Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches.

Floods are natural occurrences that pose serious risks to human life and the environment, including significant property and infrastructure damage and subsequent socioeconomic challenges. Recent floods in Cheongju County, South Korea have been linked to river overflow. In this study, we created flood susceptibility maps of Cheongju, South Korea using machine learning techniques including support vector regression (SVR), boosted tree (BOOST), and long short-term memory (LSTM) algorithms, based on environmental factors. Potentially influential variables were selected based on flood data gathered through field surveys; these included the slope, aspect, length-slope factor, wind exposition index, terrain wetness index, plan curvature, normalized difference water index, geology, soil drainage, soil depth, soil texture, land use type, and forest density. To improve the robustness of the flood susceptibility model, the most influential factors were identified using the frequency ratio method. Implementing machine learning techniques like SVR and BOOST produced encouraging outcomes, achieving the area under the curve (AUC) of 83.16% and 86.70% for training, and 81.65% and 86.43% for testing, respectively. While, the LSTM algorithm showed superior flood susceptibility mapping performance, with an AUC value of 87.01% for training and 86.91% for testing, demonstrating its robust performance and reliability in accurately assessing flood susceptibility. The results of this study enhance our understanding of flood susceptibility in South Korea and demonstrate the potential of the proposed approach for informing and guiding crucial regional policy decisions, contributing to a more resilient and prepared future.

Convolutional neural network (CNN) with metaheuristic optimization algorithms for landslide susceptibility mapping in Icheon, South Korea.

Landslides are a geological hazard that can pose a serious threat to human health and the environment of highlands or mountain slopes. Landslide susceptibility mapping is an essential tool for predicting and mitigating landslides. This study aimed to investigate the application of deep learning algorithms based on convolutional neural networks (CNNs) with metaheuristic optimization algorithms, namely the grey wolf optimizer (GWO) and imperialist competitive algorithm (ICA), to landslide susceptibility mapping. The study area was Icheon City, South Korea, for which an accurate landslide inventory dataset was available. The landslide inventory map was prepared and randomly divided into datasets of 70% for training and 30% for validation. Additionally, 18 landslide-related factors, including geo-environmental and topo-hydrological factors, were considered as predictive variables. The models were compared using area under the curve (AUC) values in receiver operating characteristic (ROC) curve analysis. The validation results showed that optimized models based on CNN-GWO (AUC = 0.876, RMSE = 0.08) and CNN-ICA (AUC = 0.852, RMSE = 0.09) outperformed the standalone CNN model (AUC = 0.847, RMSE = 0.12). Nevertheless, the CNN model outperformed previous research that used a machine learning algorithm alone. Thus, the deep learning algorithm with optimization algorithms proposed in this study can generate more suitable models for landslide susceptibility mapping in the study area due to its improved accuracy.

A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran).

In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811).

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

Subsidence of ground caused by underground mines poses hazards to human life and property. This study analyzed the hazard to ground subsidence using factors that can affect ground subsidence and a decision tree approach in a geographic information system (GIS). The study area was Taebaek, Gangwon-do, Korea, where many abandoned underground coal mines exist. Spatial data, topography, geology, and various ground-engineering data for the subsidence area were collected and compiled in a database for mapping ground-subsidence hazard (GSH). The subsidence area was randomly split 50/50 for training and validation of the models. A data-mining classification technique was applied to the GSH mapping, and decision trees were constructed using the chi-squared automatic interaction detector (CHAID) and the quick, unbiased, and efficient statistical tree (QUEST) algorithms. The frequency ratio model was also applied to the GSH mapping for comparing with probabilistic model. The resulting GSH maps were validated using area-under-the-curve (AUC) analysis with the subsidence area data that had not been used for training the model. The highest accuracy was achieved by the decision tree model using CHAID algorithm (94.01%) comparing with QUEST algorithms (90.37%) and frequency ratio model (86.70%). These accuracies are higher than previously reported results for decision tree. Decision tree methods can therefore be used efficiently for GSH analysis and might be widely used for prediction of various spatial events.

Spatial modeling of geogenic indoor radon distribution in Chungcheongnam-do, South Korea using enhanced machine learning algorithms.

