Analysis of Ground Subsidence Vulnerability in Urban Areas Using Spatial Regression Analysis

Article Chemistry, Multidisciplinary

Prediction Modeling of Ground Subsidence Risk Based on Machine Learning Using the Attribute Information of Underground Utilities in Urban Areas in Korea

Sungyeol Lee et al.

Summary: This study collected attribute information and historical ground subsidence information of six types of underground utility lines, and developed a ground subsidence risk prediction model based on machine learning to predict and prepare for ground subsidence accidents caused by damage to underground utilities in urban areas. The density was identified as the most important influencing factor in the model, and a risk map of ground subsidence in the target area was created, showing the predicted risk levels in the concentrated subsidence areas.

APPLIED SCIENCES-BASEL (2023)

Add to Collection

Review Mathematics

Mitigating the Multicollinearity Problem and Its Machine Learning Approach: A Review

Jireh Yi-Le Chan et al.

Summary: Technological advancements have facilitated the collection of big data in various fields, leading to an increase in variables and data points. However, this also introduces the problem of multicollinearity, which can be mitigated through variable selection methods and modified estimator methods. Recent studies suggest that optimization approaches using machine learning may handle multicollinearity better than traditional statistical estimators.

MATHEMATICS (2022)

Add to Collection

Article Environmental Sciences

How does new-type urbanization affect air pollution? Empirical evidence based on spatial spillover effect and spatial Durbin model

Chang Zhao et al.

Summary: This study explores the impact of new-type urbanization on air pollution through empirical research and the construction of a comprehensive evaluation index system. The results demonstrate that new-type urbanization significantly reduces air pollution, with important transmission mechanisms including industrial structure optimization, technological innovation, and energy structure adjustment. However, policy implementation deviations may weaken the emission reduction effect of new-type urbanization, and the impact varies across different regions.

ENVIRONMENT INTERNATIONAL (2022)

Add to Collection

Article Environmental Studies

Delineating the spatial-temporal variation of air pollution with urbanization in the Belt and Road Initiative area

Guoen Wei et al.

Summary: The study found that in the BRI region, PM2.5 concentrations are influenced by urbanization, showing spatial autocorrelation and differentiation, mainly in emerging developing regions such as China and India. Energy pollution emissions, economic activities, and human activities are the three main factors affecting PM2.5 accumulation. Proposed urban strategies and governance actions aim to coordinate the relationship between urban construction and atmospheric environmental protection.

ENVIRONMENTAL IMPACT ASSESSMENT REVIEW (2021)

Add to Collection

Article Environmental Sciences

Spatial Regression Modeling Approach for Assessing the Spatial Variation of Air Pollutants

Seunghoon Park et al.

Summary: The study found that socioeconomic characteristics had no significant impact on air pollution, while the built environment characteristics had varied effects on different types of pollutants. PM2.5 was more influenced by the built environment, and concentrations of different pollutants varied in different neighborhood environments.

ATMOSPHERE (2021)

Add to Collection

Article Economics

Interdependency Pattern Recognition in Econometrics: A Penalized Regularization Antidote

Kimon Ntotsis et al.

Summary: This study proposes and investigates a robust and easily interpretable methodology called Elastic Information Criterion, which accurately captures multicollinearity and provides a proper model assessment. Performance evaluation is done using simulated and real data.

ECONOMETRICS (2021)

Add to Collection

Article Environmental Sciences