Earthquake-induced landslide hazard and vegetation recovery assessment using remotely sensed data and a neural network-based classifier: a case study in central Taiwan

A catastrophic earthquake with a Richter magnitude of 7.3 occurred in the Chi-Chi area of Nantou County on 21 September 1999. Large-scale landslides were generated in the Chiufenershan area of Nantou County in central Taiwan. This study used a neural network-based classifier and the proposed NDVI-based quantitative index coupled with multitemporal SPOT images and digital elevation models (DEMs) for the assessment of long-term landscape changes and vegetation recovery conditions at the sites of these landslides. The analyzed results indicate that high accuracy of landslide mapping can be extracted using a neural network-based classifier, and the areas affected by these landslides have gradually been restored from 211.52 ha on 27 September 1999 to 113.71 ha on 11 March 2006, a reduction of 46.24%, after six and a half years of assessment. In accordance with topographic analysis at the sites of the landslides, the collapsed and deposited areas of the landslide were 100.54 and 110.98 ha, with corresponding debris volumes of 31,983,800 and 39,339,500 m³. Under natural vegetation succession, average vegetation recovery rate at the sites of the landslides reached 36.68% on 11 March 2006. The vegetation recovery conditions at the collapsed area (29.17%) are shown to be worse than at the deposited area (57.13%) due to topsoil removal and the steep slope, which can be verified based on the field survey. From 1999 to 2006, even though the landslide areas frequently suffered from the interference of typhoon strikes, the vegetation succession process at the sites of the landslides was still ongoing, which indicates that nature, itself, has the capability for strong vegetation recovery for the denudation sites. The analyzed results provide very useful information for decision-making and policy-planning in the landslide area.     

Assessment of spatio-temporal variations in vegetation recovery after the Wenchuan earthquake using Landsat data

The 8.0-magnitude Wenchuan earthquake in 2008 damaged the ecology of northwestern Sichuan, China. This study assessed ecological changes within a few years of the earthquake through satellite observations of vegetation dynamics in the earthquake area. As an ecological indicator, the fractional vegetation cover was extracted using the Normalized Difference Vegetation Index based on multi-year Landsat images and was validated using airborne images. We found that the entire mountainous disaster area had recovered by 68.45 % 3 years after the 2008 earthquake. After rapid recovery of vegetation in 2009, the recovery process slowed. The vegetation recovery rate (VRR) in the area heavily damaged by landslides was slightly lower but nearly that of the entire disaster area. In addition, because of differences in the proportions of soil and rock in the damaged areas, recovery of vegetation in the southwest portion of the study area was slower than in the northeast areas. Topographic analysis of vegetation recovery patterns indicated that damage to vegetation was closely related to slope, while recovery of vegetation was more sensitive to elevation. The landscape analysis showed that the recovery rate (65.21 %) of the excellent vegetation cover type was slower than the overall VRR. This study suggests that vegetation recovery is a slow ecological process and that ecological restoration should be implemented in mountainous regions affected by the earthquake.     

利用光学遥感数据、GIS及人工神经网络模型分析区域滑坡灾害

用光学遥感数据和地理信息系统(GIS)分析了马来西亚Selangor地区的滑坡灾害。通过遥感图像解译和野外调查,在研究区内确定出滑坡发生区。通过GIS和图像处理,建立了一个集地形、地质和遥感图像等多种信息的空间数据库。滑坡发生的因素主要为:地形坡度、地形方位、地形曲率及与排水设备距离;岩性及与线性构造距离;TM图像解译得到的植被覆盖情况;Landsat图像解译得到的植被指数;降水量。通过建立人工神经网络模型对这些因素进行分析后得到滑坡灾害图:由反向传播训练方法确定每个因素的权重值,然后用该权重值计算出滑坡灾害指数,最后用GIS工具生成滑坡灾害图。用遥感解译和野外观测确定出的滑坡位置资料验证了滑坡灾害图,准确率为82.92%。结果表明推测的滑坡灾害图与滑坡实际发生区域足够吻合。     

