共查询到20条相似文献，搜索用时 31 毫秒
1.
Alaa M. Al-Abadi 《Arabian Journal of Geosciences》2018,11(9):218
This study examined the efficacy of three machine ensemble classifiers, namely, random forest, rotation forest and AdaBoost, in assessing flood susceptibility in an arid region of southern Iraq. A dataset was created from flooded and non-flooded areas to train and validate the ensemble classifiers using a binary classification scheme (1—flood, 0—non-flood). The prepared dataset was then partitioned into two sets with a 70/30 ratio: 70% (2478 pixels) for training and 30% (1062 pixels) for testing. A total of 10 influential flood factors were selected and prepared based on data availability and a literature review. The selected factors were surface elevation, slope, plain curvature, topographic wetness index, stream power index, distance to rivers, drainage density, lithology, soil and land use/land cover. The information gain ratio was first utilised to explore the predictive abilities of the factors. The predictive performances of the three ensemble models were compared using six statistical measures: sensitivity, specificity, accuracy, kappa, root mean square error and area under the operating characteristics curve. The results revealed that the AdaBoost classifier was the best in terms of the statistical measures, followed by the random forest and rotation forest models. A flood susceptibility map was prepared based on the result of each classifier and classified into five zones: very low, low, moderate, high and very high. For the model with the best performance, i.e., the AdaBoost model, these zones were distributed over an area of 6002 km2 (44%) for the very low–low zone, 2477 km2 (18%) for the moderate zone and 5048 km2 (40%) for the high–very high zones. This study proved the high capabilities of ensemble machine learning classifiers to decipher flood susceptibility zones in an arid region. 相似文献
2.
Using statistical and artificial neural network models to forecast potentiometric levels at a deep well in South Texas 总被引：2，自引：0，他引：2
V. Uddameri 《Environmental Geology》2007,51(6):885-895
Reliable forecasts of monthly and quarterly fluctuations in groundwater levels are necessary for short- and medium-term planning
and management of aquifers to ensure proper service of seasonal demands within a region. Development of physically based transient
mathematical models at this time scale poses considerable challenges due to lack of suitable data and other uncertainties.
Artificial neural networks (ANN) possess flexible mathematical structures and are capable of mapping highly nonlinear relationships.
Feed-forward neural network models were constructed and trained using the back-percolation algorithm to forecast monthly and
quarterly time-series water levels at a well that taps into the deeper Evangeline formation of the Gulf Coast aquifer in Victoria,
TX. Unlike unconfined formations, no causal relationships exist between water levels and hydro-meteorological variables measured
near the vicinity of the well. As such, an endogenous forecasting model using dummy variables to capture short-term seasonal
fluctuations and longer-term (decadal) trends was constructed. The root mean square error, mean absolute deviation and correlation
coefficient (R) were noted to be 1.40, 0.33 and 0.77 m, respectively, for an evaluation dataset of quarterly measurements and 1.17, 0.46,
and 0.88 m for an evaluative monthly dataset not used to train or test the model. These statistics were better for the ANN
model than those developed using statistical regression techniques. 相似文献
3.
为了提高机器学习对深基坑地面沉降的预测能力,本文提出了一种基于Stacking集成学习方式的多模型融合的地面沉降预测方法,并以深圳某深基坑为例,采用斯皮尔曼相关性系数对基坑地面沉降的影响因子进行筛选;运用筛选后的8个影响因子建立Stacking深基坑地面沉降预测模型,以验证该方法的适用性。结果表明：Stacking预测模型的平均绝对误差为0.34、平均绝对误差百分比为2.22%,均方根误差为0.13,相较于传统基模型（随机森林、支持向量机和人工神经网络）,Stacking预测模型的平均绝对误差、平均绝对误差百分比和均方根误差值皆为最小。 相似文献
4.
