Application of decision tree model for the ground subsidence hazard mapping near abandoned underground coal mines

Lee, Saro; Park, Inhye

doi:10.1016/j.jenvman.2013.04.010

Cited by 98 publications

(58 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…fuzzy approach to ground subsidence mapping (Choi et al 2010), and various statistical and artificial neural network methods (Oh and Lee 2011;Guo et al 2011;Lee and Park 2013;Mathey 2013;Park et al 2014). These studies focus predominately on horizontal, single coal seam cases and in none of them, thickness, inclination of exploited coal panels and mining system factors have been considered.…”

Section: Gwr Model Resultsmentioning

confidence: 99%

“…The relations were then used as factor ratings in GIS overlay analysis to create ground subsidence hazard indices and maps. In another study in Korea, Lee and Park (2013) and Park et al (2014) have analysed land subsidence hazard caused by abandoned underground mines using the decision tree approach and factors that can influence subsidence in a geographic information system (GIS). They have produced and verified land subsidence hazard maps for the study site.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of GIS spatial regression methods in assessment of land subsidence in complicated mining conditions: case study of the Walbrzych coal mine (SW Poland)

Blachowski

2016

Nat Hazards

View full text Add to dashboard Cite

Land subsidence in the area of the city of Walbrzych (SW Poland) has been a consequence of underground mining of hard coal. Exploitation of multiseam deposit took place for several 100 years and ended in the late 90'ties of the twentieth century. During this time, many buildings and constructions were affected by subsidence-related damages and new landforms including mining waste dumps have developed on the surface in a consequence of underground extraction of coal. Previous studies indicated that cumulative subsidence calculated with the empirical Knothe theory reached -22 m, whereas calculations based on results of cartographic data processing showed more than -30 m (± 3 m) pointing to insufficient reliability of traditional methods when applied in complex and complicated conditions (multiseam and steeply inclined deposits). Present-day height of manmade landforms in areas affected by subsidence reaches 63 m (± 3 m). Therefore, in the presented research, a weighted spatial regression method has been proposed for analysis and modelling of mining induced land subsidence. The study concerned the former Walbrzych coal mine area and the 1886-2009 period. The subsidence modelling has been done in geographic information systems with geographically weighted regression (GWR) method that allows for spatial variability of subsidence factors. Four, out of the analysed seven, subsidence factors were identified as significant (thickness, inclination and depth of coal levels and surface slope) and used as independent (explanatory) variables in construction of the subsidence model with the GWR method. The validated model was used to estimate subsidence in up to now unmapped areas transformed by manmade landforms. The maximum predicted subsidence in these parts for the 1886-2009 period reaches -10.5 m. In the result, a spatial representation (hybrid map) of subsidence for the entire Walbrzych coal mine has been produced.

show abstract

Section: Gwr Model Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Application of GIS spatial regression methods in assessment of land subsidence in complicated mining conditions: case study of the Walbrzych coal mine (SW Poland)

Blachowski

2016

Nat Hazards

View full text Add to dashboard Cite

show abstract

“…Most countermeasures for ground subsidence involve simple reinforcement after the ground has already subsided [2][3][4]. As a result, it is important to have a systematic prediction and management plan for areas experiencing ground subsidence.…”

Section: Introductionmentioning

confidence: 99%

“…Recent studies have analyzed ground subsidence hazards using the results of geological and geotechnical investigations and of probability, statistical, fuzzy algebra, and artificial neural network models in tandem with GIS applications [2,[4][5][6][7][8][9][10][11][12][13][14][15]. Some studies have assessed and identified areas with a high subsidence risk.…”

Section: Introductionmentioning

confidence: 99%

“…Choi et al [11] constructed subsidence susceptibility maps based on fuzzy relations for an AUCM area. Lee and Park [4] applied frequency ratio and decision tree model to mapping GSH maps. For the same study site, Lee et al [12] applied a logistic regression model, and Oh and Lee [15] integrated GSH maps using various models such as frequency ratio model, weight of evidence, logistic regression and artificial neural network model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ensemble of ground subsidence hazard maps using fuzzy logic

