Improvement of Deep Learning Models for River Water Level Prediction Using Complex Network Method

Kim, Yejin; Han, Heechan; Wang, Wonjoon; Kim, Hung Soo

doi:10.3390/w14030466

Cited by 14 publications

(10 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Long short-term memory (LSTM), developed by ameliorating the disadvantages of recurrent neural networks (RNNs), removes unnecessary memories by adding input gates (i t ), forget gates ( f t ), and output gates (o t ) to memory cells in the hidden layer [21,[23][24][25], erasing and deciding what to remember. These three gates have a sigmoid function in common.…”

Section: Long Short-term Memorymentioning

confidence: 99%

A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station

Kim,

Choi,

Kang

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

Drought has significant impacts on both society and the environment, but it is a gradual and comprehensive process that affects a region over time. Therefore, non-structural measures are necessary to prepare and respond to the damage caused by drought in a flexible manner according to the stage of drought. In this study, an AI-based water demand prediction model was developed using deep neural network (DNN) and long short-term memory (LSTM) models. The model was trained from 2004 to 2015 and verified from 2016 to 2021. Model accuracy was evaluated using data, with the LSTM model achieving a correlation coefficient (CC) of 0.95 and normalized root mean square error (NRMSE) of 8.38, indicating excellent performance. The probability of the random variable X falling within the interval [a,b], as described by the probability density function f(x), was calculated using the water demand data. The cumulative distribution function was used to calculate the probability of the random variable being less than or equal to a specific value. These calculations were used to establish the criteria for each stage of the crisis alert system. Decision tree (DT) and random forest (RF) models, based on AI-based classification, were used to predict water demand at the Gurye intake station. The models took into account the impact of water demand from the previous day, as well as the effects of rainfall, maximum temperature, and average temperature. Daily water demand data from the Gurye intake station and the previous day’s rainfall, maximum temperature, and average temperature data from a nearby observatory were collected from 2004 to 2021. The models were trained on data from 2004 to 2015 and validated on data from 2016 to 2021. Model accuracy was evaluated using the F1-score, with the random forest model achieving a score of 0.88, indicating excellent performance.

show abstract

Section: Long Short-term Memorymentioning

confidence: 99%

A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station

Kim,

Choi,

Kang

et al. 2023

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…If all data from neighboring stations are used without classification, unnecessary data for model learning can lead to the distortion of predictions. [51].…”

Section: Calculation Of Centrality For Cai Stationsmentioning

confidence: 99%

Application of Deep Learning Models and Network Method for Comprehensive Air-Quality Index Prediction

et al. 2022

Self Cite

View full text Add to dashboard Cite

Accurate pollutant prediction is essential in fields such as meteorology, meteorological disasters, and climate change studies. In this study, long short-term memory (LSTM) and deep neural network (DNN) models were applied to six pollutants and comprehensive air-quality index (CAI) predictions from 2015 to 2020 in Korea. In addition, we used the network method to find the best data sources that provide factors affecting comprehensive air-quality index behaviors. This study had two steps: (1) predicting the six pollutants, including fine dust (PM10), fine particulate matter (PM2.5), ozone (O3), sulfurous acid gas (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO) using the LSTM model; (2) forecasting the CAI using the six predicted pollutants in the first step as predictors of DNNs. The predictive ability of each model for the six pollutants and CAI prediction was evaluated by comparing it with the observed air-quality data. This study showed that combining a DNN model with the network method provided a high predictive power, and this combination could be a remarkable strength in CAI prediction. As the need for disaster management increases, it is anticipated that the LSTM and DNN models with the network method have ample potential to track the dynamics of air pollution behaviors.

show abstract

“…구조적 대책의 경우 공학적인 기술을 이용하여 재난위험 지역에 구조물 혹은 시설물을 설치하거나 재난에 노출된 건물을 보강 및 개선하는 방법으로 재난으로 인한 위험(risk)을 낮추 고 수용력(capacity)을 높이는 것이다. 그러나, 자연보전 및 생태 경관 보전 등 생태적 가치가 중요하게 여겨지면서 시행에 어려움을 겪고 있다 (Kang et al, 2007;Kim et al, 2007;Kim, Han et al, 2022). 또한, 구조적 대책은 집중호우로 인해 설계 빈도를 초과하는 재난이 발생하면 줄이지 못하는 문제점과 비구조적 대책보다 상대적으로 비용과 시간이 많이 소요된다 .…”

Section: 서 론unclassified

“…기존의 인공신경망 모형은 데이터의 양이 많아질수록 과적합이나, 예측 성능에 한계가 있었다. 그러나 심층 신경망은 이러한 단점을 보완하고 자료의 양이 많아질수록 성능이 선형적으로 증가하는 장점이 있다 (Kim, Han et al, 2022;Fig. 3).…”

Section: 심층 신경망unclassified

Development of the Method for Flood Water Level Forecasting and Flood Damage Warning Using an AI-based Model

Kim¹,

Lee²,

Hwang-Bo³

et al. 2022

J. Korean Soc. Hazard Mitig

Self Cite

View full text Add to dashboard Cite

This study reviewed the applicability of AI-based models to predict flood water level and evaluate flood damage in small rivers with short arrival times. The Namyangju-si (Jingwan Bridge) watershed, where the most flood warnings have occurred, was selected as the target of study. Rainfall and water level data from 2008 to 2020 were collected for the watershed. A total of 40 rainfall events were identified when the water level was 1m or higher from June to September, corresponding to the flood season. Additionally, flood water level forecasting was performed using AI-based models such as deep neural network (DNN), long short term memory (LSTM), and storage function models. Predictive power evaluation revealed the DNN model displayed the lowest normalized root mean square error (NRMSE) with a value of 0.06. This study concludes that there are issues with the existing flood warning and heavy rain warning standards due to rainfall variability, correlation with the occurrence of damage caused by heavy rain, and the application of consistent standards nationwide. To solve this issue, the cause of flood damage was classified and the risk assessment criteria established by linking the water level and rainfall data. To develop an optimal flood damage classification prediction model based on the established criteria, two models were applied: XGBoost and random forest model. Evaluation of model predictive power revealed the F1-score for XGBoost was 0.92, indicating excellent predictive power. Based on the models presented herein, the flood damage assessment technique using the results of flood prediction can be used as basic data for disaster managers’ decision-making.

show abstract

Improvement of Deep Learning Models for River Water Level Prediction Using Complex Network Method

Cited by 14 publications

References 41 publications

A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station

A Study on Developing an AI-Based Water Demand Prediction and Classification Model for Gurye Intake Station

Application of Deep Learning Models and Network Method for Comprehensive Air-Quality Index Prediction

Development of the Method for Flood Water Level Forecasting and Flood Damage Warning Using an AI-based Model

Contact Info

Product

Resources

About