Development of a model for analysis of slope stability for circular mode failure using genetic algorithm 总被引：3，自引：1，他引：2
Amin Manouchehrian Javad Gholamnejad Mostafa Sharifzadeh 《Environmental Earth Sciences》2014,71(3):1267-1277
Slope stability estimation is an engineering problem that involves several parameters. The interactions between factors that affect slope instability are complex and multi-factorial, so often it is difficult to describe the slope stability mathematically. This paper, proposes the use of a genetic algorithm (GA) as a heuristic search method to find a regression model for analyzing the slope stability. For this purpose, an evolutionary algorithm based on GA was used to develop a regression model for prediction of factor of safety (FS) for circular mode failure. The proposed GA uses the root mean squared error as the fitness function and searches among a large number of possible regression models to choose the best for estimation of FS from six geotechnical and geometrical parameters. For validation of the model and checking its efficiency, a validation dataset was used to evaluate FS using the proposed model and a previously developed mathematical GA based model in the literature. Results have shown that the presented model in this study was capable of evaluating FS at a higher level of confidence regarding the other model (R = 0.89 for presented model in this study comparing R = 0.78 for the other model) and can be efficient enough to be used as a simple mathematical tool for evaluation of factor of safety for circular mode failure especially in preliminary stages of the designing phase. 相似文献
5.
为利用水文现象相似性和极限学习机(ELM)集成学习提高洪水预报精度,提出了一种基于相似度匹配的集成ELM洪水预报方法(SM-ELM)。方法首先从多个ELM模型中,为每一个训练样本找到最优的ELM模型,然后从训练集中,为测试样本匹配出最相似的前k个训练样本,最后利用这k个训练样本分别对应的最优ELM模型,对测试样本采用加权平均法进行集成预报。为证明提出方法的可行性和有效性,以昌化流域的历史洪水为例进行了验证。结果表明,相对于单个ELM,集成ELM模型能有效地提高预测精度。从均方根误差上看,集成ELM模型性能比单个ELM模型提升了10%~15%。在三种集成方法中,SM-ELM能够以较少的模型数量获得较高且稳定的预报精度。 相似文献
6.
Yudhvir Singh Rajesh R. Nair Harmandeep Singh Prattya Datta Priyank Jaiswal Pawan Dewangan T. Ramaprasad 《Arabian Journal of Geosciences》2016,9(5):415
Stepwise linear regression, multi-layer feed forward neural (MLFN) network method was used to predict the 2D distribution of P-wave velocity, resistivity, porosity, and gas hydrate saturation throughout seismic section NGHP-01 in the Krishna-Godavari basin. Log prediction process, with uncertainties based on root mean square error properties, was implemented by way of a multi-layer feed forward neural network. The log properties were merged with seismic data by applying a non-linear transform to the seismic attributes. Gas hydrate saturation estimates show an average saturation of 41 % between common depth point (CDP) 600 and 700 and an average saturation of 35 % for CDP 300–400 and 700–800, respectively. High gas hydrate saturation corresponds to high P-wave velocity and high resistivity except in a few spots, which could be due to local variation of permeability, temperature, fractures, etc. 相似文献
7.
寻找离子吸附型稀土矿床对保障我国关键矿产资源具有重要作用。综合利用广西崇左六汤矿区的基础地质、地球化学勘探、高分辨率遥感影像等多源地学数据,以已知矿床分布特征为约束,基于多项式回归及BP神经网络对该区进行建模,以决定系数R2及均方根误差（RMSE）为模型评价指标,对研究区离子吸附型稀土矿含量进行预测。研究结果表明,多项式回归模型检验R2=0.54,BP神经网络模型检验R2=0.64,剔除数据中高离群值后模型精度显著上升,多项式回归模型精度较好,但预测效果图与实测效果图差异较大。综上,数据中离群值的存在对模型的影响较大,模型拟合的好坏并非判断模型好坏的唯一标准,BP神经网络模型能较好预测研究区离子吸附型稀土矿含量。 相似文献
8.
