| 1 |
What is the purpose of the empirical case study on coal manufacturing in the paper?
|
To demonstrate the proposed decision support model |
|
Therefore, considering the impact factors such as the transport cost, time, and comprehensive risk assessment model were further created. This paper develops a decision support model using an analytic hierarchy process (AHP) and zero-one goal programing (ZOGP) to determine an optimal multimodal transportation route. AHP is employed to determine weights of each factor, which rely on expert judgments. |
Therefore, considering the impact factors such as the transport cost, time, and comprehensive risk assessment model were further created. This paper develops a decision support model using an analytic hierarchy process (AHP) and zero-one goal programing (ZOGP) to determine an optimal multimodal transportation route. AHP is employed to determine weights of each factor, which rely on expert judgments. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 2 |
Which factor does the model NOT consider in route selection for a multimodal transportation network?
|
Cultural preferences |
|
...considering the impact factors such as the transport cost, time, and comprehensive risk assessment model were further created. |
...considering the impact factors such as the transport cost, time, and comprehensive risk assessment model were further created. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 3 |
What is the role of expert judgments in the decision support model?
|
They determine the empirical case study |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 4 |
What logistics system aspect does the proposed methodology aim to improve?
|
Inventory tracking |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 5 |
Essay | Describe the role of Analytic Hierarchy Process (AHP) and Zero-One Goal Programming (ZOGP) in the decision support model for determining an optimal multimodal transportation route. Explain how these methodologies contribute to the model's effectiveness and discuss any potential limitations.
|
The Analytic Hierarchy Process (AHP) and Zero-One Goal Programming (ZOGP) are two methodologies that can be applied in the decision support model for determining an optimal multimodal transportation route. |
|
AHP is a decision-making tool that helps in structuring complex problems by breaking them down into a hierarchy of criteria and alternatives, and then synthesizing these into a single overall ranking. In the context of determining a multimodal transportation route, AHP can be used to prioritize criteria such as cost, time, environmental impact, and reliability, as well as to evaluate the performance of different transportation modes against these criteria. AHP allows decision-makers to systematically compare and weigh the relative importance of these criteria, enabling them to make informed decisions about the best transportation route.
On the other hand, ZOGP is a mathematical optimization technique used to solve decision-making problems with multiple, often conflicting, objectives. In the context of multimodal transportation route optimization, ZOGP can be used to find the best combination of transportation modes and routes that satisfy various objectives, such as minimizing costs, reducing emissions, and maximizing reliability. ZOGP can handle the trade-offs between these objectives and help in identifying the optimal solution that best balances these conflicting goals. |
|
10 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 6 |
What is the role of the FAHP method in the proposed risk analysis model?
|
To determine the weights of each risk criterion |
|
The FAHP method is utilized to determine the weight of each criterion. |
The FAHP method is utilized to determine the weight of each criterion. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 7 |
Which industry is used as a case study in the proposed risk analysis model?
|
Coal |
|
A practical case study of the coal industry in Thailand has been conducted regarding multimodal transportation routes. The high visibility risks involved with complex multimodal freight transportation are identified. With prior literature and expert knowledge, 5 main multimodal transportation risk categories are investigated. Subsequently, the local risk scores of 51 segmented routes with respect to 5 criteria are generated. The FAHP-DEA approach is an effective tool for analyzing and prioritizing the critical risks in complex systems. The results of this study provide risk scores with priority ranking. Moreover, the risk assessment model can generate an optimal route in accordance with weights from the users. |
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 8 |
What does the DEA method do in the proposed FAHP-DEA methodology?
