This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble lear...This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.展开更多
This paper highlights the crucial role of Indonesia’s GNSS receiver network in advancing Equatorial Plasma Bubble(EPB)studies in Southeast and East Asia,as ionospheric irregularities within EPB can disrupt GNSS signa...This paper highlights the crucial role of Indonesia’s GNSS receiver network in advancing Equatorial Plasma Bubble(EPB)studies in Southeast and East Asia,as ionospheric irregularities within EPB can disrupt GNSS signals and degrade positioning accuracy.Managed by the Indonesian Geospatial Information Agency(BIG),the Indonesia Continuously Operating Reference Station(Ina-CORS)network comprises over 300 GNSS receivers spanning equatorial to southern low-latitude regions.Ina-CORS is uniquely situated to monitor EPB generation,zonal drift,and dissipation across Southeast Asia.We provide a practical tool for EPB research,by sharing two-dimensional rate of Total Electron Content(TEC)change index(ROTI)derived from this network.We generate ROTI maps with a 10-minute resolution,and samples from May 2024 are publicly available for further scientific research.Two preliminary findings from the ROTI maps of Ina-CORS are noteworthy.First,the Ina-CORS ROTI maps reveal that the irregularities within a broader EPB structure persist longer,increasing the potential for these irregularities to migrate farther eastward.Second,we demonstrate that combined ROTI maps from Ina-CORS and GNSS receivers in East Asia and Australia can be used to monitor the development of ionospheric irregularities in Southeast and East Asia.We have demonstrated the combined ROTI maps to capture the development of ionospheric irregularities in the Southeast/East Asian sector during the G5 Geomagnetic Storm on May 11,2024.We observed simultaneous ionospheric irregularities in Japan and Australia,respectively propagating northwestward and southwestward,before midnight,whereas Southeast Asia’s equatorial and low-latitude regions exhibited irregularities post-midnight.By sharing ROTI maps from Indonesia and integrating them with regional GNSS networks,researchers can conduct comprehensive EPB studies,enhancing the understanding of EPB behavior across Southeast and East Asia and contributing significantly to ionospheric research.展开更多
A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning sys...A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning system) technology and change detection techniques at a 1:50000 mapping scale in the Letianxi Watershed of western Hubei Province, China. Satellite images (Landsat TM 1997 and Landsat ETM 2002) and thematic maps were used to provide comprehensive views of surface conditions such as vegetation cover and land use change. With ER Mapper and ERDAS software, the normalized difference vegetation index (NDVI) was computed and then classified into six vegetation density classes. ARC/INFO and ArcView software were used along with field observation data by GPS for analysis. Results obtained using spatial analysis methods showed that NDVI was a valuable first cut indicator for vegetation and land use systems. A regression analysis revealed that NDVI explained 94.5% of the variations for vegetation cover in the largest vegetation area, indicating that the relationship between vegetation and NDVI was not a simple linear process. Vegetation cover increased in four of areas. This meant 60.9% of land area had very slight to slight vegetation change, while 39.1% had moderate to severe vegetation change. Thus, the study area, in general, was exposed to a high risk of vegetation cover change.展开更多
Cloud computing has emerged as a leading computing paradigm,with an increasing number of geographic information(geo-information) processing tasks now running on clouds.For this reason,geographic information system/rem...Cloud computing has emerged as a leading computing paradigm,with an increasing number of geographic information(geo-information) processing tasks now running on clouds.For this reason,geographic information system/remote sensing(GIS/RS) researchers rent more public clouds or establish more private clouds.However,a large proportion of these clouds are found to be underutilized,since users do not deal with big data every day.The low usage of cloud resources violates the original intention of cloud computing,which is to save resources by improving usage.In this work,a low-cost cloud computing solution was proposed for geo-information processing,especially for temporary processing tasks.The proposed solution adopted a hosted architecture and can be realized based on ordinary computers in a common GIS/RS laboratory.The usefulness and effectiveness of the proposed solution was demonstrated by using big data simplification as a case study.Compared to commercial public clouds and dedicated private clouds,the proposed solution is more low-cost and resource-saving,and is more suitable for GIS/RS applications.展开更多
