A comparative study on machine learning modeling for mass movement susceptibility mapping (a case study of Iran)

Emami, Sayed Naeim; Yousefi, Saleh; Pourghasemi, Hamid Reza; Tavangar, Shahla; Santosh, M.

doi:10.1007/s10064-020-01915-7

Cited by 25 publications

(13 citation statements)

References 154 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ROC curve plots sensitivity on the x ‐axis and 100‐specificity on the y ‐axis (Rahmati et al, 2019). Three criteria—negative predictive value (NPV), positive predictive value (PPV), and area under the ROC curve (AUC) were used to evaluate results of the classified (Emami et al, 2020; Pourghasemi et al, 2020; Pourghasemi, Razavi‐Termeh, Kariminejad, Hong, & Chen, 2020; Pourghasemi, Yousefi, Sadhasivam, & Eskandari, 2020) [Equations )]:

PPV = \frac{TP}{TP + FP},

NPV = \frac{TN}{TN + FN},

AUC = \frac{\sum TP + \sum TN}{(NRP + NRN)},

Where: TP, FP, TN, FN, NRP, and NRN are the numbers of true positives, false positives, true negatives, false negatives, number of real positive, and number of real negatives, respectively. Sensitivity and specificity in statistics are two indices often used to evaluate the test of binary classification [Equations ) and ()].

Sensitivity = \frac{TP}{TP + FN},

Specificity = \frac{TN}{TN + FP} .

…”

Section: Methodsmentioning

confidence: 99%

“…The ROC curve plots sensitivity on the x-axis and 100-specificity on the y-axis (Rahmati et al, 2019). Three criterianegative predictive value (NPV), positive predictive value (PPV), and area under the ROC curve (AUC) were used to evaluate results of the classified (Emami et al, 2020;Pourghasemi, Razavi-Termeh, Kariminejad, Hong, & Chen, 2020;Pourghasemi, Yousefi, Sadhasivam, & Eskandari, 2020)…”

Section: Validation Of Modelsmentioning

confidence: 99%

“…MLMs have become important tools for analysis and management of many environmental processes and outcomes, like gully erosion (Arabameri et al, 2019; Hosseinalizadeh et al, 2019; Nhu et al, 2020), flood (Hong et al, 2018; Shafizadeh‐Moghadam, Valavi, Shahabi, Chapi, & Shirzadi, 2018), landslides and mass movements (Chen, Panahi, et al, 2017; Emami, Yousefi, Pourghasemi, Tavangar, & Santosh, 2020; Lee & Pradhan, 2007; Zaheer, Zaheer, & Hamza, 2020), snow avalanches (Sethia, Pandey, Chattoraj, & Manickam, 2018; Yilmaz, 2016), other geomorphological matters (Infante‐Paez & Marfurt, 2019; Pourghasemi, Yousefi, Kornejady, & Cerdà, 2017), forest fires (Gigović, Pourghasemi, Drobnjak, & Bai, 2019; Pourghasemi, Beheshtirad, & Pradhan, 2016; Pourtaghi, Pourghasemi, & Rossi, 2015), and subsidence (Abdollahi, Pourghasemi, Ghanbarian, & Safaeian, 2018; Mohammady, Pourghasemi, & Amiri, 2019). In the research literature, there are many learning models that have been used to investigate the spatial distribution of various natural phenomena (floods, forest fires, landslides, and erosion), each of which has advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

“…One of the most popular and simplest decision tree algorithms is the CART decision tree, which has many uses in classification and regression. The CART decision tree algorithm divides the data into binary parts to make the decision tree, and builds the binary tree based on them (Choubin et al, 2019;Emami et al, 2020). However, there have been no attempts to use MLM to assess rangeland quality or survey range degradation.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Assessment of land degradation using machine‐learning techniques: A case of declining rangelands