|
Analyzes road safety issues |
|
Abstract:Multimodal transportation has become a main focus of logistics systems due to environmental concerns, road safety issues, and traffic congestion. Consequently, research and policy interests in multimodal freight transportation problems are increasing. However, there are major challenges in the development of multimodal transportation associated with inherent risks and numerous uncertainties. Since risks are potential threats that directly impact logistics and transportation systems, comprehensive risk analysis should be carried out. Risk analysis is a critical process of identifying and analyzing significant issues to help industry mitigate those risks. However, identifying and prioritizing risks is more complex because of the ambiguity of the relevant data. This study proposes the integration of the fuzzy analytic hierarchy process (FAHP) and data envelopment analysis (DEA) for identifying and assessing quantitative risks. The proposed FAHP-DEA methodology uses the FAHP method to determine the weights of each risk criterion. The DEA method is employed to evaluate the linguistic variables and generate the risk scores. The simple additive weighting (SAW) method is used to aggregate risk scores under different risk criteria into an overall risk score. A case study of the coal industry demonstrates that the proposed risk analysis model is practical and allows users to more accurately prioritize risks while selecting an optimal multimodal transportation route. The process raises user's attention to the high-priority risks and is useful for industries in optimizing a multimodal transportation route under risk decision criteria. |
Abstract:Multimodal transportation has become a main focus of logistics systems due to environmental concerns, road safety issues, and traffic congestion. Consequently, research and policy interests in multimodal freight transportation problems are increasing. However, there are major challenges in the development of multimodal transportation associated with inherent risks and numerous uncertainties. Since risks are potential threats that directly impact logistics and transportation systems, comprehensive risk analysis should be carried out. Risk analysis is a critical process of identifying and analyzing significant issues to help industry mitigate those risks. However, identifying and prioritizing risks is more complex because of the ambiguity of the relevant data. This study proposes the integration of the fuzzy analytic hierarchy process (FAHP) and data envelopment analysis (DEA) for identifying and assessing quantitative risks. The proposed FAHP-DEA methodology uses the FAHP method to determine the weights of each risk criterion. The DEA method is employed to evaluate the linguistic variables and generate the risk scores. The simple additive weighting (SAW) method is used to aggregate risk scores under different risk criteria into an overall risk score. A case study of the coal industry demonstrates that the proposed risk analysis model is practical and allows users to more accurately prioritize risks while selecting an optimal multimodal transportation route. The process raises user's attention to the high-priority risks and is useful for industries in optimizing a multimodal transportation route under risk decision criteria. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 9 |
Which method is used to aggregate risk scores into an overall risk score in the proposed model?
|
Genetic Algorithm |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 10 |
Essay | Using the coal industry case study, please explain how the proposed risk analysis model is practical and aids in prioritizing risks. Discuss how this model can be beneficial for industries in optimizing multimodal transportation routes under risk decision criteria.
|
The proposed risk analysis model in the coal industry case study is practical and aids in prioritizing risks because it takes into account various factors that are relevant to the industry. The model considers factors such as the volatility of coal prices, regulatory changes, geopolitical risks, transportation risks, and environmental risks. By incorporating these factors into the risk analysis, the model provides a comprehensive view of the potential risks that the coal industry may face. |
|
The proposed risk analysis model in the coal industry case study is practical and aids in prioritizing risks because it takes into account various factors that are relevant to the industry. The model considers factors such as the volatility of coal prices, regulatory changes, geopolitical risks, transportation risks, and environmental risks. By incorporating these factors into the risk analysis, the model provides a comprehensive view of the potential risks that the coal industry may face.
The model is beneficial for industries in optimizing multimodal transportation routes under risk decision criteria because it allows for a systematic evaluation of the risks associated with different transportation routes. By considering factors such as the likelihood of transportation disruptions, the impact of those disruptions on the supply chain, and the cost of mitigating those risks, the model can help industries prioritize transportation routes based on their risk profiles.
Furthermore, the model can also help industries identify opportunities to optimize transportation routes by considering alternative modes of transportation, diversifying transportation providers, or investing in infrastructure improvements. By incorporating risk decision criteria into the optimization process, industries can make more informed decisions about their transportation routes, ultimately leading to more efficient and resilient supply chains.
Overall, the proposed risk analysis model is practical and beneficial for industries in optimizing multimodal transportation routes under risk decision criteria because it provides a structured approach to evaluating and prioritizing risks, ultimately leading to more robust and efficient transportation strategies. |
|
10 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 11 |
How were geotechnical parameters of soils at landslide-prone sites evaluated in the study?
|
Interviews with local residents |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 12 |
What modeling techniques were used to assess the probability of landslide occurrence in the future?
|
Support Vector Machines |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 13 |
What is the potential application of the study's findings in hazard management?
|
Creating awareness about heavy traffic |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 14 |
How does the study aim to contribute to hazard management in the Himalayas?
|
By serving as a guiding framework for using artificial intelligence and machine learning |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 15 |
Essay | Explain the methodology employed in the study to evaluate geotechnical parameters and assess the probability of future landslide events. Discuss the potential implications of using artificial intelligence and machine learning in hazard management in the Himalayas, with reference to the study's guiding framework.
|
The methodology employed in the study to evaluate geotechnical parameters and assess the probability of future landslide events likely involves a combination of field investigations, laboratory testing, and advanced data analysis. |
|
|
|
10 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 16 |
How was the landslide inventory database divided for training and testing in the research?