边坡位移是滑坡演化的宏观体现,分析并预测滑坡位移发展态势对于防灾减灾具有重要意义。由于滑坡位移曲线具有明显的非线性特征,单一模型往往难以刻画其非线性与复杂性。为发展一种普遍适用于滑坡位移的预测方法,提出了一种联合多种数据驱动模型的新方法。该方法根据时间序列分析理论,将滑坡位移序列分解为趋势项和周期项,趋势项采用并联型灰色神经网络处理,周期项则采用人工蜂群算法（ABC）优化后的极限学习机模型（ELM）处理,从而充分应用各种模型的优点。以三峡库区白水河和八字门滑坡为例,对位移数据进行分析处理后,灰色神经网络模型预测其趋势性位移,改进后的极限学习机模型对周期性位移进行训练及预测。结果表明:在预测精度上,优化后的极限学习机模型准确度高于极限学习机模型及小波神经网络等方法,提出的灰色神经网络与ABC-ELM的组合模型可作为实际工程的一个参考。 相似文献
9.
10.
《地学前缘(英文版)》2022,13(5):101425
Multi-hazard susceptibility prediction is an important component of disasters risk management plan. An effective multi-hazard risk mitigation strategy includes assessing individual hazards as well as their interactions. However, with the rapid development of artificial intelligence technology, multi-hazard susceptibility prediction techniques based on machine learning has encountered a huge bottleneck. In order to effectively solve this problem, this study proposes a multi-hazard susceptibility mapping framework using the classical deep learning algorithm of Convolutional Neural Networks (CNN). First, we use historical flash flood, debris flow and landslide locations based on Google Earth images, extensive field surveys, topography, hydrology, and environmental data sets to train and validate the proposed CNN method. Next, the proposed CNN method is assessed in comparison to conventional logistic regression and k-nearest neighbor methods using several objective criteria, i.e., coefficient of determination, overall accuracy, mean absolute error and the root mean square error. Experimental results show that the CNN method outperforms the conventional machine learning algorithms in predicting probability of flash floods, debris flows and landslides. Finally, the susceptibility maps of the three hazards based on CNN are combined to create a multi-hazard susceptibility map. It can be observed from the map that 62.43% of the study area are prone to hazards, while 37.57% of the study area are harmless. In hazard-prone areas, 16.14%, 4.94% and 30.66% of the study area are susceptible to flash floods, debris flows and landslides, respectively. In terms of concurrent hazards, 0.28%, 7.11% and 3.13% of the study area are susceptible to the joint occurrence of flash floods and debris flow, debris flow and landslides, and flash floods and landslides, respectively, whereas, 0.18% of the study area is subject to all the three hazards. The results of this study can benefit engineers, disaster managers and local government officials involved in sustainable land management and disaster risk mitigation. 相似文献
11.
This paper evaluates the potential of two machine learning approaches i.e. Support vector machine (SVR) and Gaussian processes (GP) regression to model the oblique load capacity of batter pile groups. Linear regression was used to compare the performance of both SVR and GP based regression approaches to model the oblique load. Data set used consists of 147 samples obtained from the laboratory experiments. Out of the total sample size, 105 randomly selected samples were used for training whereas remaining 42 were used for testing the models. Input data set consist of angle of oblique load, pile length, sand relative density, number of vertical piles, number of batter piles where as oblique load was considered as output. Two kernel functions i.e. Polynomial and radial based kernel function were used with both SVR and GP regression. A comparison of results suggest that radial basis function based SVR approach works well in comparison to GP and linear regression based approaches and it could successfully be employed in modelling the oblique load capacity of batter pile groups. Parametric analysis and sensitivity analysis suggest that loading angle, pile length and number of batter pile were important in prediction of oblique load. 相似文献
12.
This paper presents the results and analysis of Repeated Load Triaxial Testing (RLTT) conducted on three basecourse products; two crushed concrete, or Recycled Concrete Aggregate (RCA) materials, and a local Virgin Aggregate (VA). The objective of this testing program was to study the impact of applied stress states on resilient modulus and permanent deformation of the materials using the AUSTROADS RLTT approach (Vuong and Brimble 2000). A series of RLTT was performed under drained conditions on cylindrical specimens statically compacted at different levels of initial moisture content. The RLTT specimens were tested at 60, 80 and 90 % of Optimum Moisture Content (OMC) and to a single target dry density ratio of 98 % of Maximum Dry Density from Modified Proctor compaction testing. Duplicate specimens were tested for each moisture level. On sample measurements were made of sample deformation. It was found that the resilient moduli of the two RCA products ranged between 340 and 715 MPa, while corresponding moduli from tests on VA varied from 270 to 450 MPa. Resilient modulus was found to be dependent on both moisture content and applied stress. The two specimens of VA prepared at 90 % OMC failed during the permanent strain testing stages of the AUSTROADS test protocol. Moreover the recycled materials could be used as basecourses according to interpretation of the AUSTROADS RLTT data by Vuong and Arnold (2006). 相似文献
13.