基于遥感和景观分类的北京市裸露农田分析和治理对策

基于遥感影像的决策树分类,结合土地利用图,将北京市农业地表覆盖划分为春玉米、冬小麦、果园、林木苗圃、牧草地、设施农业和畜禽饲养地。考虑海拔、坡度和土壤质地三个因子将北京市分成10个景观区,在景观分区和不同农业用地基础上划分出39类农业景观单元。利用基于遥感影像计算的归一化差异植被指数,结合实地调查验证,分类出北京市冬春季裸露农田。结合景观分类,分析了不同景观单元冬春季地表裸露情况。结果表明：2007—2008年冬春季裸露农田共8.05×104 hm2,主要分布在延庆盆地、密云水库北岸和城区边缘的近郊农业区;海拔和土地利用方式对裸露情况影响较大,其中山区春玉米和平原果园裸露情况绝对面积较大,分别占到总裸露农田面积的40%和17%,牧草地、林木苗圃与设施农业地裸露程度较高。基于不同景观单元裸露程度,结合绿肥种植、保护性耕作、生草覆盖等裸露农田治理方法,探讨了北京市农业产业和景观一体化建设策略。     

Multi-temporal landsat images based on eco-environmental change analysis in and around Chah Nimeh reservoir,Balochestan (Iran)

Chah Nimeh reservoirs have served as a water storage facility, especially during droughts over the last three decades. It is also an important wintering site for migratory birds. In this study, thematic mapper time-series data were derived from Landsat images for prolonged droughts that occurred in two satellite images (2002 and 2011). The data derived from these images were used for the detection of changes in land cover and water storage in the reservoirs. First, a vegetation cover map was produced using soil-adjusted vegetation index and field sampling. Subsequently, land use/cover maps were generated using supervised and hybrid image classification method. Using the spatial change detector (SCD v1.0) software extension, the layers were combined and the change map was generated. The overall accuracy of the produced thematic images was assessed in regards to quantity and allocation disagreements. A total of five classes were defined in this investigation: deep water, shallow water, vegetation, salt land and bare land. The results showed that during the period of study, water volume reduced and vegetation cover increased, especially around the reservoirs that are important as shelter for wintering migratory birds. Comparison of land use/cover maps showed the increase in total available surface of shallow water, which indicated an increase in the habitats for surface feeding and diving birds.     

Landslide occurrence and its relation with terrain factors in the Siwalik Hills,Nepal: case study of susceptibility assessment in three basins

Landslides in the three studied basins of the Siwalik Hills are not random in distribution; they tend to cluster in certain areas implying the control of certain in situ factors or their combination. Landslide controlling in situ factors were reviewed and analyzed from maps, aerial photos and imageries using GIS. Chi square analysis was carried out to test the significance of landslide distribution vis-à-vis in situ factors. Slope gradient and relative relief were consistently significant in landslide distribution. Geology, dip-topography relation, land use and land cover, and vegetation conditions appeared important in landslide occurrence in all three basins either in terms of area or count in any two basins. Slope aspect and altitude tested significant for landslide occurrence in at least two basins. However, upslope flow contributing area, drainage density and distance to lineament were found insignificant in all three basins. In situ factors that tested significant in any two basins were used for landslide susceptibility analysis using a bivariate statistical approach. The distribution of landslides strongly correlates with susceptibility indices. With in situ factors, landslide susceptibility had good correlation with slope gradient and relative relief. Incorporating calculated factor weight values from one basin to the other two basins, proxy susceptibility index maps were also prepared. A moderate to good positive correlation appeared between them implying certain range of confidence for replicating the result for whole of the Siwalik Hills. Slope gradient and relative relief can be used as proxy indicators of landslide susceptible areas in the Siwalik Hills.     