|
80% training, 20% testing |
|
The landslide inventory database (255 locations) was randomly divided into training (80 %) and testing (20 %) sets. |
The landslide inventory database (255 locations) was randomly divided into training (80 %) and testing (20 %) sets. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 17 |
Which machine learning model showed the highest prediction rate among LR, RF, and DRT?
|
Logistic Regression (LR) |
|
Among the models, LR showed the highest prediction rate and DRT showed the highest success rate. According to susceptibility zones, DRT is the more realistic model followed by LR. The maps can be applied at the local scale for landslide hazard management. |
Among the models, LR showed the highest prediction rate and DRT showed the highest success rate. According to susceptibility zones, DRT is the more realistic model followed by LR. The maps can be applied at the local scale for landslide hazard management. |
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 18 |
What do the ROC values for training and testing data signify in the context of landslide susceptibility mapping?
|
The extent of the study area |
|
The accuracy is higher than the previous research in comparison to the extent of the study area and the size of the inventory. |
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 19 |
Which model is considered more realistic according to susceptibility zones in the research?
|
Logistic Regression (LR) |
|
|
|
7 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|
| 20 |
Essay | Compare and contrast the performance of Logistic Regression (LR), Random Forest (RF), and Decision and Regression Tree (DRT) models in landslide susceptibility mapping. Discuss the strengths and limitations of each model based on the research findings.
|
Abstract
The frequency of landslides and related economic and environmental damage has increased in recent decades across the hilly areas of the world, no exception is Bangladesh. Considering the first step in landslide disaster management, different methods have been applied but no methods found as best one. As a result, landslide assessment using different methods in different geographical regions has significant importance. The research aims to prepare and evaluate landslide susceptibility maps (LSMs) of the Chattogram district using three machine learning algorithms of Logistic Regression (LR), Random forest (RF) and Decision and Regression Tree (DRT). Sixteen landslide conditioning factors were determined considering topographic, hydro-climatic, geologic and anthropogenic influence. The landslide inventory database (255 locations) was randomly divided into training (80 %) and testing (20 %) sets. The LSMs showed that almost 9–12 % of areas of the Chattogram district are highly susceptible to landslides. The highly susceptible zones cover the Chattogram district's hill ranges where active morphological processes (erosion and denudation) are dominant. The ROC values for training data were 0.943, 0.917 and 0.947 and testing data were 0.963, 0.934 and 0.905 for LR, RF and DRT models, respectively. The accuracy is higher than the previous research in comparison to the extent of the study area and the size of the inventory. Among the models, LR showed the highest prediction rate and DRT showed the highest success rate. According to susceptibility zones, DRT is the more realistic model followed by LR. The maps can be applied at the local scale for landslide hazard management.
1. Introduction
The frequency, intensity and uncertainty of all types of natural disasters are significantly increasing across the world driven by the adverse impact of climate. According to the EM-DAT database, of 16472 natural disaster records, 40.2 % of them occurred in Asia and 12.75 % of all disasters occurred in Southern Asia. Landslide alone comprises 5.08 % of all the natural disasters occurred worldwide. Asia alone is affected by 53.88 % of all landslides that occur globally and the Asian landslide alone shares 2.74 % of all the natural disasters in the world [1]. Historically, Bangladesh experiences several natural disasters such as floods, droughts, cyclones, tidal surges, river bank erosion, salinity intrusion and earthquake due to its complex geography and climate. Over the last thirty years, hill-cutting problems become prominent in the hilly areas due to development activities and unplanned urbanization (including unplanned migration). Besides, climate change-induced short-time extreme rainfall increased in Bangladesh. As a result, landslides frequently occur in the fragile hilly landscape, causing huge casualties and significant economic loss [2,3]. From the period of 2000–2018, 204 landslides occurred in south-eastern Bangladesh resulting in 727 casualties and 1017 injuries [4]. Changes in land cover in different forms in hilly areas, especially in the Chattogram district, resulted in severe landslides and the frequency is continuously increasing. Hill cutting, expansion of brick kilns, hill soil collection for brick kilns, agricultural activities on hill slopes, unplanned urbanization, and human migration to hilly areas are the major drivers of land cover change in the hilly areas of Bangladesh. These types of land cover changes make the fragile hilly landscapes more vulnerable to landslides [2,3]. From 2000 to 2018, landslides increased at a rate of 4 % and around 19 landslides occurred each year (Sultana 2020). Though the landslide risk is particularly evident in the city corporation areas of Chattogram due to the presence huge population and resources, other areas are also becoming vulnerable to landslides causing serious damage to the environment, rural peoples and natural resources [5,6].
