Advanced susceptibility analysis of ground deformation disasters using large language models and machine learning: A Hangzhou City case study
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study integrates data-driven models and ChatGPT-4 for assessing ground deformation susceptibility, improving accuracy and reducing expert bias in urban collapse and subsidence evaluations.
Area Of Science
- Geosciences
- Artificial Intelligence
- Urban Planning
Background
- Traditional susceptibility assessments for ground deformation disasters heavily rely on knowledge-driven models and subjective expert judgments.
- This reliance can lead to inconsistencies and limitations in accuracy for complex urban environments.
Purpose Of The Study
- To explore the integration of data-driven models for evaluating urban ground collapse and subsidence susceptibility.
- To assess the feasibility of using advanced large language models (LLMs) like ChatGPT-4 to replace expert judgment in determining disaster weight factors.
- To develop a more objective and accurate susceptibility assessment framework for ground deformation.
Main Methods
- A representative study area (Hangzhou city) with specific geological characteristics (filled soil, silty sand) was selected.
- Nine relevant evaluation factors were identified, and a Random Forest-Backpropagation (RF-BP) neural network coupling model was employed for susceptibility mapping.
- ChatGPT-4 was utilized to determine the weights of evaluation factors, with its judgments validated against expert assessments using the Analytic Hierarchy Process (AHP).
Main Results
- The RF-BP neural network model demonstrated a 7% increase in Area Under the Curve (AUC) value compared to single models, indicating improved performance.
- Weights determined by ChatGPT-4 showed a minimal difference of only 3% compared to expert judgments, validating the LLM's reliability and logical consistency.
- The comprehensive susceptibility assessment using ChatGPT-4's weights yielded favorable and reliable outcomes.
Conclusions
- Integrating data-driven models, specifically the RF-BP neural network, enhances the accuracy of ground deformation susceptibility assessments.
- ChatGPT-4 offers a viable and reliable alternative to expert judgment for weight determination in disaster assessment, providing consistent and unbiased results.
- The proposed framework combining advanced AI models and LLMs presents a significant advancement in the objective and efficient assessment of urban ground deformation risks.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
GIS manipulation and analysis functions are vital for decision-making and planning. These activities range from data retrieval tasks, such as selecting information based on specific criteria, to advanced analytical techniques that address complex spatial problems.One critical GIS analysis method is overlaying, which combines multiple data layers to examine impacts. For example, overlaying a river-dammed lake boundary with road networks can identify affected infrastructure. Another common...
Flood risk assessment involves careful planning and analysis to ensure the safety of communities near water retention structures. Capacity contours are a vital tool in this process, as they illustrate the potential spread of water at specific levels in a given area. In the context of building a bund across a small valley, these contours play a critical role in evaluating the safety of nearby residential areas.In this example, the bund is intended to store stormwater in the valley. The engineers...
Geographic Information System (GIS) technology is essential for risk identification, action prioritization, and resource optimization in critical situations like flooding and earthquakes. By integrating spatial and demographic data, GIS provides a comprehensive framework for emergency response.GIS integrates data layers, like rainfall intensity, topography, elevation profiles, and river levels, to model high-risk flood zones. These layers assess areas susceptible to flooding based on their...
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...