Prolonged inhalation of indoor radon and its progenies lead to severe health problems for housing occupants; therefore, housing developments in radon-prone areas are of great concern to local municipalities. Areas with high potential for radon exposure must be identified to implement cost-effective radon mitigation plans successfully or to prevent the construction of unsafe buildings. In this study, an indoor radon potential map of Chungcheongnam-do, South Korea, was generated using a group method of data handling (GMDH) algorithm based on local soil properties, geogenic, geochemical, as well as topographic factors. To optimally tune the hyper-parameters of GMDH and enhance the prediction accuracy of modelling radon distribution, the GMDH model was integrated with two metaheuristic optimization algorithms, namely the bat (BA) and cuckoo optimization (COA) algorithms. The goodness-of-fit and predictive performance of the models was quantified using the area under the receiver operating characteristic (ROC) curve (AUC), mean squared error (MSE), root mean square error (RMSE), and standard deviation (StD). The results indicated that the GMDH-COA model outperformed the other models in the training (AUC = 0.852, MSE = 0.058, RMSE = 0.242, StD = 0.242) and testing (AUC = 0.844, MSE = 0.060, RMSE = 0.246, StD = 0.0242) phases. Additionally, using metaheuristic optimization algorithms improved the predictive ability of the GMDH. The GMDH-COA model showed that approximately 7 % of the total area of Chungcheongnam-do consists of very high radon-prone areas. The information gain ratio method was used to assess the predictive ability of considered factors. As expected, soil properties and local geology significantly affected the spatial distribution of radon potential levels. The radon potential map produced in this study represents the first stage of identifying areas where large proportions of residential buildings are expected to experience significant radon levels due to high concentrations of natural radioisotopes in rocks and derived soils beneath building foundations. The generated map assists local authorities to develop urban plans more wisely towards region with less radon concentrations.

Application of a weights-of-evidence method and GIS to regional groundwater productivity potential mapping.

The aim of this study is to analyze the relationship among groundwater productivity data including specific capacity (SPC) and transmissivity (T) as well as its related hydrogeological factors in a bedrock aquifer, and subsequently, to produce the regional groundwater productivity potential (GPP) map for the area around Pohang City, Korea using a geographic information system (GIS) and a weights-of-evidence (WOE) model. All of the related factors, including topography, lineament, geology, forest, and soil data were collected and input into a spatial database. In addition, SPC and T data were collected from 83 and 81 well locations, respectively. Four dependent variables including SPC values of ≥6.25 m3/d/m (Case 1) and T values of ≥3.79 m2/d (Case 3) corresponding to a yield (Y) of ≥500 m3/d, and SPC values of ≥3.75 m3/d/m (Case 2) and T values of ≥2.61 m2/d (Case 4) corresponding to a Y of ≥300 m3/d were also input into a spatial database. The SPC and T data were randomly selected in an approximately 70:30 ratio to train and validate the WOE model. Tests of conditional independence were performed for the used factors. To assess the regional GPP for each dependent variable, W+ and W- of each factor's rating were overlaid spatially. The results of the analysis were validated using area under curve (AUC) analysis with the existing SPC and T data that were not used for the training of the model. The AUC of Cases 1, 2, 3 and 4 showed 0.7120, 0.6893, 0.6920, and 0.7098, respectively. In the case of the dependent variables, Case 1 had an accuracy of 71.20% (AUC: 0.7120), which is the best result produced in this analysis. Such information and the maps generated from it could be used for groundwater management, a practice related to groundwater resource exploration.

Spatial prediction of ground subsidence susceptibility using an artificial neural network.

Ground subsidence in abandoned underground coal mine areas can result in loss of life and property. We analyzed ground subsidence susceptibility (GSS) around abandoned coal mines in Jeong-am, Gangwon-do, South Korea, using artificial neural network (ANN) and geographic information system approaches. Spatial data of subsidence area, topography, and geology, as well as various ground-engineering data, were collected and used to create a raster database of relevant factors for a GSS map. Eight major factors causing ground subsidence were extracted from the existing ground subsidence area: slope, depth of coal mine, distance from pit, groundwater depth, rock-mass rating, distance from fault, geology, and land use. Areas of ground subsidence were randomly divided into a training set to analyze GSS using the ANN and a test set to validate the predicted GSS map. Weights of each factor's relative importance were determined by the back-propagation training algorithms and applied to the input factor. The GSS was then calculated using the weights, and GSS maps were created. The process was repeated ten times to check the stability of analysis model using a different training data set. The map was validated using area-under-the-curve analysis with the ground subsidence areas that had not been used to train the model. The validation showed prediction accuracies between 94.84 and 95.98%, representing overall satisfactory agreement. Among the input factors, "distance from fault" had the highest average weight (i.e., 1.5477), indicating that this factor was most important. The generated maps can be used to estimate hazards to people, property, and existing infrastructure, such as the transportation network, and as part of land-use and infrastructure planning.

