Evaluation of deep learning algorithms for landslide susceptibility mapping in an alpine-gorge area:a case study in Jiuzhaigou County

With its high mountains,deep valleys,and complex geological formations,the Jiuzhaigou County has the typical characteristics of a disaster-prone mountainous region in southwestern China.On August 8,2017,a strong Ms 7.0 earthquake occurred in this region,causing some of the mountains in the area to become loose and cracked.Therefore,a survey and evaluation of landslides in this area can help to reveal hazards and take effective measures for subsequent disaster management.However,different evaluation models can yield different spatial distributions of landslide susceptibility,and thus,selecting the appropriate model and performing the optimal combination of parameters is the most effective way to improve susceptibility evaluation.In order to construct an evaluation indicator system suitable for Jiuzhaigou County,we extracted 12 factors affecting the occurrence of landslides,including slope,elevation and slope surface,and made samples.At the core of the transformer model is a self-attentive mechanism that enables any two of the features to be interlinked,after which feature extraction is performed via a forward propagation network(FFN).We exploited its coding structure to transform it into a deep learning model that is more suitable for landslide susceptibility evaluation.The results show that the transformer model has the highest accuracy(86.89%),followed by the random forest and support vector machine models(84.47%and 82.52%,respectively),and the logistic regression model achieves the lowest accuracy(79.61%).Accordingly,this deep learning model provides a new tool to achieve more accurate zonation of landslide susceptibility in Jiuzhaigou County.

基于BP神经网络的九寨沟地区地震滑坡危险性预测研究

BP神经网络因具有良好的精度和拟合能力,被广泛地运用在区域性滑坡危险性预测中。本文建立了基于BP神经网络的地震滑坡危险性评价模型并应用于四川九寨沟地区,以2017年8月8日的九寨沟MS7.0地震引发的4834个历史滑坡为例,将其随机划分为70%的训练样本集用于九寨沟地区地震滑坡危险性预测,以及30%的验证样本集对预测结果的精度进行评估。选取高程、坡度、坡向、平行发震断层距离、垂直发震断层距离、震中距离、距道路距离、地面峰值加速度(PGA)以及岩性共9个影响因子,分析发震断层对地震滑坡的控制作用,并总结九寨沟地区地震滑坡空间分布规律特征,其中发震断层、岩性和坡度对九寨沟地区地震滑坡分布产生重要影响。利用模型得到九寨沟地震滑坡危险性预测图,结果显示73.19%的滑坡位于极高和高危险区域,与实际地震滑坡分布基本相符。通过30%的验证样本集来绘制预测成功率曲线,结果表明模型预测成功率(AUC值)为0.90,证实了BP神经网络在九寨沟地区地震滑坡危险性预测中具有良好的精度和拟合能力,评价结果为后续地震滑坡灾害预测和防震减灾工作提供了科学的参考。

九寨沟7.0级地震受灾区灾后经济韧性测度及恢复效率研究

地震的应对与灾后的恢复重建是政府应急管理的重点。为研究灾后区域经济韧性和恢复效率,利用灰色预测模型、韧性测度模型、超效率SBM模型以及DEA-Malmquist指数模型,对2017年九寨沟7.0级地震四川省内5个受灾县及其周边4个县进行灾后经济韧性指数和经济恢复效率分析。结果表明:九寨沟地震受灾地区经济韧性较高,在震后第2年恢复至震前水平;受灾区经济恢复以第三产业为主,发展其服务业是经济恢复的关键;各县的经济恢复效率在震后第2年开始上升,并逐渐超越震前水平,其中九寨沟相关地区产业结构的调整和升级起到主要作用;技术进步是受灾地区的全要素生产率提升的重中之重。

九寨沟不同森林植被的芬多精成分及含量研究

为了解九寨沟不同森林林分芬多精的成分及相对含量,选择当地3种具有代表性的森林植被类型即油松林(Form.Pinus tabuliformis)、红桦林(Form.Betula albosinensis)和云杉林(Form.Picea asperata)作为研究对象,于2022年4—8月分别对3种森林类型的植物挥发性有机物(又称芬多精)进行采样,并带回实验室采用气相色谱-质谱成(GC/MS)联机法测定林分芬多精的成分及其相对含量,分析芬多精排放与环境因素的关系,以期为九寨沟森林养生游憩的推广和开展提供理论指导。结果表明:九寨沟林分芬多精的主要组成物质为萜烯类化合物,以云杉林含量最高,主要包括(+)-柠檬烯、α-蒎烯和莰烯,β-蒎烯偶有检出;3种林分排放的萜烯类物质相对含量与温度呈正相关,与相对湿度呈负相关。

