Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

Analysis of debris flow control effect and hazard assessment in Xinqiao Gully,Wenchuan M_(s)8.0 earthquake area based on numerical simulation

Xinqiao Gully is located in the area of the 2008 Wenchuan M_(s)8.0 earthquake in Sichuan province,China.Based on the investigation of the 2023"6-26"Xinqiao Gully debris flow event,this study assessed the effectiveness of the debris flow control project and evaluated the debris flow hazards.Through field investigation and numerical simulation methods,the indicators of flow intensity reduction rate and storage capacity fullness were proposed to quantify the effectiveness of the engineering measures in the debris flow event.The simulation results show that the debris flow control project reduced the flow intensity by41.05%to 64.61%.The storage capacity of the dam decreases gradually from upstream to the mouth of the gully,thus effectively intercepting and controlling the debris flow.By evaluating the debris flow of different recurrence intervals,further measures are recommended for managing debris flow events.

Topographic Features of Debris Flow Gullies in Moxi Basin, Southwestern of China

Debris flows are the main geological hazards in the Moxi basin, which locate on the eastern slope of the M.T Minya Konka, Sichuan province, southwestern of China. The location of 49 debris flow gullies have been identified and mapped from the 1:50000 scale through the extensive field survey across the Moxi basin. The historical events data were collected from documents and visit to local residents, and were used as the basis for frequency analysis. Anymore, topographic features of debris flow gullies have been calculated using GIS software. The analysis showed that 73.5% of the debris flow gullies are not randomly distributed but concentrated directly adjacent to the western side of Moxi fault, and only 26.5% are located to the eastern side. The numbers, frequency, catchments area, gully length, gully slope ratio of these debris flow gullies in Moxi basin were affected by the glaciations and geological activity. The results show potential activity of debris flow in Moxi basin is strong, this research is essential to debris flow hazards mitigation.

Sedimentary Microfacies and Porosity Modeling of Deep-Water Sandy Debris Flows by Combining Sedimentary Patterns with Seismic Data： An Example from Unit I of Gas Field A, South China Sea

Sandy debris flow deposits are present in Unit I during Miocene of Gas Field A in the Baiyun Depression of the South China Sea. The paucity of well data and the great variability of the sedimentary microfacies make it difficult to identify and predict the distribution patterns of the main gas reservoir, and have seriously hindered further exploration and development of the gas field. Therefore, making full use of the available seismic data is extremely important for predicting the spatial distribution of sedimentary microfacies when constructing three-dimensional reservoir models. A suitable reservoir modeling strategy or workflow controlled by sedimentary microfacies and seismic data has been developed. Five types of seismic attributes were selected to correlate with the sand percentage, and the root mean square （RMS） amplitude performed the best. The relation between the RMS amplitude and the sand percentage was used to construct a reservoir sand distribution map. Three types of main sedimentary microfacies were identified： debris channels, fan lobes, and natural levees. Using constraints from the sedimentary microfacies boundaries, a sedimentary microfacies model was constructed using the sequential indicator and assigned value simulation methods. Finally, reservoir models of physical properties for sandy debris flow deposits controlled by sedimentary microfacies and seismic inversion data were established. Property cutoff values were adopted because the sedimentary microfacies and the reservoir properties from well-logging interpretation are intrinsically different. Selection of appropriate reservoir property cutoffs is a key step in reservoir modeling when using simulation methods based on sedimentary microfacies control. When the abnormal data are truncated and the reservoir properties probability distribution fits a normal distribution, microfacies-controlled reservoir property models are more reliable than those obtained from the sequence Gauss simulation method. The cutoffs for effective porosity of the debris channel, fan lobe, and natural levee facies were 0.2, 0.09, and 0.12, respectively; the corresponding average effective porosities were 0.24, 0.13, and 0.15. The proposed modeling method makes full use of seismic attributes and seismic inversion data, and also makes the property data of single-well depositional microfacies more conformable to a normal distribution with geological significance. Thus, the method allows use of more reliable input data when we construct a model of a sandy debris flow.