Regional landslide susceptibility analysis using back-propagation neural network model at Cameron Highland,Malaysia

This paper presents landslide susceptibility analysis around the Cameron Highlands area, Malaysia using a geographic information system (GIS) and remote sensing techniques. Landslide locations were identified in the study area from interpretation of aerial photographs and field surveys. Topographical, geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. Ten landslide occurrence factors were selected as: topographic slope, topographic aspect, topographic curvature and distance from drainage, lithology and distance from lineament, soil type, rainfall, land cover from SPOT 5 satellite images, and the vegetation index value from SPOT 5 satellite image. These factors were analyzed using an advanced artificial neural network model to generate the landslide susceptibility map. Each factor’s weight was determined by the back-propagation training method. Then, the landslide susceptibility indices were calculated using the trained back-propagation weights, and finally, the landslide susceptibility map was generated using GIS tools. The results of the neural network model suggest that the effect of topographic slope has the highest weight value (0.205) which has more than two times among the other factors, followed by the distance from drainage (0.141) and then lithology (0.117). Landslide locations were used to validate the results of the landslide susceptibility map, and the verification results showed 83% accuracy. The validation results showed sufficient agreement between the computed susceptibility map and the existing data on landslide areas.     

Landslide hazard mapping at Selangor, Malaysia using frequency ratio and logistic regression models

The aim of this study is to evaluate the landslide hazards at Selangor area, Malaysia, using Geographic Information System (GIS) and Remote Sensing. Landslide locations of the study area were identified from aerial photograph interpretation and field survey. Topographical maps, geological data, and satellite images were collected, processed, and constructed into a spatial database in a GIS platform. The factors chosen that influence landslide occurrence were: slope, aspect, curvature, distance from drainage, lithology, distance from lineaments, land cover, vegetation index, and precipitation distribution. Landslide hazardous areas were analyzed and mapped using the landslide-occurrence factors by frequency ratio and logistic regression models. The results of the analysis were verified using the landslide location data and compared with probability model. The comparison results showed that the frequency ratio model (accuracy is 93.04%) is better in prediction than logistic regression (accuracy is 90.34%) model.     

汶川震区北川县泥石流流域崩滑体时空演变特征

2008年5月12日的汶川大地震引发了大规模同震山体滑坡,随后的强降雨又引发新的山体滑坡,滑坡形成的松散固体物质成为后续泥石流灾害的主要物质来源。为探究强震区泥石流流域崩滑体时空演变特征,文章以北川县魏家沟等8条泥石流流域为例,选取8期遥感影像（2008年震后、“9.24”泥石流发生后、2010年、2011年、2013年、2014年、2015年、2016年）,分别解译崩滑体,统计其空间分布特征。此外,利用归一化植被指数（NDVI）计算研究区内植被覆盖度（VFC）及植被覆盖度恢复率（VCRR）。结果表明:研究区内崩滑体发育面积在强降雨作用后达到峰值,随后呈稳定恢复状态,面积逐年减小。崩滑体在高程900~1 100 m范围、坡度30°~45°范围、坡向90°~135°范围、距沟道150 m范围内发育面积最大。流域内植被覆盖度在2008年“9.24”泥石流灾害后最低,随后呈稳定恢复。自震后到2010年的时期内,植被覆盖度恢复率中等以下区域较多,植被恢复程度较低。2011年之后,流域内大多区域处于植被覆盖度恢复率中等以上等级,植被恢复程度较高。到2016年,研究区植被覆盖度已恢复至较高水平。研究表明:除地层岩性、微地貌等因素影响外,植被对泥石流活动性具有一定的抑制作用。     

50余年来岩溶山地近郊村域土地利用与景观格局演变——以贵州省清镇市王家寨地区为例

选取贵州省清镇市近郊村域王家寨地区为研究对象,在GIS支持下,利用该区域1963年、1982年、2005年、2010年和2015年5期土地利用图形数据叠加分析,提取出研究区50余年来的土地利用/覆盖信息,并结合相应的社会经济统计数据,分析了其驱动力因子,其结果表明:(1)1963—2015年间,土地覆盖类型的总体变化为高被草地和平坝旱耕地明显减少,低被草地、农村居民点、工矿用地、公路用地面积大幅增加,其中,平坝旱耕地有向经济效益更高的土地利用方式转变的趋势;（2）景观格局演变的总体趋势是:自1963年起,斑块数量、斑块密度持续增加,到2015年呈下降趋势,而最大斑块指数逐年减小,形状趋于不规则,同时,近50年景观的多样性指数持续增加;（3）区内土地利用/覆盖和景观格局呈阶段性变化,从1963年到2005年,坡地土地利用活动较强,2005年后,平地土地利用强度增加、农业逐渐转型、聚落持续扩展;（4）区内土地利用及景观格局的变化主要受经济、人口和政策因素的影响。      