2013年岷县漳县M_(S)6.6地震和2017年九寨沟M_(S)7.0地震震前地球物理观测异常空间分布机理分析

对甘东南地区2013年岷县漳县M_(S)6.6地震和2017年九寨沟M_(S)7.0地震震前地球物理观测异常特征进行总结梳理。根据活动构造单元对地球物理观测台站进行区域划分,统计了相关构造单元上异常的数量和百分比,以及不同学科震前异常数量、百分比、异常持续时间等特征,并对异常的空间分布和机理进行分析,讨论了活动构造对异常分布的影响、异常强度与震源机制及断层应力之间的关系。结果表明:①2013年岷县漳县M_(S)6.6地震比2017年九寨沟M_(S)7.0地震震前地球物理观测异常百分比高,两次地震的震前电磁异常和跨断层水准测量异常均较为显著,而流体异常不明显;②震前地球物理观测异常分布与活动构造相关,2013年岷县漳县M_(S)6.6地震震前异常主要集中在东昆仑-西秦岭断裂带和六盘山-海原断裂带,2017年九寨沟M_(S)7.0地震震前异常则主要集中在龙门山断裂带和东昆仑-西秦岭断裂带;③两次地震震前地球物理观测异常分布均与GNSS速度场分布特征有较好的对应关系;④安德森断层应力模式解释了2013年岷县漳县M_(S)6.6地震(逆冲型)比2017年九寨沟M_(S)7.0地震(走滑型)的形成需要更多的应力积累,因此2013年岷县漳县M_(S)6.6地震虽然震级较小但震前异常更显著。

九寨沟强震区熊猫海—五花海段震裂山体发育特征及崩塌动力学分析

位于九寨沟世界遗产保护区内的熊猫海—五花海段危岩区,历经“5·12”汶川地震和“8·8”九寨沟强烈地震,崩塌落石频发,成为了控制性特大地质灾害点。该文通过现场调查、无人机测绘,查明了震后震裂山体(危岩)空间分布位置和崩塌落石堆积特征,并结合RocPro3D数值模拟,探讨了高位震裂山体(危岩)崩塌落石运动特征和危害程度。结果显示,熊猫海—五花海段震裂山体落石灾害频发,影响景区道路总长度约1045 m,且在长期差异性风化作用下,崩塌落石灾害危险性有逐渐增大的趋势。危岩Ⅳ区落石模拟结果得到,崩塌落石冲击能量和运动速度整体上呈现先增大后减小的特点,落石达到景区道路的最大冲击能量、弹跳高度和运动速度分别为8673kJ、11.63 m和53.8 m/s,其中WYD3到达块石数量占比最大,达到68.6%,落石直接到达日则沟的块石数量占比小,但平均能量达到1770kJ。基于震裂山体(危岩)分布高位陡坡、成灾动力学强、危害性大,提出以景区道路改为隧道方案,以确保景区运行安全。

Application of Sustainable Development Theories in Ecotourism Destinations—With Jiuzhaigou Scenic Area as a Study Case

By taking Jiuzhaizhou Scenic Area for an example, this study proposed that ecotourism destinations should value the application of science and technology as well as the capital investment, devote more efforts in improving the system construction of the scenic area, especially in the aspects of talent training and management, thoroughly carry out the guideline of "protective development", in this way, to achieve rapid economic growth and environmental protection and bring benefits to local residents.

