Determination of importance for comprehensive topographic factors on landslide hazard mapping using artificial neural network   总被引：1，自引：0，他引：1  

Mutasem Sh. Alkhasawneh  Umi Kalthum Ngah  Lea Tien Tay  Nor Ashidi Mat Isa 《Environmental Earth Sciences》2014,72(3):787-799

A landslide is one of the natural disasters that occur in Malaysia. In addition to the geological factor and the rain as triggering factor, topographic factors such as elevation, slope angle, slope aspect, and curvature are considered as the main causes of landslides. The study in this paper was conducted in three stages. The first stage involved the extraction of extra topographic factors. Previous landslide studies had identified only four of the topographic factors. However, eight new additional factors have also been identified in this study. They are general curvature, longitudinal curvature, tangential curvature, cross-section curvature, surface area, diagonal line length, surface roughness, and rugosity. At this stage, 13 factors were extracted from the digital elevation model. The second stage involved specifying the importance of each factor. The multilayer perceptron network and backpropagation algorithm were used to specify the weight of each factor. Results were verified using the receiver operating characteristics based on the area under the curve method in the third stage. The results indicated 76.07 % accuracy in predicting of landslides, with slope angle as the most important factor while the tangential curvature has the least importance.  相似文献   

A Novel Classifier Based on Composite Hyper-cubes on Iterated Random Projections for Assessment of Landslide Susceptibility     

Binh Thai Pham 《Journal of the Geological Society of India》2018,91(3):355-362

In this paper, the main objective is to discover an application of a novel classifier based on Composite Hyper-cubes on Iterated Random Projections (CHIRP) for assessment of landslide susceptibility at the Uttarakhand Area (India). For this, 1295 historical landslides events and landslide affecting parameters were collected and used for creating training and testing datasets. Other benchmark models namely Logistic Regression (LR), RBF neural network (ANN-RBF), and Naïve Bayes (NB) were chosen for comparison. Analysis results indicate that the CHIRP is the best, followed by the LR, the ANN-RBF, and the NB, respectively. Overall, the CHIRP indicates as a promising and good alternative method that could be used to assess landslide susceptibility in other landslide prone areas.  相似文献   

Climatic hazards,health risk and response in Vietnam: Case studies on social dimensions of vulnerability     

Roger Few  Pham Gia Tran 《Global Environmental Change》2010,20(3):529-538

Vietnam is highly prone to climatic hazards, including extreme weather events and marked seasonal changes. Climatic hazards have wide-ranging implications for human health, but in most hazard-prone countries there has been little household level research on health risks. Drawing on the results of exploratory research in low-income communities in the Central Provinces and the Mekong Delta, this paper uses a qualitative approach to examine how the social dimensions of vulnerability can come into play in the generation of health outcomes associated with hazards. It explores particularly how aspects of economic livelihood, physical location, education and protective behaviour combined to influence the exposure and susceptibility of households, as well as to shape their capability to avoid adverse health impacts. These aspects were closely linked with, but not solely determined by, income-poverty: underlining the argument that understanding of risks to health in low-income settings requires careful analysis of this complex shaping of vulnerability. It also requires recognition that health protection for the poor may be articulated more in terms of protection of wider livelihood assets than preventive health actions per se.  相似文献   

OpenCIS—Open Source GIS‐based web community information system     

Daniel Caldeweyher  Jinglan Zhang  Binh Pham 《International journal of geographical information science》2013,27(8):885-898

Geographic Information System (GIS) technology has many applications and plays a vital role in the majority of the daily operations by government and public administration. However, due to its technical complexity and cost, communities lacking the expertise and resources cannot benefit from this technology. The OpenCIS project, a user‐friendly free Open Source GIS‐based Web Community Information System, seeks to address this issue by bridging the gap between a simple map viewer and full GIS, representing one of the first steps towards the goal of grassroots empowerment through GIS technology.  相似文献   

On the potential for CO2 mineral storage in continental flood basalts - PHREEQC batch- and 1D diffusion-reaction simulations     