吉林西部多时相遥感数据分类方案的构建及应用

为了深化遥感监测方法在生态环境调查中的应用,本文以吉林西部为试验区,设计了一种多时相遥感数据分类方案。该方案以物候信息为主,结合地物特征变量(植被、水体和土地信息)构建的多维特征空间数据集用于土地覆被分类。该遥感分类方案提取了9种地表覆被类型,结果表明:地表植被季节变化信息和土地利用信息的引入能明显改善土地覆被的分类精度;与基于原始波段的分类方案相比,多时相遥感数据分类方案的分类精度最好,总体分类精度为95.50%,Kappa系数为95.04%。     

Manifestation of remote sensing data and GIS on landslide hazard analysis using spatial-based statistical models

This paper presents landslide hazard analysis at Cameron area, Malaysia, using a geographic information system (GIS) and remote sensing data. Landslide locations were identified from interpretation of aerial photographs and field surveys. Topographical and geological data and satellite images were collected, processed, and constructed into a spatial database using GIS and image processing. The factors chosen that influence landslide occurrence are topographic slope, topographic aspect, topographic curvature, and distance to rivers, all from the topographic database; lithology and distance to faults were taken from the geologic database; land cover from TM satellite image; the vegetation index value was taken from Landsat images; and precipitation distribution from meteorological data. Landslide hazard area was analyzed and mapped using the landslide occurrence factors by frequency ratio and bivariate logistic regression models. The results of the analysis were verified using the landslide location data and compared with the probabilistic models. The validation results showed that the frequency ratio model (accuracy is 89.25%) is better in prediction of landslide than bivariate logistic regression (accuracy is 85.73%) model.     

Wetland conservation: Change and fragmentation in Trinidad’s protected areas

Conservation efforts often neglect the importance of monitoring of protected areas, which is key to adaptively managing dynamic landscapes. In many developing countries, like Trinidad, protected areas are set aside as a result of an agreement with an international conservation organization, often resulting in inadequate planning and monitoring of the protected area. Monitoring of protected areas allows for an examination of the conservation scheme implemented and enables improved conservation decisions to be made. The research presented provides an example of the use of technology in monitoring conservation strategies in two protected wetlands, Caroni and Nariva, in Trinidad. Remote sensing and fragmentation analyses are used to quantify land cover change within these two protected wetlands. Results show that the classification of Caroni immediately identifies a shift towards anthropogenic land cover types, suggesting an increase in human activity within the park. This finding is further supported by the continuous measures used, such as decreases in mean NDVI and greenness values suggesting a decrease in the amount or health of the vegetation. While the classification of Nariva suggests a return to natural land covers, the continuous measures of land cover change indicate the opposite. Land cover change analyses are limited in Trinidad and in the Caribbean in general, partly due to satellite data availability, thus this research presents remote sensing and landscape fragmentation analyses as new tools for monitoring land cover change and conservation effectiveness in Trinidad.     

Urban land use/land cover changes in the Tema metropolitan area (1990–2010)

Land use and land cover changes are local and place specific, occurring incrementally in ways that often escape our attention. This study sought to detect changes in land cover in the Tema Metropolis of Ghana from 1990 to 2010. Multispectral Landsat Thematic Mapper data sets of 1990, 2000 and 2007 were acquired, pre-processed and enhanced. Unsupervised classification of the images was performed and six land cover classes (water, wetlands, closed vegetation, open vegetation, cropped lands, and built-up) were derived. The post-classification change detection technique was performed to derive the changes in land cover and their corresponding change matrices. Between 1990 and 2010, built-up areas expanded steadily to become the most prevalent land cover type in the metropolis, reducing vegetation cover dramatically. High population growth with its attendant rise in the demand for housing, and increasing commercial activities, were found to have influenced land cover changes over the period.     