九寨沟典型苔藓结皮的生态效应研究

苔藓植物作为初生演替阶段的先锋种,其独特的生理结构和脱水复苏能力在水源涵养、土壤保持、生物多样性维持等方面发挥着重要作用。以不同生境下(草地、灌木、乔木林以及空地)东亚砂藓(Racomitrium japonicum)、大灰藓(Hypnum plumaeforme)及阔边匐灯藓(Plagiomnium ellipticum)3种苔藓植物为研究对象,通过野外实地考察与室内分析,评估3种典型苔藓结皮的溶蚀能力、固土以及保水特性对九寨沟国家自然保护区震后恢复的生态效应。结果表明:东亚砂藓具有最高的碳酸酐酶活性(50.5 U·g^(-1) DW),进而具备最大的溶蚀速率(4.8×10^(-4) t·km^(-2)·a^(-1) CO_(2))与碳汇量(2.12 mg·m^(-2)·a^(-1))。不同生境条件下的不同苔藓固土能力不同,其中大灰藓结皮层的固土量最高(3.1×103 kg·hm^(-2)),最高固土率可达到自身干重的2倍以上。此外,阔边匍灯藓的保水能力均高于大灰藓与东亚砂藓,其保水量维持在1100-1400 kg·hm^(-2)之间,保水率可达自身干重的8倍以上。综上,在利用苔藓结皮进行生态恢复过程中,建议从成土、固土、保水等生态修复的角度出发,针对不同阶段、不同生境条件选择特定藓种,以加快九寨沟地区震后的生态恢复与重建。

ON BIO-EFFECTS ON KARST LANDSCAPE IN JIUZHAIGOU CONSERVATION, SICHUAN PROVINCE, CHINA—WITH SPECIAL REFERENCE TO A MICROMORPHOLOFICAL APPROACH

Jiuzhaigou Conservation is a typical karst region with scenic tufa constructive landscape. With observation in situ and optical microscope as well as scanning electronic microscope, a series minor and micro biokarst solution features and related agents were identified and described related to local environmental condition, and also the bioeffect on karst deposition in formation of the local tufa dammed lakes were elucidated and discussed.It is shown in the cycle model proposed in the paper that many organisms (algae,mosses,and bushes etc.) with various effects (assimilation,interception,encrustation,trapping and binding etc.)on tufa deposition play an important role throughout the compound cycle process of the tufa dam gradation,i.e.the formation of the tufa dammed lakes in the stream channels which are character of local karst landscape.

基于生境适宜性评价和地灾影响的九寨沟大熊猫栖息地保护重点区域分析

综合海拔、植被类型、主食竹分布等环境因子,基于MaxEnt模型对九寨沟自然保护区进行大熊猫生境的适宜性评价,发现大熊猫偏好海拔2 700~3 500 m、坡度10°左右有竹子分布且郁闭度在75%以上的林地活动。在此基础上叠加地灾影响范围,根据适宜生境的分布特征和地灾影响情况,识别大熊猫栖息地保护的重点区域,以期更有针对性地开展大熊猫及其栖息地的保护工作。

九寨沟7.0级地震孕育过程中的地震学特征

以2017-08-08四川九寨沟7.0级地震为研究对象,使用地震前震中附近10个台站宽频带地震仪数据计算地面运动速度的排列熵,讨论地面运动排列熵的时空变化与大地震孕育之间的关系。结果表明,2017-07下旬,震中附近排列熵出现两次异常变化,幅度最大的一次出现在2017-07末。10个台站均存在熵减过程,其中马尔康台(MEK)、舟曲台(ZHQ)和迭部台(DBT)的排列熵下降幅度较大,熵值分别为0.75、0.76和0.79,与均值相比分别下降12%、12%和10%。多个台站熵值的降低表明,地壳运动中有序振动信号的占比增大。震中东北部和西南部低值区的空间演变图像也表明,熵值异常变化与此次大地震的形成有关。结合以往研究结果认为,青藏高原地块的东移与华北地块和华南地块的阻挡导致此次地震的能量积累,受阻后的中下地壳物质上涌和侧挤引发九寨沟7.0级地震。

中国伪瘤姬蜂属一新种(膜翅目:姬蜂科)及世界已知种检索表

首次在四川发现伪瘤姬蜂属(Pseudopimpla Habermehl)的分布,并记录该属1新种:九寨沟伪瘤姬蜂(Pseudopimpla jiuzhaiensis Li&Sun,sp.nov.),给出该种的形态描述和特征图,提供了世界已知种检索表。标本采自四川省九寨沟国家级自然保护区,保存于国家林业和草原局生物灾害防控中心昆虫博物馆。

Geometry and tectonic deformation of the seismogenic structure for the 8 August 2017 M_S 7.0 Jiuzhaigou earthquake sequence,northern Sichuan, China