Fractal Characteristic of Soil in Typical Debris Flow-Triggering Region:A Case Study in Jiangjia Ravine of Dongchuan, Yunnan

The structural features of soil in debris flow-triggering region play an important role in the formation and evolution of debris flow. In this paper, a case study on the fractal of soil particle-size distribution （PSDFs） and pore-solid （PSFs） in Jiangjia Ravine was conducted. The results revealed that the soil in Jiangjia Ravine had significant fractal features and its PSDF and PSF had the same variation trend despite different type of soils in debris flow-triggering region： residual soil （RS） 〉 debris flow deposit （DFD）~clinosol （CL）, their fractal dimension of PSDFs are respectively between 2.62 and 2.96, 2.52 and 2.68, 2.37 and 2.52; and the fractal dimension of PSFs are respectively between 2. 75 and 2.95, 2. 57 and 2. 72, 2.59 and 2.64. The fractal dimension of soil reflected its complexity as a self-organizing system and was closely related to the evolution of soil in debris flow- triggering region.

Geomorphologic analysis and physico-dynamic characteristics of Zhatai-Gully debris flows in SW China

Zhatai gully is a typical debris flow channel in Butuo county of Sichuan province, southwestern China. The geomorphologic features are analyzed and the physical-dynamic characteristics are discussed on the basis of field investigation and laboratory tests. Geomorphologic analysis indicates that Zhatai-gully drainage in relation to debris flow can be divided into source area, transport area, and deposition area. The source area has a steep slope and has very limited vegetation cover, which favors runoff, allowing loose solid materials to be mobilized easily and rapidly. In the transport area, there are many small landslides, lateral lobes, and loose materials distributed on both banks. These landslides are active and constantly providing abundant source of soils for the debris flows. In the deposition area, three old debris-flow deposits of different ages can be observed. The dynamic calculation shows that within the recurrence intervals of 50 and lOO years, debris flow discharges are 155.77m^3/s and 178.19m^3/s and deposition volumes are 16.39 × 10^4 m^3 and 18.14 × 10^4 m^3, respectively. The depositional fan of an old debris flow in the outlet of the gully can be subdivided into six layers. There are three debris flow deposits on left and two on the right side of the gully. Grain-size tests of sediments from the soil, gulley bed deposits, and the fresh and old debris flow deposits showed that high amounts of clay and fine gravel were derived from the soil in the source area whereas much of the gravel fraction were sourced from the gully bed deposits. Comprehensive analysis indicates that Zhatai gully is viscous debris-flow gully with moderate to high frequency and moderate to large magnitude debris flows. The risk of a debris flow disaster in Zhatai-gully is moderate and poses a potential threat to the planned hydroelectric dam. Appropriate engineering measures are suggested in the construction and protection of the planned hydroelectric station.

Coarse grain deposit feature of Guantao formation in western depression Shuyi area of Liaohe basin

The extensive distribution of coarse-grained clastic rock of Guantao formation in Shuyi area of Liaohe basin was considered as a result of fluvial deposit. According to the comprehensive analysis of seism data, well log, core observation and experimental data, this kind of clastic rock is composed of pebblestone-cobblestone, microconglomerate, sand conglomerate, medium-coarse grained sandstone and fine-sandstone. According to the clast composition, sedimentary texture, structure and rock type, 3 kinds of sediment facies can be recognized ie the mixed accumulation-conglomerate dominated debris flow, pebblestone-cobblestone dominated gradient flow and sandstone dominated braided stream. Vertically, the bottom gradient current deposit and top braided stream deposit form fining-upward sediment sequence, and the debris flow deposit distributes in them at random. The sedimentary feature of coarse grain clastic of Guantao formation in Shuyi area is accordant with proximal wet alluvial fan deposited in wet climate at foreland and this kind of alluvial fan is different from the traditional one.

