Spatial modeling of susceptibility to subsidence using machine learning techniques

Mohammady, Majid; Pourghasemi, Hamid Reza; Amiri, Mojtaba; Tiefenbacher, John P.

doi:10.1007/s00477-020-01967-x

Cited by 24 publications

(17 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reliability of numerical models is closely related to the professional background and engineering experience of the modeler [10,11]. In recent years, with the development of AI technology, mining scientists and technicians have introduced AI models into the field of mining subsidence prediction and obtained certain research results [12][13][14]. The research on mining subsidence prediction has achieved many research results, and each method has its own advantages and disadvantages.…”

Section: Introductionmentioning

confidence: 99%

Research on the Prediction Model of Mine Subsidence Based on Object-Oriented and Probability Integration Method

Zhao

Gao

et al. 2022

Geofluids

View full text Add to dashboard Cite

The movement of rock formations caused by mining eventually leads to the mining subsidence damage of the surface. In order to accurately and efficiently predict the surface subsidence caused by mining, an object-oriented method combined with the classical probability integration method is introduced in this paper, and an object-oriented probability integration prediction model framework is established. MATLAB2019 is used to develop the application program of the prediction model, the reliability of the prediction model is tested by engineering cases, and the main influencing factors of mining subsidence are analyzed at the same time. The results show that the predicted results of the model are basically consistent with the case. The prediction model developed in this paper using the object-oriented method combined with the probability integration method is reliable. It is feasible to apply the object-oriented method to mining subsidence prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on the Prediction Model of Mine Subsidence Based on Object-Oriented and Probability Integration Method

Zhao

Gao

et al. 2022

Geofluids

View full text Add to dashboard Cite

show abstract

“…(Chen et al, 2016;Ju and Xu, 2015;Ma et al, 2017;Yan et al, 2018). With the rapid development of the subject of arti cial intelligence, many scholars have cited arti cial intelligence technology in the prediction and evaluation of MLS (Mohammady et al, 2021;Yan et al, 2021b).Research methods based on numerical simulation are also widely used in the evaluation and analysis of MLS (Liu et al, 2021;Sikora and Wesolowski, 2021). At present, the probability integral method is the most widely used subsidence prediction method in China (Xing et al, 2021;Yuan et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Assessment on coal mining land subsidence by using an innovative comprehensive weighted cloud model combination PSR conceptual model

Zhou

Xiong

et al. 2022

Preprint

View full text Add to dashboard Cite

The research on land subsidence (LS) is a global topic. In recent years, the environmental problems caused by coal mining have received great attention. In particular, mining land subsidence (MLS) caused damage to villages, buildings, farmland, etc, which seriously threatened the living environment and ecological environment of the mining area. To reasonably evaluate mining land subsidence (MLS) of coal mine, based on characteristics of strata movement in coal mining, this study put forward PSR (Pressure-State-Response) concept model based on MLS to build an evaluation index system of MLS in coal mine. Based on this index system, in view of the uncertainty in the evaluation process, the cloud model is used to represent the index weight and comprehensive evaluation calculations, which fully consider the randomness and ambiguity in the evaluation process. MLS of several important mining areas in China were evaluated and were classified as three grades (Slight-Medium-Strong). The cloud model assessment results are compared with the result of the probability integration method and the actual situation. The assessment results of the cloud model are closer to the actual situation than the probability integration method. It shows that the established MLS evaluation method based on cloud model in this study is reasonable and feasible. The Mining width and height ratio, depth and height ratio and coal seam dip angle are important factors affecting MLS. Therefore, improving the mining method to deal with the goaf reasonably, optimizing the mining design to control the influence range of mining are important measures to reduce the MLS and protect the ecological environment of mining areas.

show abstract

“…(Kavzoglu et al, 2019). Approaches to LSM modeling vary widely, and some of the most common approaches are highlighted in this study: AHP (Kayastha et al, 2013;Roccati et al, 2021;Grozavu and Patriche, 2021), ANFIS (Paryani et al, 2020;Chen et al, 2021), ANN (Chen et al, 2017), PSO-ANN (Moayedi et al, 2019), Weighting Factor (Yalcin, 2008;Hussain et al, 2021), Bayesian (Sun et al, 2021;Lee et al, 2020), Deep Learning (Dao et al, 2020;Ngo et al, 2021), Frequency Ratio (Senanayake et al, 2020;Berhane et al, 2020), Fuzzy Logic (Tsangaratos et al, 2018Razifard et al, 2019), Logistic Regression (Schlögel et al, 2018;Chen et al, 2019), Machine Learning (Ghorbanzadeh et al, 2019, Kavzoglu et al, 2019, Mohammady et al, 2021, M-AHP (Nefeslioglu et al, 2012;Bugday and Akay, 2019), Multilayer Perceptron Neural Network (Li et al, 2019;Hong et al, 2020), SWARA (Dehnavi et al, 2015;Pourghasemi et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Assessment of alternative forest road routes and landslide susceptibility mapping using machine learning

Buğday

Akay

2022

CERNE

View full text Add to dashboard Cite

Background: Forest roads are among the most basic infrastructure used for forestry activities and services. To facilitate the increased amount of biomass harvesting adequately, the existing road network may require modifications to allow forest transportation within harvesting units that are not yet accessed by the roads. The construction of a forest road can trigger landslides, so the necessary constraints should be considered when the road is being planned to preclude such problems. Landslide Susceptibility Mapping (LSM) has become an integral part of the growing process of machine learning (ML), providing a more effective platform for practitioners, planners, and decision-makers. This study aims to reveal the most suitable alternative routes for a forest road, especially in areas susceptible to landslides, and to provide an effective tool for decision-makers.Results: For this purpose, two models were developed through ML: Logistic Regression (LR) and Random Forest (RF). Elevation, slope, aspect, curvature, Topographic Wetness Index (TWI), Stream Power Index (SPI), distance from the fault, the road, and the stream, and lithology were considered as the main landslide susceptibility factors in these models. The best model was obtained by the RF approach with an Area Under ROC Curve (AUC) value of 81.9%, while the LR model was 78.2%. LSM data was used as a base, and alternative routes were obtained through CostPath analysis. Conclusion:It has been shown that the ML methods used in this study can positively contribute to decision-making by providing more effective LSM calculations in studies to determine alternative routes in a forest road network.

show abstract

Spatial modeling of susceptibility to subsidence using machine learning techniques

Cited by 24 publications

References 62 publications

Research on the Prediction Model of Mine Subsidence Based on Object-Oriented and Probability Integration Method

Research on the Prediction Model of Mine Subsidence Based on Object-Oriented and Probability Integration Method

Assessment on coal mining land subsidence by using an innovative comprehensive weighted cloud model combination PSR conceptual model

Assessment of alternative forest road routes and landslide susceptibility mapping using machine learning

Contact Info

Product

Resources

About