To reveal the geometry of the seismogenic structure of the Aug. 8, 2017 M_S 7.0 Jiuzhaigou earthquake in northern Sichuan,data from the regional seismic network from the time of the main event to Oct. 31, 2017 were used to relocate the earthquake sequence by the tomoDD program, and the focal mechanism solutions and centroid depths of the M_L ≥ 3.5 events in the sequence were determined using the CAP waveform inversion method. Further, the segmental tectonic deformation characteristics of the seismogenic faults were analyzed preliminarily by using strain rosettes and areal strains(As). The results indicate:(1) The relocated M_S 7.0 Jiuzhaigou earthquake sequence displays a narrow ～ 38 km long NNW-SSE-trending zone between the NW-striking Tazang Fault and the nearly NSstriking Minjiang Fault, two branches of the East Kunlun Fault Zone. The spatial distribution of the sequence is narrow and deep for the southern segment, and relatively wide and shallow for the northern segment. The initial rupture depth of the mainshock is 12.5 km, the dominant depth range of the aftershock sequence is between 0 and 10 km with an average depth of 6.7 km. The mainshock epicenter is located in the middle of the aftershock region, showing a bilateral rupture behavior. The centroid depths of 32 M_L ≥ 3.5 events range from 3 to 12 km with a mean of about 7.3 km, consistent with the predominant focal depth of the whole sequence.(2) The geometric structure of the seismogenic fault on the southern section of the aftershock area(south of the mainshock) is relatively simple, with overall strike of ～150° and dip angle ～75°, but the dip angle and dip-orientation exhibit some variation along the segment. The seismogenic structure on the northern segment is more complicated; several faults, including the Minjiang Fault, may be responsible for the aftershock activities. The overall strike of this section is ～159° and dip angle is ～59°, illustrating a certain clockwise rotation and a smaller dip angle than the southern segment. The differences between the two segments demonstrate variation of the geometric structure along the seismogenic faults.(3) The focal mechanism solutions of 32 M_L ≥ 3.5 events in the earthquake sequence have obvious segmental characteristics. Strike-slip earthquakes are dominant on the southern segment, while 50% of events on the northern segment are thrusting and oblique thrusting earthquakes, revealing significant differences in the kinematic features of the seismogenic faults between the two segments.(4) The strain rosettes for the mainshock and the entire sequence of 31 M_L ≥ 3.5 aftershocks correspond to strike-slip type with NWW-SEE compressional white lobes and NNE-SSW extensional black lobes of nearly similar size. The strain rosette and As value of the entire sequence of 22 M_L ≥ 3.5 events on the southern segment are the same as those of the M_S 7.0 mainshock,indicating that the tectonic deformation here is strike-slip. However, the strain rosette of the entire sequence of 10 M_L ≥ 3.5 events on the northern segment show prominent white compressional lobes and small black extensional lobes, and the related As value is up to 0.52,indicating that the tectonic deformation of this segment is oblique thrusting with a certain strike-slip component. Differences between the two segments all reveal distinctly obvious segmental characteristics of the tectonic deformation of the seismogenic faults for the Jiuzhaigou earthquake sequence.

Seismogenic fault and topography control on the spatial patterns of landslides triggered by the 2017 Jiuzhaigou earthquake

Jiuzhaigou National Park, located in northwest plateau of Sichuan Province, is a UNESCO World Heritage Site, and one of the most popular scenic areas in China. On August 8, 2017, a Mw 6.5 earthquake occurred 5 km to the west of a major scenic area, causing 25 deaths and injuring 525, and the Park was seriously affected. The objective of this study was to explore the controls of seismogenic fault and topographic factors on the spatial patterns of these landslides. Immediately after the main shock, field survey, remote-sensing investigations, and statistical and spatial analysis were undertaken. At least 2212 earthquake-triggered landslides were identified, covering a total area of 11.8 km^2. Thesewere mainly shallow landslides and rock falls. Results demonstrated that landslides exhibited a close spatial correlation with seismogenic faults. More than 85% of the landslides occurred at 2200 to 3700 m elevations. The largest quantity of landslides was recorded in places with local topographic reliefs ranging from 200 to 500 m. Slopes in the range of ~20°-50° are the most susceptible to failure. Landslides occurred mostly on slopes facing east-northeast(ENE), east(E), east-southeast(ESE), and southeast(SE), which were nearly vertical to the orientation of the seismogenic fault slip. The back-slope direction and thin ridge amplification effects were documented. These results provide insights on the control of the spatial pattern of earthquake-triggered landslides modified by the synergetic effect of seismogenic faults and topography.

