A Comparative Study of Landslide Susceptibility Mapping Using SVM and PSO-SVM Models Based on Grid and Slope Units

Zhao, Shuai; Zhao, Zhou

doi:10.1155/2021/8854606

Cited by 38 publications

(19 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the strong correlation between the precipitation and elevation conditioning factors, we proposed several improvement measures. The four commonly used models achieved excellent susceptibility classification results, however the improved synthesis algorithms exhibited a better performance (Saha et al 2020;Zhao and Zhao 2021). This study improved the optimal algorithm of the four models through two key steps: (1) the high correlation between precipitation and elevation allowed precipitation to be ignored in the factor refinement classification.…”

Section: Discussionmentioning

confidence: 97%

A comparative evaluation of machine learning algorithms and an improved optimal model for landslide susceptibility: a case study

Liu

Cao

et al. 2021

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

In this study, four representative machine learning methods (support vector machine (SVM), maximum entropy (MaxEnt), random forest (RF), and artificial neural network (ANN)) were employed to construct a landslide susceptibility map (LSM) in Xulong Gully (XLG), southwest China. The models were subsequently compared in order to select the best-performing model. This model was further improved to optimize the machine learning method. A total of 16 layers were extracted from the collected data and employed as conditional factors for the correlation analysis and subsequent modelling. The LSMs were then divided into four levels (very high susceptibility (VH), high susceptibility (H), moderate susceptibility (M) and low susceptibility (L)). The results were verified by receiver operating characteristic (ROC) curves, Root Mean Squared Error (RMSE) and Frequency Ratio (FR). The higher of the area under ROC curve (AUC) and the lower the RMSE, the more accurate and stable the performance. Following the factor performance analysis, the optimal SVM model was linearity improved to the Trace Ratio Criterion (TRC)-SVM, with a better performance and the ability to overcome the factor defect. The comprehensive comparisons and proposed LSM can support future research, as well as local authorities in the development of landslide remission strategies.

show abstract

Section: Discussionmentioning

confidence: 97%

A comparative evaluation of machine learning algorithms and an improved optimal model for landslide susceptibility: a case study

Liu

Cao

et al. 2021

Geomatics, Natural Hazards and Risk

View full text Add to dashboard Cite

show abstract

“…According to the reviewed literature [ 47 , 54 ], first, we graded the input variables (15 evaluation factors) and calculated the frequency ratios for each factor after grading. The results of the grading factors and frequency ratio calculation are shown in Table 8 .…”

Section: Discussionmentioning

confidence: 99%

“…Ludian county is situated in an active fault zone with frequent earthquakes, making it extremely vulnerable to landslide devastations. Based on previous research, 12 influencing factors, including geological factors, topographic factors, environmental factors, and human engineering activities, were selected [ 47 , 48 , 49 ]. As evaluation factors, four influencing factors were considered: landslide time series deformation of ascending and descending orbit, seismic intensity released by the Ludian earthquake on 3 August 2014, and epicentral distance with a 2 km radius.…”

Section: Methodsmentioning

confidence: 99%

Combined SBAS-InSAR and PSO-RF Algorithm for Evaluating the Susceptibility Prediction of Landslide in Complex Mountainous Area: A Case Study of Ludian County, China