级配与拦挡位置对滑坡碎屑流运动影响研究

为了研究不同级配的高位滑坡碎屑流经多级偏转后冲击不同拦挡结构的运动特性以及致灾效应,结合自然地形构建固定坡度和偏转角度均为45°的离散元模型,并利用DEM软件进行数值模拟分析不同拦挡工况和不同级配对碎屑流颗粒运动过程中能量耗散、最终堆积形态,以及碎屑流冲击挡板的作用高度的影响,进而建立相关冲击力学模型。研究结果显示:(1)上下均设置挡板的工况能有效减缓碎屑流颗粒的平均动能和势能,且能有效降低颗粒流翻越挡板的数量,并降低颗粒流的最大运动距离从而减小致灾范围;随着颗粒组级配的增大,势能时程曲线分散点出现的时间越晚,颗粒流最终堆积面积中细颗粒组最大,粗颗粒组最小。(2)当滑槽底部反作用力位置取2/3静止堆积体长度时,计算所得碎屑流最大冲击作用高度与模拟试验结果相接近,力学模型计算的冲击作用高度在0.017~0.138 m。在实际工程中,可按研究相似比对此范围进行加强抗冲击防护。(3)由于侧板的切向力和“颗粒分选效应”,大颗粒会主要冲击挡板的中上部,小颗粒主要冲击挡板的下部,并受偏转角影响集中在一侧,因此工程设计可根据实际情况避免在沟道偏转方向的反向建设工程。研究结果可为高位滑坡碎屑流灾害的治理防护提供参考。

涪江源区韩家沟泥石流防治工程改进前后危险性分析

为了降低涪江源区左岸韩家沟泥石流的危害,文章采用遥感解译、野外调查、FLO-2D数值模拟等手段,查清了韩家沟泥石流特征及其防治现状,认为现有防治工程不能满足防灾需求,并据此提出改进的防治工程,对不同降雨频率下防治工程改进前后的泥石流危险性进行了研究,并分析改进防治工程的有效性。结果表明:韩家沟位于“8·8”九寨沟地震扰动区,震后泥石流物源丰富,导致每逢强降雨时泥石流频发。在10年一遇降雨频率下,丰河村及平松路均处于低危险区,现有防治工程可有效防治泥石流灾害;在50年一遇降雨频率下,丰河村处于泥石流高危险区,泥石流冲出排导槽,冲毁平松路,现有防治工程不能满足要求。采用多级拦挡坝、排导槽截弯取直等改进的防治工程后,可有效预防泥石流对沟口下方承灾体的损害,泥石流堆积方量减少50.2%,堆积面积减少86%,高危险区均位于排导槽内,治理效果显著。

新疆阜康抽水蓄能电站库区泥石流危险性评价与防治措施

根据新疆阜康抽蓄库区泥石流形成条件及发育特征,通过现场调查、遥感解译、现场试验等方法确定了影响较大的4条沟谷泥石流静力、动力特征值,选取泥石流多因子综合模型评价了泥石流的危险性,并从两方面分析了泥石流对工程安全的影响,提出了“稳坡、拦挡、停淤”的综合防治体系。结果表明:西岔沟泥石流危险度最大,值为0.43,属于中度危险;库区泥石流沟的影响主要表现为淤泥作用和冲击作用;“稳、拦、停”的立体综合防治体系具有良好的防治效果,值得推广采用。

四川龙门山强震区特大泥石流综合防控技术体系研究

强震区泥石流表现出群沟暴发、范围广、持续时间长、规模大、危害重、防治难等特点,文章以强震区数十条典型特大泥石流沟为研究对象,采用野外调查、分析统计、试验验证及示范工程应用等方法,开展了典型泥石流沟特点及其防治工程效果研究,构建了强震区特大泥石流综合防控技术体系,形成了强震区特大泥石流勘查设计技术和防控关键技术体系。勘查设计体系在现有勘查技术基础上提出震裂物源识别新技术、堵塞系数分项取值新思路等;根据泥石流沟谷形态将强震区泥石流分为窄陡型和宽缓型;防控关键技术体系针对不同沟谷形态的泥石流分别进行综合防控关键技术探讨实践,统筹考虑了窄陡型和宽缓型泥石流沟上游、中游、下游沟谷特征。组合多种综合防控措施,建立了“起动控源→过程控量→末端控灾”逐级控制的强震区特大泥石流综合防控体系。结果可为强震区泥石流综合防控提供技术支撑,也可为非震区泥石流综合防控提供参考。