Integrated rockfall hazard and risk assessment along highways: An example for Jiuzhaigou area after the 2017 Ms 7.0 Jiuzhaigou earthquake, China

This work addresses the integrated assessment of rockfall(including landslides) hazards and risk for S301, Z120, and Z128 highways, which are important transportation corridors to the world heritage site Jiuzhai Valley National Park in Sichuan, China. The highways are severely threatened by rockfalls or landslide events after the 2017 Ms 7.0 Jiuzhaigou earthquake. Field survey(September 14-18 th, 2017, May 15-20 th, 2018, and September 9-17 th, 2018), unmanned aerial vehicle(UAV), and satellite image identified high-relief rockfalls and road construction rockfalls or landslides along the highway. Rockfall hazard is qualitatively evaluated using block count, velocity, and flying height through a 3D rockfall simulation at local and regional scales. Rockfall risk is quantitatively assessed with rockfall event probability, propagation probability, spatial probability, and vulnerability for different block volume classes. Approximately 21.5%, 20.5%, and 5.3% of the road mileage was found to be subject to an unacceptable(UA) risk class for vehicles along S301, Z120, and Z128 highways, respectively. Approximately 20.1% and 3.3% of the road mileage belong to the UA risk class for tourists along Z120 and Z128 highways, respectively. Results highlighted that high-relief rockfall events were intensively located at K50 to K55(Guanmenzi to Ganheba) and K70 to K72(Jiudaoguai to Shangsizhai Village) road mileages along S301 highway and KZ18 to KZ22(Five Flower Lake to Arrow Bamboo Lake) road mileages, KZ30(Swan Lake to Virgin Forests), and KY10.5 kilometers in Jiuzhai Valley. Rockfalls in these locations were classified under the UA risk class and medium to very high hazard index. Road construction rockfalls were located at K67(Jiuzhai Paradise) and K75–K76 kilometers along S301 highway and KZ12 to KZ14(Rhino Lake to Nuorilang Waterfall), KZ16.5 to KZ17.5(Golden Bell Lake), KY5(Lower Seasonal Lake), and KY14(Upper Seasonal Lake) kilometers along Z120 and Z128 highway in Jiuzhai Valley. Rockfalls in these areas were within a reasonable practicable risk to UA risk class and very low to medium hazard index. Finally, defensive measures, including flexible nets, concrete walls, and artificial tunnels, could be selected appropriately on the basis of the rockfall hazard index and risk class. This study revealed the integration between qualitative rockfall hazard assessment and quantitative rockfall risk assessment, which is crucial in studying rockfall prevention and mitigation.

Assessment of prospective hazards resulting from the 2017 earthquake at the world heritage site Jiuzhaigou Valley, Sichuan, China

On August 8, 2017, a Ms = 7.0 magnitude earthquake occurred in the Jiuzhaigou Valley, in Sichuan Province, China(N: 33.20°, E: 103.82°). Jiuzhaigou Valley is an area recognized and listed as a world heritage site by UNESCO in 1992. Data analysis and field survey were conducted on the landslide, collapse, and debris flow gully, to assess the coseismic geological hazards generated by the earthquake using an unmanned aerial vehicle(UAV), remote-sensing imaging, laser range finders, geological radars, and cameras. The results highlighted the occurrence of 13 landslides, 70 collapses, and 25 potential debris flow gullies following the earthquake. The hazards were classified on the basis of their size and the potential property loss attributable to them. Consequently, 14 large-scale hazards, 30 medium-sized hazards, and 64 small hazards accounting for 13%, 28%, and 59% of the total hazards, respectively, were identified. Based on the variation tendency of the geological hazards that ensued in areas affected by the Kanto earthquake(Japan), Chi-chi earthquake(Taiwan China), and Wenchuan earthquake(Sichuan China), the study predicts that, depending on the rain intensity cycle, the duration of geological hazard activities in the Jiuzhaigou Valley may last over ten years and will gradually decrease for the following five to ten yearsbefore returning to pre-earthquake levels. Thus,necessary monitoring and early warning systems must be implemented to ensure the safety of residents,workers and tourists during the construction of engineering projects and reopening of scenic sites to the public.