Radon potential mapping in Jangsu-gun, South Korea using probabilistic and deep learning algorithms.

The adverse health effects associated with the inhalation and ingestion of naturally occurring radon gas produced during the uranium decay chain mean that there is a need to identify high-risk areas. This study detected radon-prone areas using a geographic information system (GIS)-based probabilistic and machine learning methods, including the frequency ratio (FR) model and a convolutional neural network (CNN). Ten influencing factors, namely elevation, slope, the topographic wetness index (TWI), valley depth, fault density, lithology, and the average soil copper (Cu), calcium oxide (Cao), ferric oxide (Fe2O3), and lead (Pb) concentrations, were analyzed. In total, 27 rock samples with high activity concentration index values were divided randomly into training and validation datasets (70:30 ratio) to train the models. Areas were categorized as very high, high, moderate, low, and very low radon areas. According to the models, approximately 40% of the study area was classified as very high or high risk. Finally, the radon potential maps were validated using the area under the receiver operating characteristic curve (AUC) analysis. This showed that the CNN algorithm was superior to the FR method; for the former, AUC values of 0.844 and 0.840 were obtained using the training and validation datasets, respectively. However, both algorithms had high predictive power. Slope, lithology, and TWI were the best predictors of radon-affected areas. These results provide new information regarding the spatial distribution of radon, and could inform the development of new residential areas. Radon screening is important to reduce public exposure to high levels of naturally occurring radiation.

Spatial prediction of landslide susceptibility using hybrid support vector regression (SVR) and the adaptive neuro-fuzzy inference system (ANFIS) with various metaheuristic algorithms.

Landslides are natural and sometimes quasi-natural hazards that are destructive to natural resources and cause loss of human life every year. Hence, preparing susceptibility maps for landslide monitoring is essential to minimizing their negative effects. The main aim of the current research was to develop landslide susceptibility maps for Icheon Township, South Korea, using hybrid Machin learning and metaheuristic algorithms, that is, the bee algorithm (Bee), the adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), and the grey wolf optimizer (GWO), and to compare their predictive accuracy. Based on identified landslide locations, an inventory map was prepared and divided into training and validation data sets (70%/30%). the predicated model outcomes were validated with root mean square error (RMSE), and area under receiver operating characteristic curve (AUC), and pairwise comparison values for the ANFIS, ANFIS-Bee, ANFIS-GWO, SVR, SVR-Bee, and SVR-GWO models were obtained. The area under the curve was obtained with the training and validation data sets. Based on the training data sets, AUC of 80%, 83%, 83%, 69%, 81%, and 80% were obtained for the SVR, SVR-GWO, SVR-Bee, ANFIS, ANFIS-GWO, and ANFIS-Bee models, respectively. For the validation data sets, values of 79%, 82%, 82%, 68%, 79%, and 79%, respectively, were obtained. The SVR-GWO and SVR-Bee models were the most predictive models in terms of constructing the exceptionally focused landslide susceptibility map, with little spatial variation in the highly susceptible classes. Furthermore, the MSE, RMSE, and pairwise comparisons indicated that the SVR-GWO and SVR-Bee models were superior models for this study township. In addition, ANFIS individually was not superior to the ensembles of ANFIS-GWO and ANFIS-Bee for landslide assessment. These landslide susceptibility maps provide a platform for land use planning with an eye toward sustainable development of infrastructure and damage reduction for Icheon Township.

Modelling gully-erosion susceptibility in a semi-arid region, Iran: Investigation of applicability of certainty factor and maximum entropy models.

Gully erosion susceptibility mapping is a fundamental tool for land-use planning aimed at mitigating land degradation. However, the capabilities of some state-of-the-art data-mining models for developing accurate maps of gully erosion susceptibility have not yet been fully investigated. This study assessed and compared the performance of two different types of data-mining models for accurately mapping gully erosion susceptibility at a regional scale in Chavar, Ilam, Iran. The two methods evaluated were: Certainty Factor (CF), a bivariate statistical model; and Maximum Entropy (ME), an advanced machine learning model. Several geographic and environmental factors that can contribute to gully erosion were considered as predictor variables of gully erosion susceptibility. Based on an existing differential GPS survey inventory of gully erosion, a total of 63 eroded gullies were spatially randomly split in a 70:30 ratio for use in model calibration and validation, respectively. Accuracy assessments completed with the receiver operating characteristic curve method showed that the ME-based regional gully susceptibility map has an area under the curve (AUC) value of 88.6% whereas the CF-based map has an AUC of 81.8%. According to jackknife tests that were used to investigate the relative importance of predictor variables, aspect, distance to river, lithology and land use are the most influential factors for the spatial distribution of gully erosion susceptibility in this region of Iran. The gully erosion susceptibility maps produced in this study could be useful tools for land managers and engineers tasked with road development, urbanization and other future development.