Dieu Tien Bui Tran Anh Tuan Harald Klempe Biswajeet Pradhan Inge Revhaug 《Landslides》2016,13(2):361-378
Preparation of landslide susceptibility maps is considered as the first important step in landslide risk assessments, but these maps are accepted as an end product that can be used for land use planning. The main objective of this study is to explore some new state-of-the-art sophisticated machine learning techniques and introduce a framework for training and validation of shallow landslide susceptibility models by using the latest statistical methods. The Son La hydropower basin (Vietnam) was selected as a case study. First, a landslide inventory map was constructed using the historical landslide locations from two national projects in Vietnam. A total of 12 landslide conditioning factors were then constructed from various data sources. Landslide locations were randomly split into a ratio of 70:30 for training and validating the models. To choose the best subset of conditioning factors, predictive ability of the factors were assessed using the Information Gain Ratio with 10-fold cross-validation technique. Factors with null predictive ability were removed to optimize the models. Subsequently, five landslide models were built using support vector machines (SVM), multi-layer perceptron neural networks (MLP Neural Nets), radial basis function neural networks (RBF Neural Nets), kernel logistic regression (KLR), and logistic model trees (LMT). The resulting models were validated and compared using the receive operating characteristic (ROC), Kappa index, and several statistical evaluation measures. Additionally, Friedman and Wilcoxon signed-rank tests were applied to confirm significant statistical differences among the five machine learning models employed in this study. Overall, the MLP Neural Nets model has the highest prediction capability (90.2 %), followed by the SVM model (88.7 %) and the KLR model (87.9 %), the RBF Neural Nets model (87.1 %), and the LMT model (86.1 %). Results revealed that both the KLR and the LMT models showed promising methods for shallow landslide susceptibility mapping. The result from this study demonstrates the benefit of selecting the optimal machine learning techniques with proper conditioning selection method in shallow landslide susceptibility mapping. 相似文献
14.
《地学前缘(英文版)》2020,11(6):2207-2219
This investigation assessed the efficacy of 10 widely used machine learning algorithms (MLA) comprising the least absolute shrinkage and selection operator (LASSO), generalized linear model (GLM), stepwise generalized linear model (SGLM), elastic net (ENET), partial least square (PLS), ridge regression, support vector machine (SVM), classification and regression trees (CART), bagged CART, and random forest (RF) for gully erosion susceptibility mapping (GESM) in Iran. The location of 462 previously existing gully erosion sites were mapped through widespread field investigations, of which 70% (323) and 30% (139) of observations were arbitrarily divided for algorithm calibration and validation. Twelve controlling factors for gully erosion, namely, soil texture, annual mean rainfall, digital elevation model (DEM), drainage density, slope, lithology, topographic wetness index (TWI), distance from rivers, aspect, distance from roads, plan curvature, and profile curvature were ranked in terms of their importance using each MLA. The MLA were compared using a training dataset for gully erosion and statistical measures such as RMSE (root mean square error), MAE (mean absolute error), and R-squared. Based on the comparisons among MLA, the RF algorithm exhibited the minimum RMSE and MAE and the maximum value of R-squared, and was therefore selected as the best model. The variable importance evaluation using the RF model revealed that distance from rivers had the highest significance in influencing the occurrence of gully erosion whereas plan curvature had the least importance. According to the GESM generated using RF, most of the study area is predicted to have a low (53.72%) or moderate (29.65%) susceptibility to gully erosion, whereas only a small area is identified to have a high (12.56%) or very high (4.07%) susceptibility. The outcome generated by RF model is validated using the ROC (Receiver Operating Characteristics) curve approach, which returned an area under the curve (AUC) of 0.985, proving the excellent forecasting ability of the model. The GESM prepared using the RF algorithm can aid decision-makers in targeting remedial actions for minimizing the damage caused by gully erosion. 相似文献
15.