Quantitative assessment of the impact of earthquakeinduced geohazards on natural landscapes in Jiuzhaigou Valley

Many natural landscapes that lie in high mountain regions are highly susceptible to geological hazards, and their values and integrity are strongly threatened by the hazards. A preliminary framework was proposed to undertake a quantitative assessment of the impact of earthquake-induced geological hazards on the natural landscapes. Four factors reflecting the aesthetic value, ecological value, integrity of landscapes were selected to assess their vulnerability. The impact of earthquake-induced geological hazards on the landscapes is quantitatively expressed as the product of their vulnerability and resilience. The assessment framework was applied to Jiuzhaigou Valley which was severely struck by the Ms 7.0 earthquake on August 8, 2017. Field survey, satellite image interpretation, high-resolution DEM and unmanned aerial vehicle(UAV) reconnaissance were used to retrieve the values of the assessment factors. Twenty seven World Heritage Sites in the valley strongly influenced by the earthquakeinduced geohazards were evaluated. The impact values of two sites of them(Sparking Lake and Nuorilang Waterfall) are up to 8.24 and 4.65, respectively, and their natural landscapes were greatly damaged. The assessment results show a good agreement with the actual damages of the heritage sites.

Management Philosophy and Practices of Habitat Conservation for Jiuzhaigou Nature Reserve, Sichuan, China

Starting from the pressure on habitat of Jiuzhaigou Nature Reserve broughtabout by traveling activity, this paper puts forward such philosophy of community co-management ofconservation-based tourism development for Jiuzhaigou Nature Reserve. According to this philosophy,emphasis is laid on the analysis of the mission of habitat protection, functional division, habitatmaintenance, community construction, scientific study and management organization system. The studyshows that the close relation and significance of rights and interests shared between nature reserveand residents in community, as well as the value of community co-management philosophy ofconservation-based tourism development in sustainable management of nature reserve, have set anexemplary example for other nature reserves.

Territorial suitability assessment and function zoning in the Jiuzhaigou earthquake-stricken area

An earthquake in the Jiuzhaigou area caused numerous secondary disasters, such as rolling stones, land collapse, landslides and debris flow, which badly affected the safety of human settlements and influenced the spatial layout of the post-disaster reconstruction. Therefore, carrying out assessments of land and identifying a suitable zone for human habitats were very important. This research creates the territorial suitability assessment and function zoning conceptual model in the earthquake-stricken area, and the new methods of the territorial suitability evaluation system were used to divide the spatial functional zones of the earthquake stricken area, which provide a theoretical guidance and decisionmaking basis for the reconstruction of the disaster area. The results showed that:(1) The Jiuzhaigou earthquake-stricken area comprises of an ecological area that has a high level of importance to the ecosystem. In the earthquake-stricken area, 65% of national land is at an altitude of 3000-4000 m, and therefore not suitable for a high level of intensive reconstruction, but reconstructed in an eco-friendly manner.(2) The zone suitable for reconstruction comprises mainly of the river valley and the flat terrain of western parts. The land with low suitability is mainly located on steep terrain, such as highmountains and low gullies. The geographic and geomorphic conditions limit the spread of a suitable reconstruction zone.(3) The earthquake-stricken area mainly comprises of a tourism industry gathering area, population gathering area, agriculture and animal husbandry development area, and ecological preservation area with areas of 76 km^2, 44 km^2, 1591 km^2 and 7512 km^2, respectively. Scientifically zoning the reconstruction areas using scientific evaluation may provide guidance for the location of reconstruction sites.

FUZZY SYNTHETIC EVALUATION ON RESIDENT'S PERCEPTIONS OF TOURISM IMPACTS——Case of Jiuzhaigou National Park, Sichuan Province, China

Tourism can have both positive and negative outcomes for residents in tourism destinations, It is a good method to analyze the status of tourism impact by means of investigating residents＇ perceptions of it. Various methods have been used in previous authoritative studies. However, owing to inherent imprecision, difficulties always exist in some conventional methodologies when describing the interpretation of linguistic or measured uncertainties for real-world randoln phenomena. The purpose of this research is to present the fuzzy synthetic evaluation method to investigate residents＇ perceptions of tourisln impacts. At first, basic attributes and a hierarchical framework of tourism impacts are defined and formed. Secondly, the weighted vectors are determined according to the knowledge and experience of experts. Thirdly, the weighted evaluation matrices are aggregated to get the fuzzy sets of tourism impacts. In the last stage, the final fuzzy sets are defuzzified to get the rank of the residents＇ perceptions of tourism impacts. A case study in Jiuzhaigou National Park of China is provided to demonstrate the application of this method.