结构提供有用的工具。这将提高模型在现实世界场景中的实用性,并降低与分析城市数据相关的费用。
{"title":"A global polycenter identification method with single‐source data: The integration of local multisource data recognition","authors":"Yichen Ruan, Xiaoyi Zhang, Qiuxiao Chen, Mingyu Zhang","doi":"10.1111/tgis.13211","DOIUrl":"https://doi.org/10.1111/tgis.13211","url":null,"abstract":"With the widespread application of multisource data, the identification of urban polycenters faces the challenge of increasing data costs. This study developed a cost‐effective model for identifying urban polycenters by employing a combination of the Random Forest algorithm and Local Moran's <jats:italic>I</jats:italic> index. Using point‐of‐interest data from Amap, our model was benchmarked against a multisource data model to verify its effectiveness and accuracy. The results indicate that the single‐source model possesses an accuracy comparable to that of the multisource model in determining the centrality and spatial distribution of urban centers, thus offering a substantial capability to reduce reliance on multisource data. The random forest method exhibits a significant accuracy advantage over traditional ordinary least squares regression methods. However, it also exhibited susceptibility to overfitting and variations in data sampling. This suggests that while the model is highly effective for large‐scale urban studies, it requires careful handling of data inputs. This model can be applied to actual urban planning and research, providing a useful instrument for investigating urban polycentric structures at different spatial scales. This will increase the usefulness of the model in real‐world scenarios and lower the expenses related to analyzing urban data.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"16 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141609145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The problem of visual pollution is a growing concern in urban areas, characterized by intrusive visual elements that can lead to overstimulation and distraction, obstructing views and causing distractions for drivers. Large‐area advertising structures, such as billboards, while being effective advertisement mediums, are significant contributors to visual pollution. Illegally placed or huge billboards can also exacerbate those issues and pose safety hazards. Therefore, there is a pressing need for effective and efficient methods to identify and manage advertising structures in urban areas. This article proposes a deep‐learning‐based system for automatically detecting billboards using consumer‐grade unmanned aerial vehicles. Thanks to the geospatial information from the drone's sensors, the position of billboards can be estimated. Side by side with the system, we share the very first dataset for billboard detection from a drone view. It contains 1361 images supplemented with spatial metadata, together with 5210 annotations.
{"title":"Mapping urban large‐area advertising structures using drone imagery and deep learning‐based spatial data analysis","authors":"Bartosz Ptak, Marek Kraft","doi":"10.1111/tgis.13208","DOIUrl":"https://doi.org/10.1111/tgis.13208","url":null,"abstract":"The problem of visual pollution is a growing concern in urban areas, characterized by intrusive visual elements that can lead to overstimulation and distraction, obstructing views and causing distractions for drivers. Large‐area advertising structures, such as billboards, while being effective advertisement mediums, are significant contributors to visual pollution. Illegally placed or huge billboards can also exacerbate those issues and pose safety hazards. Therefore, there is a pressing need for effective and efficient methods to identify and manage advertising structures in urban areas. This article proposes a deep‐learning‐based system for automatically detecting billboards using consumer‐grade unmanned aerial vehicles. Thanks to the geospatial information from the drone's sensors, the position of billboards can be estimated. Side by side with the system, we share the very first dataset for billboard detection from a drone view. It contains 1361 images supplemented with spatial metadata, together with 5210 annotations.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"37 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141570784","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This article proposes a cartographic solution to represent the emotional landscapes of evasion for a Holocaust survivor, specifically his perceptions of safety or danger during his escape. The victim's emotional landscapes are spatially interpolated using techniques for vectors of both travel direction and magnitude (of perceptions of safety or danger). The implications for the spatial representation of emotions are that emotional landscapes might be better understood by going through an interpolation process, as the statistical analysis reveals spatial trends and autocorrelation. This may help in understanding how the abstract notion of space and the human valence of place vary in relation to each other (or not), and whether and how that variation differs based on distance and direction.