Landslide susceptibility mapping is considered the first step in landslide hazard assessment. Subsequently, it helps in landslide management and disaster loss reduction in a region [[6], [7], [8]]. The assumption is that proper monitoring, scientific assessment and detection of landslide-prone areas is the best approach to landslide risk reduction [9]. An accurate landslide susceptible map and the relevant spatial data have a significant value in decision-making, disaster policy formulation, proper land use plan implementation at the local scale and taking essential measures for disaster risk reduction and prevention to reduce larger loss during the disaster [10].
There are several types of landslide susceptibility mapping techniques such as physically based models, qualitative, semi-quantitative and quantitative. Physically based models extract the internal process of landslides. Semi-quantitative techniques combine qualitative (expert opinion) and quantitative techniques [11]. The quantitative analysis measures the bivariate, multivariate or inherent relationship between landslide incidents and the corresponding spatial arrangement of the conditioning factors in a given landslide zone using statistical, machine and deep learning techniques [[11], [12], [13]]. In a quantitative method, the numerical approximation of the likelihood of landslide occurrence in a given landslide zone is measured using a landslide inventory database. The presumption is that the actual landslides (landslides in the inventory database) and the factors related to landslide occurrences are homogeneously distributed over the study area. There are many quantitative methods have been popularly used in landslide susceptibility mapping such as frequency ratio, information value [[14], [15], [16], [17], [18], [19], [20]], logistic regression [13,[21], [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32], [33]], random forest [19,[34], [35], [36], [37], [38], [39], [40]], support vector machine [13,[41], [42], [43], [44], [45]], and regression and decision tree [15,19,23,26,[46], [47], [48], [49], [50], [51]]. Among the quantitative methods, machine learning models had been producing more reliable and better results compared to statistical models even in the data-scarce regions [10,15,39,52,53,54]. Sometimes, bivariate models can produce similar [16] or better result compared to logistic regression model [54] and logistic regression model can over perform to machine learning model [55]. Though a number of techniques have been applied to map landslide-susceptible zones across the world, no single method is developed as a suitable one [56]. The performance of a model changes from region to region and different methods produce different results in a given study area [7,11,[57], [58], [59], [60], [61], [62]]. To overcome this limitation, the error rate of different models are compared for a single study area and the model that produces the highest accuracy is considered the best model for the given study area. This is the best and easiest strategy to choose the optimal model for landslide hazard mapping for a study area. The hypothesis is “the best model will produce the lowest error rate and it will be considered as the best predictive model” [56,63]. For this reason, researchers compared different computing techniques [57,60,61], spatial data sources [59], inventory mapping [62], the combination of spatial data [59], computing software [64] etc. to get the best landslide susceptibility map. Over time GIS-based techniques have become more popular among the scientific community for landslide-prone area prediction [10,65]. GIS and remote sensing techniques have been popularly applied to carry out many studies in landslide susceptibility mapping research across the world [61].
The rapid development of GIS (Geographic Information Systems) and the easy integration of other technology into the GIS environment enable users to easy application of several landslide susceptibility mapping models [10,66,63]. Machine learning models can be easily integrated into GIS that can simulate landslide susceptibility zones in an accurate and scientific manner. CRAN-R software, in this case, by analysing data, enables the prediction of landslides by different machine learning models and the result can be further integrated into GIS to predict probable landslide-susceptible zones.
Though some landslide susceptibility maps have been prepared for the Chattogram district but covering the whole district is limited and only application of bivariate statistical models are found. Also, machine learning methods were applied to produce landslide susceptibility maps of Chattogram Metropolitan Areas. So, the aim of the current research is to prepare landslide susceptibility maps of Chattogram District utilizing GIS-based machine learning models. The machine learning models chosen to compare are logistic regression, random forest and decision and regression tree which have been widely used in different study areas across the world with higher accuracy. The landslide susceptibility map of the whole Chattogram district was not produced using the selected machine learning models before. The landslide susceptibility map and the spatial databases will be helpful for land use planning, identifying vulnerable areas, and sustainable hill planning in the region. The scientific community, policy-makers and stakeholders will be beneficial from this research. |
|
|
|
10 |
-.50
-.25
+.25
เต็ม
0
-35%
+30%
+35%
|