Park

Lee

Lee³

2014

Open Geosciences

Self Cite

View full text Add to dashboard Cite

Hazard maps of ground subsidence around abandoned underground coal mines (AUCMs) in Samcheok, Korea, were constructed using fuzzy ensemble techniques and a geographical information system (GIS). To evaluate the factors related to ground subsidence, a spatial database was constructed from topographic, geologic, mine tunnel, land use, groundwater, and ground subsidence maps. Spatial data, topography, geology, and various ground-engineering data for the subsidence area were collected and compiled in a database for mapping groundsubsidence hazard (GSH). The subsidence area was randomly split 70/30 for training and validation of the models. The relationships between the detected ground-subsidence area and the factors were identified and quantified by frequency ratio (FR), logistic regression (LR) and artificial neural network (ANN) models. The relationships were used as factor ratings in the overlay analysis to create ground-subsidence hazard indexes and maps. The three GSH maps were then used as new input factors and integrated using fuzzy-ensemble methods to make better hazard maps. All of the hazard maps were validated by comparison with known subsidence areas that were not used directly in the analysis. As the result, the ensemble model was found to be more effective in terms of prediction accuracy than the individual model.

show abstract

Application of novel hybrid model for land subsidence susceptibility mapping

2022

View full text Add to dashboard Cite

Land subsidence (LS) is one of the challenging geo‐hazards in several regions of the world that is mainly caused by the overexploitation of groundwater and subsequent collapse of underground cavities. The prediction of LS is difficult due to limitations in monitoring, proper surveys, and knowledge related to the functioning and behaviour of the phenomenon. The application of remote sensing (RS) and global positioning system (GPS) for the proper location identification of LS in the ground and its implementation in susceptibility mapping can help to better constrain this geohazard. However, proper LS susceptibility maps to identify LS prone areas and to mitigate this problem in a way are generally lacking. Several methodologies have been developed for preparing LS susceptibility maps through RS techniques coupled with statistical and machine learning (ML) algorithms. Furthermore, different regions have unique natural and anthropogenic causes for the occurrence of LS, such as subsidence due to groundwater over‐exploitation, road construction, consolidation of alluvial soil, mining activities, and so forth, resulting in severe economic losses. The LS susceptibility mapping (LSSM) can help to prevent natural and human catastrophes and reduce the economic damages. ML techniques are becoming increasingly proficient at modelling such occurrences and have wide application in LSSM. This study compares the performances of single and hybrid ML models to predict and map the susceptible areas prone to LS. A combination of several algorithms helps to improve the overall results. In order to achieve this, the gradient‐boosting machine‐evolutionary genetic algorithm (GBM‐EG) was adopted in this study for LS assessment and compared to three algorithms, namely random forest, artificial neural networks, and alternating decision tree, that stand as commonly used benchmarks. This case study on LSSM was carried out in the Abozidabad watershed, Isfahan Province, Iran, and a total of 155 LS locations were identified by using GPS. Measures of 12 conditioning factors were compiled for each of the sites. These data were input into the models in five different training‐to‐validation configurations of sample ratios: D1 (90%:10%), D2 (80%:20%), D3 (70%:30%), D4 (60%:40%), and D5 (50%:50%). The performance of the algorithms were evaluated with the receiver operating characteristic curve and seed cell area index (SCAI). The results show that the best area under curve value (0.989) and SCAI value were achieved by the GBM‐EG hybrid model in an 80:20 ratio. The results demonstrate that LSSMs can be effectively produced to support planning and land use for management decisions.

show abstract

Application of decision tree model for the ground subsidence hazard mapping near abandoned underground coal mines

Cited by 98 publications

References 31 publications

Application of GIS spatial regression methods in assessment of land subsidence in complicated mining conditions: case study of the Walbrzych coal mine (SW Poland)

Application of GIS spatial regression methods in assessment of land subsidence in complicated mining conditions: case study of the Walbrzych coal mine (SW Poland)

Ensemble of ground subsidence hazard maps using fuzzy logic

Application of novel hybrid model for land subsidence susceptibility mapping

Contact Info

Product

Resources

About