Van Pham TH  Aagaard P  Hellevang H 《Geochemical transactions》2012,13(1):5

ABSTRACT: Continental flood basalts (CFB) are considered as potential CO2 storage sites because of their high reactivity and abundant divalent metal ions that can potentially trap carbon for geological timescales. Moreover, laterally extensive CFB are found in many place in the world within reasonable distances from major CO2 point emission sources.Based on the mineral and glass composition of the Columbia River Basalt (CRB) we estimated the potential of CFB to store CO2 in secondary carbonates. We simulated the system using kinetic dependent dissolution of primary basalt-minerals (pyroxene, feldspar and glass) and the local equilibrium assumption for secondary phases (weathering products). The simulations were divided into closed-system batch simulations at a constant CO2 pressure of 100?bar with sensitivity studies of temperature and reactive surface area, an evaluation of the reactivity of H2O in scCO2, and finally 1D reactive diffusion simulations giving reactivity at CO2 pressures varying from 0 to 100?bar.Although the uncertainty in reactive surface area and corresponding reaction rates are large, we have estimated the potential for CO2 mineral storage and identified factors that control the maximum extent of carbonation. The simulations showed that formation of carbonates from basalt at 40?C may be limited to the formation of siderite and possibly FeMg carbonates. Calcium was largely consumed by zeolite and oxide instead of forming carbonates. At higher temperatures (60 - 100?C), magnesite is suggested to form together with siderite and ankerite. The maximum potential of CO2 stored as solid carbonates, if CO2 is supplied to the reactions unlimited, is shown to depend on the availability of pore space as the hydration and carbonation reactions increase the solid volume and clog the pore space. For systems such as in the scCO2 phase with limited amount of water, the total carbonation potential is limited by the amount of water present for hydration of basalt.  相似文献   

越南西北部PhanSiPan地区新生代埃达克质侵入岩时代、成因及构造意义——U-Pb锆石年龄、元素地球化学和Hf同位素证据   总被引：2，自引：1，他引：1  

HIEU Pham Trung  王涛  童英 《岩石学报》2012,28(9):3031-3041

越南西北部PhanSiPan地区新生代花岗岩,高SiO2(69.95%～70.52%)、A12O3(15.77%～17.11%)、K2O(4.97%～5.63%)、Na2O(4.29%～4.98%),K2O/Na2O=1.02～1.31、Sr(744×10-6～1316×10-6),贫Y(6.93×10-6～8.06×10-6),低MgO和CaO,富集LILE元素及LREE,亏损HREE具有典型的埃达克岩特征。采用LA-ICPMS方法对该岩体进行了U-Pb同位素定年和Hf同位素分析,结果表明该岩体为始新世(38Ma)岩浆活动的产物。锆石Hf同位素研究结果显示,εHf(t)变化范围为-5.5至+7.3,二阶段Hf模式年龄(tDM2)为652Ma至1466Ma、集中在1.1～1.3Ga,说明花岗岩岩体主要由中-(新)元古代地壳物质部分熔融形成。部分锆石具有正的εHf(t)值,可能指示花岗岩岩浆形成的过程中存在壳-幔混合相互作用。越南西北部Phan Si Pan地区新生代花岗岩和扬子地块-(哀牢山-金沙江-红河带)高钾富碱的岩石形成的时代和机制具有密切的关系,可能与印度-亚洲大陆的碰撞导致红河带区域性走滑断裂系统的形成有关。  相似文献   

Anthropogenic Radionuclides in the Caspian Sea     

Oregioni  B.  Gastaud  J.  Pham  M. K.  Povinec  P. P. 《Water Resources》2003,30(1):86-91

Analysis and interpretation of the distribution of anthropogenic radionuclides ⁹⁰Sr, ¹³⁷Cs, and ^239,240Pu in the Caspian Sea water are presented. These radionuclides are shown to be of environmental importance and to be useful for studying water mass dynamics.  相似文献   