同震滑坡发生概率研究——新一代地震滑坡危险性模型

地震滑坡发生真实概率研究基本空白。本研究创新性的利用贝叶斯概率方法与机器模型开展了中国地震滑坡危险性真实概率研究,制作了第一代中国地震滑坡危险性概率图。基于9个地震案例开展研究,包括1999年台湾集集、2005年克什米尔、2008年汶川、2010年玉树、2013年芦山、2013岷县、2014鲁甸、2015尼泊尔、2017九寨沟地震,这9次地震中7次发生在中国,2005年克什米尔与2015尼泊尔地震均发生在中国邻区,可以更好的控制模型预测精度。这些地震事件均有详细完整的,利用面要素标识的地震滑坡数据,包括306 435处真实的地震滑坡记录。考虑到真实的地震滑坡发生区域,滑坡面积规模的差别,滑坡与不滑样本的比例等因素,共选取了5 117 000个模型训练样本。选择绝对高程、相对高差、坡度、坡向、斜坡曲率、坡位、地形湿度指数、土地覆盖类型、植被覆盖度、与断层距离、地层、年均降水量、地震动峰值加速度共13个地震滑坡影响因子。采用贝叶斯概率方法与机器学习模型相结合,建立地震滑坡发生的多因素影响模型,得到各个连续因子的权重与分类因子的各个分类的权重。再将模型应用到整个中国研究区,地震动峰值加速度因子为触发因子。分别考虑研究区在经历不同地震动峰值加速度（0.1~1 g,每0.1 g一个结果,共10个结果）下的地震滑坡发生真实概率。此外,还结合中国地震动峰值加速度分布图,得到了中国地震动峰值加速度背景下的地震滑坡发生真实概率分布。     

Applying different scenarios for landslide spatial modeling using computational intelligence methods

Landslides every year impose extensive damages to human beings in various parts of the world; therefore, identifying prone areas to landslides for preventive measures is essential. The main purpose of this research is applying different scenarios for landslide susceptibility mapping by means of combination of bivariate statistical (frequency ratio) and computational intelligence methods (random forest and support vector machine) in landslide polygon and point formats. For this purpose, in the first step, a total of 294 landslide locations were determined from various sources such as aerial photographs, satellite images, and field surveys. Landslide inventory was randomly split into a testing dataset 70% (206 landslide locations) for training the different scenarios, and the remaining 30% (88 landslides locations) was used for validation purposes. To providing landslide susceptibility maps, 13 conditioning factors including altitude, slope angle, plan curvature, slope aspect, topographic wetness index, lithology, land use/land cover, distance from rivers, drainage density, distance from fault, distance from roads, convergence index, and annual rainfall are used. Tolerance and the variance inflation factor indices were used for considering multi-collinearity of conditioning factors. Results indicated that the smallest tolerance and highest variance inflation factor were 0.31 and 3.20, respectively. Subsequently, spatial relationship between classes of each landslide conditioning factor and landslides was obtained by frequency ratio (FR) model. Also, importance of the mentioned factors was obtained by random forest (RF) as a machine learning technique. The results showed that according to mean decrease accuracy, factors of altitude, aspect, drainage density, and distance from rivers had the greatest effect on the occurrence of landslide in the study area. Finally, the landslide susceptibility maps were produced by ten scenarios according to different ensembles. The receiver operating characteristics, including the area under the curve (AUC), were used to assess the accuracy of the models. Results of validation of scenarios showed that AUC was varying from 0.668 to 0.749. Also, FR and seed cell area index indicators show a high correlation between the susceptibility classes with the landslide pixels and field observations in all scenarios except scenarios 10_RF and 10_SVM. The results of this study can be used for landslides management and mitigation and development activities such as construction of settlements and infrastructure in the future.     