This study applied a computerized parametric methodology to monitor, map, and quantify land degradation by salinization risk detection techniques at a 1：250 000 mapping scale using geo-information technology. The nor...This study applied a computerized parametric methodology to monitor, map, and quantify land degradation by salinization risk detection techniques at a 1：250 000 mapping scale using geo-information technology. The northern part of the Shaanxi province in China was taken as a case. Multi-temporal remotely sensed materials of both Landsat TM and thematic maps （ETM＋） were used as the bases to provide comprehensive views of surface conditions such as vegetation cover and salinization detection. With ERDAS ver. 9.1 software, the Normalized Differential Salinity Index （NDSl） and Salinity Index （S.I.） were computed and then evaluated for land degradation by salinization. Arc/Info ver. 9.2 software was used along with field observation data （GPS） for analysis. Using spatial analysis methods, results showed that 19 973.1 km^2 （72%） of land had no risk of land degradation by salinization, 3 684.7 km^2 （13%） had slight land degradation by salinization risk, 2 797.9 km^2 （10%） had moderate land degradation by salinization risk, and 1 218.9 km^2 （4%） of the total land area was at a high risk of land degradation by salinization. The study area, in general, is exposed to a high risk of soil salinization.展开更多
The three-period (1995, 1998 and 2003) remote sensing images in Jinan City, China are selected. And the information of green land, construction land, woodland and water body is extracted by using the image processing ...The three-period (1995, 1998 and 2003) remote sensing images in Jinan City, China are selected. And the information of green land, construction land, woodland and water body is extracted by using the image processing module of remote-sensing software and computerized interpretation module. Both the change table and transfer matrix table of land use area are analyzed by modeling module of remote-sensing software. Then, the Geo-information Tupu is obtained; and the temporal and spatial variation of land use in Jinan City is monitored and analyzed by Geo-information Tupu and transfer matrix. Result shows that land use structure change of Jinan City in the years 1995-1998 shows a transformation from green land to construction land. Area of green land circulating into construction land reaches 62.27 square kilometers, accounting for 25.84% of the initial green land. In the year 1998, areas of woodland and green land are reduced due to the urban expansion of Jinan City. However, with the enhancement of people's awareness of environmental protection, areas of woodland and green land gradually increase in the year 2003, which are still less than those in the year 1995.展开更多
基金the University of Transport Technology under the project entitled“Application of Machine Learning Algorithms in Landslide Susceptibility Mapping in Mountainous Areas”with grant number DTTD2022-16.
文摘This study was aimed to prepare landslide susceptibility maps for the Pithoragarh district in Uttarakhand,India,using advanced ensemble models that combined Radial Basis Function Networks(RBFN)with three ensemble learning techniques:DAGGING(DG),MULTIBOOST(MB),and ADABOOST(AB).This combination resulted in three distinct ensemble models:DG-RBFN,MB-RBFN,and AB-RBFN.Additionally,a traditional weighted method,Information Value(IV),and a benchmark machine learning(ML)model,Multilayer Perceptron Neural Network(MLP),were employed for comparison and validation.The models were developed using ten landslide conditioning factors,which included slope,aspect,elevation,curvature,land cover,geomorphology,overburden depth,lithology,distance to rivers and distance to roads.These factors were instrumental in predicting the output variable,which was the probability of landslide occurrence.Statistical analysis of the models’performance indicated that the DG-RBFN model,with an Area Under ROC Curve(AUC)of 0.931,outperformed the other models.The AB-RBFN model achieved an AUC of 0.929,the MB-RBFN model had an AUC of 0.913,and the MLP model recorded an AUC of 0.926.These results suggest that the advanced ensemble ML model DG-RBFN was more accurate than traditional statistical model,single MLP model,and other ensemble models in preparing trustworthy landslide susceptibility maps,thereby enhancing land use planning and decision-making.