Hydrogeological investigation in the Mekong Delta around Ho-Chi-Minh City (South Vietnam) by electric tomographyInvestigation hydrogéologique dans le delta du Mékong,autour de la ville de Ho-Chi-Minh (Sud-Vietnam), par tomographie électrique     

Van Ngoc Pham  Danièle Boyer  Jean-Louis Le Mouël  Thi Kim Thoa Nguyen 《Comptes Rendus Geoscience》2002,334(10):733-740

In the Mekong Delta (South Vietnam), the agglomeration of Ho-Chi-Minh (HCM) City, with more than 5 million inhabitants, is confronted with a dramatic shortage of fresh water supply because of the pollution of several aquifers at different depths. The electric tomography, obtained by concurrent inversion of two complementary geoelectrical methods, the Vertical Electrical Sounding (VES) and the Magneto-Telluric Sounding (MTS), turned out to be very efficient to provide a complete electrical image of the underground from the surface until about 800 m depth. This methodology constitutes a very cheap guide for the evaluation of the quality of the groundwater resources in the vast alluvial plain of the Mekong Delta. To cite this article: V.N. Pham et al., C. R. Geoscience 334 (2002) 733–740.  相似文献   

Biomass estimation of Sonneratia caseolaris (l.) Engler at a coastal area of Hai Phong city (Vietnam) using ALOS-2 PALSAR imagery and GIS-based multi-layer perceptron neural networks     

Tien Dat Pham  Kunihiko Yoshino  Dieu Tien Bui 《地理信息系统科学与遥感》2017,54(3):329-353

This study tested the use of machine learning techniques for the estimation of above-ground biomass (AGB) of Sonneratia caseolaris in a coastal area of Hai Phong city, Vietnam. We employed a GIS database and multi-layer perceptron neural networks (MLPNN) to build and verify an AGB model, drawing upon data from a survey of 1508 mangrove trees in 18 sampling plots and ALOS-2 PALSAR imagery. We assessed the model’s performance using root-mean-square error, mean absolute error, coefficient of determination (R²), and leave-one-out cross-validation. We also compared the model’s usability with four machine learning techniques: support vector regression, radial basis function neural networks, Gaussian process, and random forest. The MLPNN model performed well and outperformed the machine learning techniques. The MLPNN model-estimated AGB ranged between 2.78 and 298.95 Mg ha^?1 (average = 55.8 Mg ha^?1); below-ground biomass ranged between 4.06 and 436.47 Mg ha^?1 (average = 81.47 Mg ha^?1), and total carbon stock ranged between 3.22 and 345.65 Mg C ha^?1 (average = 64.52 Mg C ha^?1). We conclude that ALOS-2 PALSAR data can be accurately used with MLPNN models for estimating mangrove forest biomass in tropical areas.  相似文献   

Landslide Hazard Assessment Using Random SubSpace Fuzzy Rules Based Classifier Ensemble and Probability Analysis of Rainfall Data: A Case Study at Mu Cang Chai District,Yen Bai Province (Viet Nam)     

Binh Thai Pham  Dieu Tien Bui  Ha Viet Pham  Hung Quoc Le  Indra Prakash  M. B. Dholakia 《Journal of the Indian Society of Remote Sensing》2017,45(4):673-683

Landslide hazard assessment at the Mu Cang Chai district; Yen Bai province (Viet Nam) has been done using Random SubSpace fuzzy rules based Classifier Ensemble (RSSCE) method and probability analysis of rainfall data. RSSCE which is a novel classifier ensemble method has been applied to predict spatially landslide occurrences in the area. Prediction of temporally landslide occurrences in the present study has been done using rainfall data for the period 2008–2013. A total of fifteen landslide influencing factors namely slope, aspect, curvature, plan curvature, profile curvature, elevation, land use, lithology, rainfall, distance to faults, fault density, distance to roads, road density, distance to rivers, and river density have been utilized. The result of the analysis shows that RSSCE and probability analysis of rainfall data are promising methods for landslide hazard assessment. Finally, landslide hazard map has been generated by integrating spatial prediction and temporal probability analysis of landslides for the land use planning and landslide hazard management.  相似文献