基于景观生态学的喀斯特生态脆弱区土地利用/覆被变化评价——以贵州猫跳河流域为例

通过运用遥感、地理信息系统以及全球卫星定位系统等技术手段,借助于景观生态学中的景观格局指数以及构建生态价值指数,对位于贵州中部典型喀斯特地区的猫跳河流域1973年以来的土地利用/覆被变化及其对整个区域生态环境状况的影响以及近30年来土地利用的合理性进行了评价。研究表明,在过去的30年间,研究区的土地覆被发生了显著的变化,并对区域的生态环境造成了深刻的影响。1973- 1990年,猫跳河流域的景观趋于破碎化,斑块总数从3 438个增加到3 619个,生态服务价值指数从3 626. 58降低到3 343. 47,土地利用具有明显的不可持续性; 1990- 2002年,猫跳河流域的景观破碎度降低,斑块数量从1990年的3 619个减少到3 312个,整个流域的生态服务指数从3 343. 47上升到3 738. 4,生态环境质量开始向好的方向发展。      

Pre-conditioning factors and susceptibility assessments of Wenchuan earthquake landslide at the Zhouqu segment of Bailongjiang basin, China

In this study, we present a landslide susceptibility assessment carried out after the devastating 2008 Wenchuan earthquake. For the Zhouqu segment in the Bailongjiang basin in north-western China landslide susceptibility was computed by a logistic regression method. This region has been experiencing landslides for a long time, and numerous additional slope failures were triggered by the 2008 Wenchuan earthquake. The data used for this study consists of slope failures attributed to the 2008 earthquake, the 878 post Wenchuan earthquake landslides and collapses inventory build up by combination the field investigation, monoscopic manual interpretation, image classification and texture analysis using SPOT 5 and ALOS remote-sensing image data. All data derived from remote sensing images are validated during field investigations. The landslide pre-disposing factor database was constructed. A digital elevation model (DEM) with a 30 × 30 m resolution, orthophotos, geological and land-use maps and information on peak ground acceleration data from the 2008 earthquake is used. The statistical analysis of the relation between Wencuan earthquake-triggered landslides and pre-disposing factors show the great influence of lithological and topographical conditions for earthquake-triggered slope failures. The quality of susceptibility mapping was validated by splitting the study area into a training and validation set. The prediction capability analysis showed that the landslide susceptibility map could be used for land planning as well as emergency planning by local authorities in this region.     

大布苏地区土地利用及其景观格局变化研究

利用大布苏地区1996年和2001年两个时相的TM遥感图像,获取不同时期的土地利用信息,分析了大布苏地区土地利用时空变化,借助FRAGSTATS软件进行了景观格局变化研究。研究结果表明,土地利用变化的总趋势是水域、荒草地减少,居民用地、耕地增加,土地利用综合程度指数降低;从景观尺度上看,斑块密度、多样性指数、优势度和均匀度指数减小,最大斑块指数、景观形状指数增加。     

Landslide susceptibility mapping using rough sets and back-propagation neural networks in the Three Gorges, China

In the Three Gorges of China, there are frequent landslides, and the potential risk of landslides is tremendous. An efficient and accurate method of generating landslide susceptibility maps is very important to mitigate the loss of lives and properties caused by these landslides. This paper presents landslide susceptibility mapping on the Zigui-Badong of the Three Gorges, using rough sets and back-propagation neural networks (BPNNs). Landslide locations were obtained from a landslide inventory map, supported by field surveys. Twenty-two landslide-related factors were extracted from the 1:10,000-scale topographic maps, 1:50,000-scale geological maps, Landsat ETM + satellite images with a spatial resolution of 28.5 m, and HJ-A satellite images with a spatial resolution of 30 m. Twelve key environmental factors were selected as independent variables using the rough set and correlation coefficient analysis, including elevation, slope, profile curvature, catchment aspect, catchment height, distance from drainage, engineering rock group, distance from faults, slope structure, land cover, topographic wetness index, and normalized difference vegetation index. The initial, three-layered, and four-layered BPNN were trained and then used to map landslide susceptibility, respectively. To evaluate the models, the susceptibility maps were validated by comparing with the existing landslide locations according to the area under the curve. The four-layered BPNN outperforms the other two models with the best accuracy of 91.53 %. Approximately 91.37 % of landslides were classified as high and very high landslide-prone areas. The validation results show sufficient agreement between the obtained susceptibility maps and the existing landslide locations.