Development of a Heavy Rain Damage Prediction Function by Risk Classification

Prediction models of heavy rain damage using machine learning based on big data were developed for the Seoul Capital Area in the Republic of Korea. We used data on the occurrence of heavy rain damage from 1994 to 2015 as dependent variables and weather big data as explanatory variables. The model was developed by applying machine learning techniques such as decision trees, bagging, random forests, and boosting. As a result of evaluating the prediction performance of each model, the AUC value of the boosting model using meteorological data from the past 1 to 4 days was the highest at 95.87% and was selected as the final model. By using the prediction model developed in this study to predict the occurrence of heavy rain damage for each administrative region, we can greatly reduce the damage through proactive disaster management.

Download Full-text

Development of Combined Heavy Rain Damage Prediction Models with Machine Learning

Water ◽

10.3390/w11122516 ◽

2019 ◽

Vol 11 (12) ◽

pp. 2516 ◽

Cited By ~ 1

Author(s):

Changhyun Choi ◽

Jeonghwan Kim ◽

Jungwook Kim ◽

Hung Soo Kim

Keyword(s):

Machine Learning ◽

Linear Regression ◽

Prediction Model ◽

Prediction Models ◽

Predictive Performance ◽

Heavy Rain ◽

Learning Models ◽

Damage Prediction ◽

Natural Disaster Management ◽

Machine Learning Models

Adequate forecasting and preparation for heavy rain can minimize life and property damage. Some studies have been conducted on the heavy rain damage prediction model (HDPM), however, most of their models are limited to the linear regression model that simply explains the linear relation between rainfall data and damage. This study develops the combined heavy rain damage prediction model (CHDPM) where the residual prediction model (RPM) is added to the HDPM. The predictive performance of the CHDPM is analyzed to be 4–14% higher than that of HDPM. Through this, we confirmed that the predictive performance of the model is improved by combining the RPM of the machine learning models to complement the linearity of the HDPM. The results of this study can be used as basic data beneficial for natural disaster management.

Download Full-text

Heavy Rain Damage Prediction Considering Regional Disaster Prevention Budget

Korean Society of Hazard Mitigation ◽

10.9798/kosham.2019.19.6.207 ◽

2019 ◽

Vol 19 (6) ◽

pp. 207-214 ◽

Cited By ~ 1

Author(s):

Junhyeong Lee ◽

Jongsung Kim ◽

Donghyun Kim ◽

Taewoo Lee ◽

Hung Soo Kim

Keyword(s):

Heavy Rain ◽

Disaster Prevention ◽

Damage Prediction

Download Full-text

Making Evacuation Routine Behavior: Impact of Experiencing Severe Flood Damage on Recognition and Advance Evacuation Behavior

Journal of Disaster Research ◽

10.20965/jdr.2021.p0250 ◽

2021 ◽

Vol 16 (2) ◽

pp. 250-262

Author(s):

Masato Tanaka ◽

◽

Minori Shimomura

Keyword(s):

Heavy Rain ◽

Disaster Risk ◽

Flood Damage ◽

Risk Recognition ◽

Damage Prediction ◽

Disaster Victims ◽

Damage Recognition ◽

Evacuation Behavior ◽

The Difference ◽

The Impact

This study analyzes the impact of experiencing a disaster on subsequent risk recognition and evacuation behavior using data collated from the interview of victims of the flood and landslides that followed the 2014 Hiroshima Heavy Rain Disaster. The high accuracy of the storm and flood damage prediction system has made it possible to limit human casualties by routinizing advance evacuation behavior. The study explores conditions for the routinization of evacuation behavior and its findings are as follows: (i) a series of experiences such as timing of incidental awareness, evacuation, housing damage, and human damage define the damage recognition of each victim. The difference between each damage recognition has different influences on their post-disaster risk recognition and behaviors; (ii) experiencing severe disasters generally enhances disaster risk recognition. However, whether it promotes advanced evacuation behavior is dependent on the magnitude of the damage and pre-disaster risk recognition. If risk recognition is ambiguous, the effect of the experience is minimal even if the damage is severe; (iii) for disaster victims to inculcate an evacuation behavior in preparation for the next disaster, they must first have clear pre-disaster risk recognition mechanisms. It is also necessary to have a reliable destination that is incorporated into the daily life of the residents, which can serve as an evacuation site.

Download Full-text

SEISMIC DAMAGE PREDICTION FOR JAPANESE-STYLE WOODEN HOUSE IN THE 2016 KUMAMOTO EARTHQUAKE

Proceedings of International Structural Engineering and Construction ◽

10.14455/isec.res.2018.125 ◽

2018 ◽

Vol 5 (2) ◽

Author(s):

Tomiya Takatani ◽

Hayato Nishikawa

Keyword(s):

Process Analysis ◽

Ground Surface ◽

Seismic Damage ◽

2016 Kumamoto Earthquake ◽

Damage Prediction ◽

Kumamoto Earthquake ◽

Seismic Fault ◽

Prediction Function ◽

The 2016 Kumamoto Earthquake ◽

Wooden House

Thousands of wooden houses were destroyed by the 2016 Kumamoto Earthquake. A seismic damage prediction function for wooden houses taking into consideration the consecutive strong earthquake motions, the amplification effect of ground surface layer, and the rupture propagation effect of seismic fault was proposed in this paper. Relationship between three ground characteristics above mentioned and the seismic damage for wooden house in the 2016 Kumamoto earthquake was analytically investigated by 3-D collapsing process analysis. The maximum drift angle was evaluated in this collapsing analysis of two-story wooden house.

Download Full-text