Xiao

Zhao

et al. 2022

Sensors

View full text Add to dashboard Cite

In complex mountainous areas where earthquakes are frequent, landslide hazards pose a significant threat to human life and property due to their high degree of concealment, complex development mechanism, and abrupt nature. In view of the problems of the existing landslide hazard susceptibility evaluation model, such as poor effectiveness and inaccuracy of landslide hazard data and the need for experts to participate in the calculation of a large number of evaluation factor weight classification statistics. In this paper, a combined SBAS-InSAR (Small Baseline Subsets-Interferometric Synthetic Aperture Radar) and PSO-RF (Particle Swarm Optimization-Random Forest) algorithm was proposed to evaluate the susceptibility of landslide hazards in complex mountainous regions characterized by frequent earthquakes, deep river valleys, and large terrain height differences. First, the SBAS-InSAR technique was used to invert the surface deformation rates of the study area and identified potential landslide hazards. Second, the study area was divided into 412,585 grid cells, and the 16 selected environmental factors were analyzed comprehensively to identify the most effective evaluation factors. Last, 2722 landslide (1361 grid cells) and non-landslide (1361 grid cells) grid cells in the study area were randomly divided into a training dataset (70%) and a test dataset (30%). By analyzing real landslide and non-landslide data, the performances of the PSO-RF algorithm and three other machine learning algorithms, BP (back propagation), SVM (support vector machines), and RF (random forest) algorithms were compared. The results showed that 329 potential landslide hazards were updated using the surface deformation rates and existing landslide cataloguing data. Furthermore, the area under the curve (AUC) value and the accuracy (ACC) of the PSO-RF algorithm were 0.9567 and 0.8874, which were higher than those of the BP (0.8823 and 0.8274), SVM (0.8910 and 0.8311), and RF (0.9293 and 0.8531), respectively. In conclusion, the method put forth in this paper can be effectively updated landslide data sources and implemented a susceptibility prediction assessment of landslide disasters in intricate mountainous areas. The findings can serve as a strong reference for the prevention of landslide hazards and decision-making mitigation by government departments.

show abstract

“…The speed is not as good as gradient descent optimization, which requires large computing resources. Its advantages are simple, easy to implement, no gradient information, few parameters, especially its natural real coding characteristics, especially suitable for dealing with real optimization problems [39]. Liu et al [40] realize the high-density culture of Saccharomyces boulardii, the high-density fermentation medium and fermentation process were optimized.…”

Section: Optimization Of Mb Removal By Modified Pomelomentioning

confidence: 99%

Optimizing the Methylene Blue Removal from Aqueous Solution Using Pomelo Peel Based Biochar Assisted by RSM and ANN-PSO

Wang¹,

Wu²,

Long³

2021

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

Biochar is regarded as an ideal adsorbent because of its low cost, high adsorption performance, large porosity and high carbon content, which can effectively adsorb organic pollutants in wastewater. The present study explores the modified pomelo peel based biochar used to remove methylene blue (MB) from the simulated wastewater and its adsorption mechanism. The calcinated biochar prepared by pomelo peel under the three temperatures (450ºC, 500ºC and 550ºC) was characterized using SEM, FI-IR, XRD, N 2 adsorption and TGA. The removal conditions were optimized by response surface methodology (RSM) and artificial neural network-particle swarm optimization (ANN-PSO). The results showed that the bulk structure and surface rougher of the biochar increase with the rising of calcination temperature. The prepared materials contained a large number of active functional groups such as lignin, cellulose and hemicellulose. The specific surface area of the calcinated materials at 450ºC, 500ºC and 550ºC is 2.511, 3.353 and 4.344 m 2 /g, respectively, which were belong to mesoporous materials (2-50 nm). ANN-PSO was more suitable than that of RSM to optimize the removal conditions of MB using the prepared materials. The maximum removal efficiency of MB was reached at 89.72% under temperature = 34.63ºC, reaction time = 80.00 min, initial MB concentration = 169.73 mg/L and initial pH = 7. The actual removal efficiency of verification experiment was 87.96%, and the absolute error was 1.76%. The process of MB adsorbed onto the prepared biochar was well accordant with the pseudo second-order kinetic and Langmuir models. The adsorption process of MB by the biochar was a spontaneous, endothermic and entropy-driven. In summary, it is thus indicated that the modified pomelo peel based biochar can be regenerated within fourth cycle and have application prospect as a useful adsorbent for water treatment.

show abstract

A Comparative Study of Landslide Susceptibility Mapping Using SVM and PSO-SVM Models Based on Grid and Slope Units

Cited by 38 publications

References 75 publications

A comparative evaluation of machine learning algorithms and an improved optimal model for landslide susceptibility: a case study

A comparative evaluation of machine learning algorithms and an improved optimal model for landslide susceptibility: a case study

Combined SBAS-InSAR and PSO-RF Algorithm for Evaluating the Susceptibility Prediction of Landslide in Complex Mountainous Area: A Case Study of Ludian County, China

Optimizing the Methylene Blue Removal from Aqueous Solution Using Pomelo Peel Based Biochar Assisted by RSM and ANN-PSO

Contact Info

Product

Resources

About