Modeling of a permeate flux of cross-flow membrane filtration of colloidal suspensions: A wavelet network approach 总被引：1，自引：1，他引：0
A. L. Wei G. M. Zeng Ph.D. G. H. Huang Ph.D. J. Liang X. D. Li Ph.D. 《International Journal of Environmental Science and Technology》2009,6(3):395-406
Although traditional artificial neural networks have been an attractive topic in modeling membrane filtration, lower efficiency by trial-and-error constructing and random initializing methods often accompanies neural networks. To improve traditional neural networks, the present research used the wavelet network, a special feedforward neural network with a single hidden layer supported by the wavelet theory. Prediction performance and efficiency of the proposed network were examined with a published experimental dataset of cross-flow membrane filtration. The dataset was divided into two parts: 62 samples for training data and 329 samples for testing data. Various combinations of transmembrane pressure, filtration time, ionic strength and zeta potential were used as inputs of the wavelet network so as to predict the permeate flux. Through the orthogonal least square alogorithm, an initial network with 12 hidden neurons was obtained which offered a normalized square root of mean square of 0.103 for the training data. The initial network led to a wavelet network model after training procedures with fast convergence within 30 epochs. Futher the wavelet network model accurately depicted the positive effects of either transmembrane pressure or zeta potential on permeate flux. The wavelet network also offered accurate predictions for the testing data, 96.4 % of which deviated the measured data within the ± 10 % relative error range. Moreover, comparisons indicated the wavelet network model produced better predictability than the back-forward backpropagation neural network and the multiple regression models. Thus the wavelet network approach could be employed successfully in modeling dynamic permeate flux in cross-flow membrane filtration. 相似文献
16.
Frequent fires can affect ecosystems and public safety. The occurrence of fires has varied with hot and cold months in China. To analyze how temperature influences fire frequency, a fire dataset including 20,622 fires and a historical weather dataset for Changsha in China were gathered and processed. Through data mining, it was found that the mean daily fire frequency tended to be the lowest in the temperature range of (20 °C, 25 °C] and should be related to the low utilization rate of electricity. Through polynomial fitting, it was found that the prediction performance using the daily minimum temperature was generally better than that using the daily maximum temperature, and a quadruplicate polynomial model based on the mean daily minimum temperature of 3 days (the day and the prior 2 days) had the best performance. Then, a temperature-based fire frequency prediction model was established using quadruplicate polynomial regression. Moreover, the results are contrary to the content stipulated in China’s national standard of urban fire-danger weather ratings GB/T 20487-2006. The findings of this study can be applied as technical guidance for fire risk prediction and the revision of GB/T 20487-2006.
相似文献17.
Estimating leaf chlorophyll contents through leaf reflectance spectra is efficient and nondestructive, but the actual dataset always based on a single or a few kinds of specific species, has a limitation and instability for a common use. To address this problem, a combination of multiple spectral indices and a model simulated dataset are proposed in this paper. Six spectral indices are selected, including Blue Green Index (BGI), Photochemical Reflectance Index (PRI_5), Triangle Vegetation Index (TVI), Chlorophyll Absorption Ratio Index (CARI), Carotenoid Reflectance Index (CRI) and the green peak reflectance (R525). Both stepwise linear regression (SLR) and back-propagation artificial neural network (ANN) are used to combine the six spectral indices for the estimation of chlorophyll content (Cab). In addition, to overcome the limitation of actual dataset, a “big data” is applied by a within-leaf radiation transfer model (PROSPECT) to generate a large number of simulated samples with varying biochemical and biophysical parameters. 30% of the simulated dataset (SIM30) and an experimental dataset are used for validation. Compared with linear regression method, NN yields better result with R2 = 0.96 and RMSE = 5.80ug.cm?2 for Cab if validated by SIM30, while R2 = 0.95 and RMSE = 6.39ug.cm?2 for SLR. NN also gives satisfactory result with R2 = 0.80 and RMSE = 5.93ug.cm?2 for Cab if validated by LOPEX dataset, however, the SLR only gets 0.72 of R2 and 12.20ug.cm?2 of RMSE. The results indicate that integrating multiple spectral indices can improve the Cab estimating accuracy with a better stability in different kind of species and the model simulated dataset can make up the shortfall of actual measured dataset. 相似文献
18.