基于多特征提取的合成射流涡流控制机理研究

在横流的底部施加倾斜角为60?的合成射流,并采用大涡模拟(LES)对其周期性涡运动过程进行了数值模拟,研究不同激励参数条件下合成射流与横流相互作用涡环结构的产生机理及演变规律。该文首先利用第三代涡识别方法(Liutex矢量法)对流场中涡环的演变过程进行了运动跟踪,并且定量统计合成射流在不同驱动频率(S_(t)=0.25,0.5,0.75,1)和驱动振幅(A_(0)=1,1.5,2,2.5)下涡旋结构的旋转强度和涡核尺度。此外,采用本征正交分解法(proper orthogonal decomposition,POD)方法和动态模态分解(dynamic mode decomposition,DMD)对合成射流特定频率(S_(t)=0.25)及振幅(A_(0)=2.5)下流场速度场进行模态分解,提取影响流场的主特征模态。结果表明:振幅对旋转强度和涡核尺寸大小有正贡献,而频率对旋转强度和涡核尺寸大小有负贡献;合成射流在横流中的涡运动机理可以概括为,在低频低振幅条件下有利于顺时针涡结构的产生,而在高频高振幅条件下有利于逆时针涡结构的产生;基于各阶POD模态的空间结构及频谱特征等特性,流场主特征结构为脱落涡,脱落频率与射流驱动频率一致(S_(t)=0.25)。初级顺时针涡旋结构为涡流控制的主导结构,而每阶模态均为多频耦合;通过DMD对流场信息进行时空解耦,得到了剪切诱导、涡合并等动力特征。多种特征提取方法的结合更有助于合成射流涡流控制机理的深入研究。

基于复杂网络的火后泥石流成灾机理的建模方法

为更加全面地对火后泥石流致灾因素进行定性分析,达到灾害防控目的,基于复杂网络理论,通过梳理既有的致灾机理研究,萃取了包含致灾因素和过程事件在内的39个节点,建立了火后泥石流触发网络。随后,基于有向网络的结构特点拓展了综合度的概念,并通过综合出(入)度、中介中心性、连边脆弱度3项复杂网络拓扑特征提出了节点风险扩散度指标(NRD)用于评估网络中的关键节点。最后,以3种攻击方式针对PDFTN,对比该网络的连通度变化,以验证NRD识别结果的有效性。结果表明:NRD能够有效识别出有向网络中的关键节点,其中NRD识别出的火后泥石流关键致灾因素为地表径流,该结果与现有研究结论一致。因此,致灾因素对火后泥石流灾害结果的影响可以通过本文提出的NRD指标进行有效表征,从而为火后泥石流灾害防控提供辅助决策依据。

混合流动控制对风机叶片气动特性的影响

针对风力机叶片失速会降低风力机输出功率的问题,文章首先基于Fluent软件建立了NREL Phase Ⅵ风力机气动特性分析模型,计算风速为13 m/s时风力机叶片截面压力系数及功率特性,并与风洞实验数据进行对比,验证风力机气动特性分析模型的准确性;然后,将主动射流和涡流发生器(VGs)耦合到风力机叶片上,发现随射流孔宽度和涡流发生器高度的增加,风力机功率均呈先增后减趋势;最后,建立混合流动控制的风力机气动分析模型,研究射流与VGs弦向间距及后缘VGs高度对风力机气动特性的影响。研究表明:当间距为0.3C(C为翼型弦长)时,风力机输出功率达到最高,相比于射流单一控制,增幅为6.61%;当后缘VGs高度为15 mm时,混合式流动控制的效果最佳,风机功率最高。