基金support received from Telkom University under the“Skema Penelitian Terapan Periode I Tahun Anggaran 2024”and the Memorandum of Understanding for Research Collaboration on Regional Ionospheric Observation(No:092/SAM3/TEDEK/2021)along with colleagues UAA and WPT.INM sincerely thanks the National Institute of Information and Communications Technology(NICT)International Exchange Program 2024−2025(No.2024−007)for their invaluable support for a one-year visiting research at Hokkaido University.
文摘This paper highlights the crucial role of Indonesia’s GNSS receiver network in advancing Equatorial Plasma Bubble(EPB)studies in Southeast and East Asia,as ionospheric irregularities within EPB can disrupt GNSS signals and degrade positioning accuracy.Managed by the Indonesian Geospatial Information Agency(BIG),the Indonesia Continuously Operating Reference Station(Ina-CORS)network comprises over 300 GNSS receivers spanning equatorial to southern low-latitude regions.Ina-CORS is uniquely situated to monitor EPB generation,zonal drift,and dissipation across Southeast Asia.We provide a practical tool for EPB research,by sharing two-dimensional rate of Total Electron Content(TEC)change index(ROTI)derived from this network.We generate ROTI maps with a 10-minute resolution,and samples from May 2024 are publicly available for further scientific research.Two preliminary findings from the ROTI maps of Ina-CORS are noteworthy.First,the Ina-CORS ROTI maps reveal that the irregularities within a broader EPB structure persist longer,increasing the potential for these irregularities to migrate farther eastward.Second,we demonstrate that combined ROTI maps from Ina-CORS and GNSS receivers in East Asia and Australia can be used to monitor the development of ionospheric irregularities in Southeast and East Asia.We have demonstrated the combined ROTI maps to capture the development of ionospheric irregularities in the Southeast/East Asian sector during the G5 Geomagnetic Storm on May 11,2024.We observed simultaneous ionospheric irregularities in Japan and Australia,respectively propagating northwestward and southwestward,before midnight,whereas Southeast Asia’s equatorial and low-latitude regions exhibited irregularities post-midnight.By sharing ROTI maps from Indonesia and integrating them with regional GNSS networks,researchers can conduct comprehensive EPB studies,enhancing the understanding of EPB behavior across Southeast and East Asia and contributing significantly to ionospheric research.
文摘背景:腰椎小关节炎是引起下腰痛的一个主要原因,目前主要依靠MRI进行初步定性诊断,但仍有一定漏诊、误诊的概率发生,因此MR T2^(*)mapping成像技术有望成为定量检查腰椎小关节炎软骨损伤的重要检测手段。目的:探讨MR T2^(*)mapping成像技术在定量分析腰椎小关节炎软骨损伤退变中的应用价值。方法:收集南京医科大学第四附属医院2020年4月至2022年3月门诊或住院合并下腰痛共110例患者,设为病例组;同时招募无症状志愿者80例,设为对照组。对所有纳入对象L1-S1的小关节行3.0 T MR扫描,获取T2^(*)mapping横断位图像和T2WI图像,分别对所有小关节软骨进行Weishaupt分级及T2^(*)值测量,收集数据并行统计学分析。不同小关节Weishaupt分级之间小关节软骨T2^(*)值比较采用单因素方差分析。结果与结论:①经统计分析发现,病例组腰椎小关节软骨T2^(*)值(17.6±1.5)ms明显较对照组(21.4±1.3)ms降低,差异有显著性意义(P<0.05);②在病例组中,随着腰椎小关节Weishaupt分级增加,小关节软骨T2^(*)值也呈逐渐下降趋势,且这种差异有显著性意义(P<0.05);③提示T2^(*)mapping能够较好地显示腰椎小关节软骨损伤的早期病理变化,腰椎小关节软骨的T2^(*)值能够定量评估腰椎小关节的软骨损伤程度;T2^(*)mapping成像技术能为影像学诊断腰椎小关节炎软骨早期损伤提供很好的理论依据,具有重要的临床应用价值。
基金Project Supported by the National Natural Science Foundation of China (No. 40271073).