基于KNN机器学习方法对青藏高原唐古拉地区表层土壤水热状况的模拟 总被引：1，自引：1，他引：0
利用唐古拉站2004—2012年气象观测资料,基于KNN算法,结合机器学习思想,建立了一个气象回归模型,模拟了2005年唐古拉地区表层土壤水热变化趋势,结合实测数据,将模拟值与观测值进行对比,并对模型模拟效果进行了评估。结果表明：KNN模型能够较好地模拟活动层表层土壤水热状况,各层土壤温度的模拟值与观测值的相关系数均在0.99以上,均方根误差在1.25 ℃以内;不同深度土壤水分的模拟值与观测值的相关系数均在0.95以上,均方根误差在0.02 m3?m-3以内。总体上,KNN模型能够对青藏高原多年冻土区唐古拉地区表层土壤水热状况进行较为精确地模拟,该模型对于青藏高原其他地区的适用性有待进一步研究验证。 相似文献
19.
Binh Thai Pham Dieu Tien Bui M. B. Dholakia Indra Prakash Ha Viet Pham 《Geotechnical and Geological Engineering》2016,34(6):1807-1824
The objective of this study is to explore and compare the least square support vector machine (LSSVM) and multiclass alternating decision tree (MADT) techniques for the spatial prediction of landslides. The Luc Yen district in Yen Bai province (Vietnam) has been selected as a case study. LSSVM and MADT are effective machine learning techniques of classification applied in other fields but not in the field of landslide hazard assessment. For this, Landslide inventory map was first constructed with 95 landslide locations identified from aerial photos and verified from field investigations. These landslide locations were then divided randomly into two parts for training (70 % locations) and validation (30 % locations) processes. Secondly, landslide affecting factors such as slope, aspect, elevation, curvature, lithology, land use, distance to roads, distance to faults, distance to rivers, and rainfall were selected and applied for landslide susceptibility assessment. Subsequently, the LSSVM and MADT models were built to assess the landslide susceptibility in the study area using training dataset. Finally, receiver operating characteristic curve and statistical index-based evaluations techniques were employed to validate the predictive capability of these models. As a result, both the LSSVM and MADT models have high performance for spatial prediction of landslides in the study area. Out of these, the MADT model (AUC = 0.853) outperforms the LSSVM model (AUC = 0.803). From the landslide study of Luc Yen district in Yen Bai province (Vietnam), it can be conclude that the LSSVM and MADT models can be applied in other areas of world also for and spatial prediction. Landslide susceptibility maps obtained from this study may be helpful in planning, decision making for natural hazard management of the areas susceptible to landslide hazards. 相似文献
20.
Pijush Samui Tim Lansivaara Madhav R. Bhatt 《Geotechnical and Geological Engineering》2013,31(4):1329-1334
This paper investigates the feasibility of Least square support vector machine (LSSVM) model to cope the problem of implicit performance function during first order second moment (FOSM) method based slope reliability analysis. LSSVM is firmly based on the theory of statistical learning. In LSSVM, Vapnik’s ε -insensitive loss function has been replaced by a cost function which corresponds to a form of ridge regression. Here, LSSVM has been used as a regression technique to approximate implicit performance functions. A slope example has been presented for illustrating the applicability of LSSVM based FOSM method. The developed LSSVM based FOSM has been compared with the artificial neural network (ANN) and least square method. The result shows that the approximation of LSSVM can be used in the FOSM method for slope reliability analysis. 相似文献