et al. 2020

Self Cite

View full text Add to dashboard Cite

Increased use and increasing demands pose serious threats to rangelands. In this study, we document a pronounced downward trend in rangeland quality in the Alborz Mountains in Firozkuh County, Iran using analysis of three machine‐learning models (MLMs). A total of 1,147 transects were established to evaluate the rangeland quality trends from field data collected over a 7‐year period. Twelve independent conditional factors were analyzed for their relationships to range quality through three MLMs—Random Forest (RF), classification and regression tree (CART), and support vector machine (SVM). Based on assessments of the trained and validated models, RF, with a ROC‐AUC = 0.96, was determined to be the most robust. The results show that about 20% of the rangeland in the study area is in a critically degraded condition. Distances from roads and livestock density are the two factors most strongly linked to degradation. These results, in combination with field observations, indicate that the rangelands of the study area face two major challenges (overgrazing and early grazing) that require new strategies to mitigate and prevent damages. This study may provide important guidance for evaluating rangeland conditions in other regions of the world.

show abstract

PPV = \frac{TP}{TP + FP},

NPV = \frac{TN}{TN + FN},

AUC = \frac{\sum TP + \sum TN}{(NRP + NRN)},

Sensitivity = \frac{TP}{TP + FN},

Specificity = \frac{TN}{TN + FP} .

…”

Section: Methodsmentioning

confidence: 99%

Section: Validation Of Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Assessment of land degradation using machine‐learning techniques: A case of declining rangelands

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, they may affect infrastructure conditions and their serviceability and are represented by extreme natural events, such as landslides, subsidence, and floods. It is known that such phenomena can be linked to environmental parameters of a territory, such as topological, geomorphological, geomorphometric, and hydrological features [ 84 , 85 , 86 , 87 ]. Therefore, by using MLAs, we aimed to correlate PS-InSAR-based surface motion estimates and several environmental parameters.…”

Section: Test Sites and Sar-based Mlasmentioning

confidence: 99%

Can Machine Learning and PS-InSAR Reliably Stand in for Road Profilometric Surveys?

Fiorentini

Maboudi

Leandri

et al. 2021

Sensors

View full text Add to dashboard Cite

This paper proposes a methodology for correlating products derived by Synthetic Aperture Radar (SAR) measurements and laser profilometric road roughness surveys. The procedure stems from two previous studies, in which several Machine Learning Algorithms (MLAs) have been calibrated for predicting the average vertical displacement (in terms of mm/year) of road pavements as a result of exogenous phenomena occurrence, such as subsidence. Such algorithms are based on surveys performed with Persistent Scatterer Interferometric SAR (PS-InSAR) over an area of 964 km2 in the Tuscany Region, Central Italy. Starting from this basis, in this paper, we propose to integrate the information provided by these MLAs with 10 km of in situ profilometric measurements of the pavement surface roughness and relative calculation of the International Roughness Index (IRI). Accordingly, the aim is to appreciate whether and to what extent there is an association between displacements estimated by MLAs and IRI values. If a dependence exists, we may argue that road regularity is driven by exogenous phenomena and MLAs allow for the replacement of in situ surveys, saving considerable time and money. In this research framework, results reveal that there are several road sections that manifest a clear association among these two methods, while others denote that the relationship is weaker, and in situ activities cannot be bypassed to evaluate the real pavement conditions. We could wrap up that, in these stretches, the road regularity is driven by endogenous factors which MLAs did not integrate during their training. Once additional MLAs conditioned by endogenous factors have been developed (such as traffic flow, the structure of the pavement layers, and material characteristics), practitioners should be able to estimate the quality of pavement over extensive and complex road networks quickly, automatically, and with relatively low costs.

show abstract

Evaluation of Effective Criteria on Determination of Capable Areas to Construction of Underground Dam in Shahrekord Watershed, Iran

Emami

Yousefi

Nekoeimehr

2023

Springer Hydrogeology

View full text Add to dashboard Cite

A comparative study on machine learning modeling for mass movement susceptibility mapping (a case study of Iran)

Cited by 25 publications

References 154 publications

Assessment of land degradation using machine‐learning techniques: A case of declining rangelands

Assessment of land degradation using machine‐learning techniques: A case of declining rangelands

Can Machine Learning and PS-InSAR Reliably Stand in for Road Profilometric Surveys?

Evaluation of Effective Criteria on Determination of Capable Areas to Construction of Underground Dam in Shahrekord Watershed, Iran

Contact Info

Product

Resources

About