川西北某泥石流沟发育特征及易发性评价

川西北某泥石流沟位于汶川“5.12”8级地震中心影响区域岷江河谷,该区域地质构造复杂,新构造运动强烈,强震频发,加之受岷江河谷深切,地形陡峻,出露地层以软质岩为主,沟道及两侧物源十分丰富,强降雨条件下易引发泥石流灾害。通过收集区域地质资料、遥感解译、现场地质勘察和力学计算等方法相结合,从地形、物源和水动力条件等方面,研究了该区域某泥石流沟的发育特征并开展易发性评价,提出了相应的工程防治对策。研究结果表明:(1)川西北某泥石流沟为暴雨崩滑沟谷型泥石流,泥石流沟流域面积20.8 km^(2),固体物质总储量约258.9×10^(4) m^(3),可能的动储量约64.5×10^(4) m^(3);(2)100年一遇的泥石流重度为1.74 t/m^(3),平均流速为5.12 m/s,最大峰值流量为535.4 m^(3)/s,泥石流最大冲起高度为1.34 m,预测100年一遇的泥石流淤积厚度为4.8 m,具有中度易发性风险;(3)针对工程区的泥石流发育特征及易发性程度,建议以桥梁工程形式并留足净空通过泥石流沟,提出了泥石流防治对策与建议。研究成果对川西北山区铁路勘察设计和施工建设具有一定借鉴价值。

北天山干线泥石流发育特征与防治措施研究

北天山干线穿越多种地貌类型、地质构造复杂、灾害种类及数量均偏多,制约着新疆地区公路、铁路等基础建设的发展。以北天山G577线精河至伊宁县公路沿线泥石流为研究对象,对泥石流的发育特征、防治措施、选线及通过形式进行系统研究,提出北天山干线泥石流避让方式及防治措施。

山西省文水县地质灾害风险评价及风险管控研究:以区域泥石流、崩塌和滑坡为例

地质灾害易发性评价是风险性评价的基础,以往的区域地质灾害易发性评价常采用同一种单元划分方法,而不同灾种受不同因素的影响,需采用不同的评价指标建立模型。本文以文水县地质灾害发育特征分析为基础,考虑泥石流发育诱发因素的特殊性,采用流域评价单元对泥石流灾害进行易发性评价,采用栅格评价单元对崩塌、滑坡灾害进行易发性评价,在两者加权叠加的基础上开展区域风险评价,并提出风险管控建议。

泥石流灾害及工程防治对策研究

泥石流作为一种地质灾害现象,在全球山区范围内广泛发生。当前,泥石流灾害在强降雨及气候的影响下,形成机制愈加复杂,预警及防治工作十分困难,是人民的生命和财产安全的潜在风险,严重制约了国家重大基础设施的建设和后期的安全运行,也极大地影响了社会的可持续发展,是现阶段亟待突破的科学难题。因此,对泥石流灾害防治工作的研究显得尤为重要。本文通过分析泥石流灾害及工程防治技术上的进展,探讨未来研究要关注的问题。

森林火灾对泥石流孕灾环境及成灾机制的影响分析

火后泥石流是最危险的森林火灾次生灾害之一,为了探讨森林火灾对泥石流孕灾环境及成灾机制的影响,本文以湖南新田县过火区域为研究对象,利用遥感解译、野外实地调查、室内实验等方法,开展火后泥石流孕灾因子及成灾机制研究。研究结果表明,森林火灾对岩土体、植被和物源产生重要影响,因岩土体性质和植被烧毁的影响,提高了坡面地表径流和坡面侵蚀,降低了泥石流启动降雨阈值,形成初次以灰烬层为主的泥石流。这与常规泥石流的特点和成灾机制有所不同,可为火后泥石流灾害防治与风险评价提供重要参考和技术支撑。

丰沙铁路山区段坡面型泥石流特征分析及防治建议

既有山区铁路泥石流灾害时有发生,随着极端气候变化灾害愈发严重,极大危及铁路行车安全,尤其以坡面型泥石流的高速度、大冲击力、突发性、短暂性等特征对铁路的影响较大,严重威胁行车安全。针对山区铁路发生坡面型泥石流的水害处所,通过现场踏勘并采用遥感影像及无人机倾斜摄影技术,对水害点展开调查研究,分析坡面型泥石流特征及发生机理,并提出针对性防治措施。研究结果可为类似水害治理提供参考。