{"title":"A spatial model for the representation of emotional landscapes","authors":"Christopher J. Anderson, Alberto Giordano","doi":"10.1111/tgis.13212","DOIUrl":"https://doi.org/10.1111/tgis.13212","url":null,"abstract":"This article proposes a cartographic solution to represent the emotional landscapes of evasion for a Holocaust survivor, specifically his perceptions of safety or danger during his escape. The victim's emotional landscapes are spatially interpolated using techniques for vectors of both travel direction and magnitude (of perceptions of safety or danger). The implications for the spatial representation of emotions are that emotional landscapes might be better understood by going through an interpolation process, as the statistical analysis reveals spatial trends and autocorrelation. This may help in understanding how the abstract notion of space and the human valence of place vary in relation to each other (or not), and whether and how that variation differs based on distance and direction.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"87 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141570864","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Viktor Marković, Ivan Potić, Dejan Đorđević, Sanja Stojković, Siniša Drobnjak
This study integrates aerial LiDAR data and 2D cartographic information to rapidly develop an advanced non‐photorealistic rendering (NPR) model for rural environment analysis. The focus is enhancing decision support in crises and assessing potential hazards in these territories. The methodology involves capturing LiDAR data from high altitudes and classifying it as Ground, Vegetation, and Buildings. The integration of this data with 2D cartographic information, augmented with attribute data from a GIS database, is achieved through a semi‐automatic process. This process facilitates the creation of detailed 3D models, providing a more nuanced, visually and semantically rich representation of the rural landscape. The study underscores the benefits of combining LiDAR, photogrammetric, and cartographic data for creating accurate and detailed models of the rural environment, which are crucial for effective decision‐making and threat assessment.
{"title":"LiDAR and maps blend for rural decision support","authors":"Viktor Marković, Ivan Potić, Dejan Đorđević, Sanja Stojković, Siniša Drobnjak","doi":"10.1111/tgis.13217","DOIUrl":"https://doi.org/10.1111/tgis.13217","url":null,"abstract":"This study integrates aerial LiDAR data and 2D cartographic information to rapidly develop an advanced non‐photorealistic rendering (NPR) model for rural environment analysis. The focus is enhancing decision support in crises and assessing potential hazards in these territories. The methodology involves capturing LiDAR data from high altitudes and classifying it as Ground, Vegetation, and Buildings. The integration of this data with 2D cartographic information, augmented with attribute data from a GIS database, is achieved through a semi‐automatic process. This process facilitates the creation of detailed 3D models, providing a more nuanced, visually and semantically rich representation of the rural landscape. The study underscores the benefits of combining LiDAR, photogrammetric, and cartographic data for creating accurate and detailed models of the rural environment, which are crucial for effective decision‐making and threat assessment.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"19 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141570865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study delves into the spatio‐temporal dynamics and influencing mechanisms of technology transfer. Leveraging graph theory, we constructed a patent transfer network to understand its evolving patterns. We redefined technology transfer types, analyzed transition probabilities through Markov chain, and summarized their temporal and spatial shifts. Incorporating spatial and nonspatial methods, we explored the heterogeneity of key drivers, such as GDP and internal R&D expenditures, across regions. Our findings reveal that China's AI technology transfer network transformed from sparse to densely interconnected, with transfer types evolving from singular to diversified directions and objects. Provinces often maintain stability or transition to adjacent types, forming agglomerations of similar transfer types. GDP and internal R&D expenditures emerge as key drivers, exerting distinct impacts across regions. This study offers insights to enterprises and policymakers in developing tailored strategies for promoting technology transfer.
本研究深入探讨了技术转让的时空动态和影响机制。利用图论,我们构建了一个专利转让网络,以了解其演变模式。我们重新定义了技术转移类型,通过马尔可夫链分析了过渡概率,并总结了其时空变化。结合空间和非空间方法,我们探索了各地区关键驱动因素的异质性,如 GDP 和内部研发支出。我们的研究结果表明,中国的人工智能技术转移网络从稀疏到密集,转移类型从单一到方向和对象多样化。各省往往保持稳定或向相邻类型过渡,形成相似转移类型的聚集。国内生产总值和内部研发支出成为主要驱动因素,对不同地区产生不同影响。这项研究为企业和政策制定者制定有针对性的促进技术转让战略提供了启示。
{"title":"Untangling spatio‐temporal dynamics and determinants of technology transfer from a patent assignment perspective: The case of China's AI data","authors":"Wen Zeng, Yuefen Wang, Zhichao Ba, Yonghua Cen","doi":"10.1111/tgis.13204","DOIUrl":"https://doi.org/10.1111/tgis.13204","url":null,"abstract":"This study delves into the spatio‐temporal dynamics and influencing mechanisms of technology transfer. Leveraging graph theory, we constructed a patent transfer network to understand its evolving patterns. We redefined technology transfer types, analyzed transition probabilities through Markov chain, and summarized their temporal and spatial shifts. Incorporating spatial and nonspatial methods, we explored the heterogeneity of key drivers, such as GDP and internal R&D expenditures, across regions. Our findings reveal that China's AI technology transfer network transformed from sparse to densely interconnected, with transfer types evolving from singular to diversified directions and objects. Provinces often maintain stability or transition to adjacent types, forming agglomerations of similar transfer types. GDP and internal R&D expenditures emerge as key drivers, exerting distinct impacts across regions. This study offers insights to enterprises and policymakers in developing tailored strategies for promoting technology transfer.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":"30 1","pages":""},"PeriodicalIF":2.4,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141527022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}