Groundwater productivity potential mapping using evidential belief function.

The evidential belief function (EBF) model was applied and validated for analysis of groundwater-productivity potential (GPP) in Boryeong and Pohang cities, agriculture region in Korea using geographic information systems (GIS). Data about related factors, including topography, lineament, geology, forest, soil, and groundwater data were collected and input into a spatial database. Additionally, in the Boryeong area, specific capacity (SPC) data not lower than 4.55 m3 /d/m were collected, corresponding to 300 m3 /d yield from 72 well locations. In the Pohang area, SPC data of ≥ 6.25 m3 /d/m were collected, corresponding to a yield of 500 m3 /d from 44 well locations. By using the constructed spatial database, 19 factors related to groundwater productivity were extracted. The relationships between the well locations and the factors were identified and quantified by using the EBF model. Four relationships were calculated: belief (Bel), disbelief (Dis), uncertainty (Unc), and plausibility (Pls). The relationships were used as factor ratings in the overlay analysis to create GPP indices and maps. The resulting GPP maps showed 83.41% and 77.53% accuracy in Boryeong and Pohang areas, respectively. The EBF model was found to be more effective in terms of prediction accuracy.

Macrobenthos habitat potential mapping using GIS-based artificial neural network models.

This paper proposes and tests a method of producing macrobenthos habitat potential maps in Hwangdo tidal flat, Korea based on an artificial neural network. Samples of macrobenthos were collected during field work, and eight control factors were compiled as a spatial database from remotely sensed data and GIS analysis. The macrobenthos habitat potential maps were produced using an artificial neural network model. Macrobenthos habitat potential maps were made for Macrophthalmus dilatatus, Cerithideopsilla cingulata, and Armandia lanceolata. The maps were validated by compared with the surveyed habitat locations. A strong correlation between the potential maps and species locations was revealed. The validation result showed average accuracies of 74.9%, 78.32%, and 73.27% for M. dilatatus, C. cingulata, and A. lanceolata, respectively. A GIS-based artificial neural network model combined with remote sensing techniques is an effective tool for mapping the areas of macrobenthos habitat potential in tidal flats.

Macrobenthos habitat mapping in a tidal flat using remotely sensed data and a GIS-based probabilistic model.

This paper proposes and tests a method of producing macrofauna habitat potential maps based on a weights-of-evidence model (a probabilistic approach) for the Hwangdo tidal flat, Korea. Samples of macrobenthos were collected during field work, and we considered five mollusca species for habitat mapping. A weights-of-evidence model was used to calculate the relative weights of 10 control factors that affect the macrobenthos habitat. The control factors were compiled as a spatial database from remotely sensed data combined with GIS analysis. The relative weight of each factor was integrated as a species potential index (SPI), which produced habitat potential maps. The maps were compared with the surveyed habitat locations, revealing a strong correlation between the potential maps and species locations. The combination of a GIS-based weights-of-evidence model and remote sensing techniques is an effective method in determining areas of macrobenthos habitat potential in a tidal flat setting.

Application of likelihood ratio and logistic regression models to landslide susceptibility mapping using GIS.

For landslide susceptibility mapping, this study applied and verified a Bayesian probability model, a likelihood ratio and statistical model, and logistic regression to Janghung, Korea, using a Geographic Information System (GIS). Landslide locations were identified in the study area from interpretation of IRS satellite imagery and field surveys; and a spatial database was constructed from topographic maps, soil type, forest cover, geology and land cover. The factors that influence landslide occurrence, such as slope gradient, slope aspect, and curvature of topography, were calculated from the topographic database. Soil texture, material, drainage, and effective depth were extracted from the soil database, while forest type, diameter, and density were extracted from the forest database. Land cover was classified from Landsat TM satellite imagery using unsupervised classification. The likelihood ratio and logistic regression coefficient were overlaid to determine each factor's rating for landslide susceptibility mapping. Then the landslide susceptibility map was verified and compared with known landslide locations. The logistic regression model had higher prediction accuracy than the likelihood ratio model. The method can be used to reduce hazards associated with landslides and to land cover planning.