文摘A computerized parametric methodology was applied to monitor, map, and estimate vegetation change in combination with '3S' (RS-remote sensing, GIS-geographic information systems, and GPS-global positioning system) technology and change detection techniques at a 1:50000 mapping scale in the Letianxi Watershed of western Hubei Province, China. Satellite images (Landsat TM 1997 and Landsat ETM 2002) and thematic maps were used to provide comprehensive views of surface conditions such as vegetation cover and land use change. With ER Mapper and ERDAS software, the normalized difference vegetation index (NDVI) was computed and then classified into six vegetation density classes. ARC/INFO and ArcView software were used along with field observation data by GPS for analysis. Results obtained using spatial analysis methods showed that NDVI was a valuable first cut indicator for vegetation and land use systems. A regression analysis revealed that NDVI explained 94.5% of the variations for vegetation cover in the largest vegetation area, indicating that the relationship between vegetation and NDVI was not a simple linear process. Vegetation cover increased in four of areas. This meant 60.9% of land area had very slight to slight vegetation change, while 39.1% had moderate to severe vegetation change. Thus, the study area, in general, was exposed to a high risk of vegetation cover change.
基金Project(41401434)supported by the National Natural Science Foundation of China
文摘Cloud computing has emerged as a leading computing paradigm,with an increasing number of geographic information(geo-information) processing tasks now running on clouds.For this reason,geographic information system/remote sensing(GIS/RS) researchers rent more public clouds or establish more private clouds.However,a large proportion of these clouds are found to be underutilized,since users do not deal with big data every day.The low usage of cloud resources violates the original intention of cloud computing,which is to save resources by improving usage.In this work,a low-cost cloud computing solution was proposed for geo-information processing,especially for temporary processing tasks.The proposed solution adopted a hosted architecture and can be realized based on ordinary computers in a common GIS/RS laboratory.The usefulness and effectiveness of the proposed solution was demonstrated by using big data simplification as a case study.Compared to commercial public clouds and dedicated private clouds,the proposed solution is more low-cost and resource-saving,and is more suitable for GIS/RS applications.
基金the Geo-information Science and Technology Program (No. IRT 0438)
文摘This study applied a computerized parametric methodology to monitor, map, and quantify land degradation by salinization risk detection techniques at a 1：250 000 mapping scale using geo-information technology. The northern part of the Shaanxi province in China was taken as a case. Multi-temporal remotely sensed materials of both Landsat TM and thematic maps （ETM＋） were used as the bases to provide comprehensive views of surface conditions such as vegetation cover and salinization detection. With ERDAS ver. 9.1 software, the Normalized Differential Salinity Index （NDSl） and Salinity Index （S.I.） were computed and then evaluated for land degradation by salinization. Arc/Info ver. 9.2 software was used along with field observation data （GPS） for analysis. Using spatial analysis methods, results showed that 19 973.1 km^2 （72%） of land had no risk of land degradation by salinization, 3 684.7 km^2 （13%） had slight land degradation by salinization risk, 2 797.9 km^2 （10%） had moderate land degradation by salinization risk, and 1 218.9 km^2 （4%） of the total land area was at a high risk of land degradation by salinization. The study area, in general, is exposed to a high risk of soil salinization.
基金Supported by the Natural Science Foundation of Shandong Province(Y2007E21)the Key Programs for Science and Technology Development of Shandong Province(2006GG2308005)the Soft Science Project of the Shandong Provincial Department of Science and Technology (200624-14)
文摘The three-period (1995, 1998 and 2003) remote sensing images in Jinan City, China are selected. And the information of green land, construction land, woodland and water body is extracted by using the image processing module of remote-sensing software and computerized interpretation module. Both the change table and transfer matrix table of land use area are analyzed by modeling module of remote-sensing software. Then, the Geo-information Tupu is obtained; and the temporal and spatial variation of land use in Jinan City is monitored and analyzed by Geo-information Tupu and transfer matrix. Result shows that land use structure change of Jinan City in the years 1995-1998 shows a transformation from green land to construction land. Area of green land circulating into construction land reaches 62.27 square kilometers, accounting for 25.84% of the initial green land. In the year 1998, areas of woodland and green land are reduced due to the urban expansion of Jinan City. However, with the enhancement of people's awareness of environmental protection, areas of woodland and green land gradually increase in the year 2003, which are still less than those in the year 1995.
