An Optimal Model based on Multifactors for Container Throughput Forecasting

Shuang Tang,Sudong Xu,Jianwen Gao 대한토목학회 2019 KSCE JOURNAL OF CIVIL ENGINEERING Vol.23 No.9

Containerization plays an important role in international trade. Container throughput is a key indicator to measure the development level of a port. In this paper, Lianyungang Port and Shanghai Port are chosen to study the method for container throughput forecasting. Gray model, triple exponential smoothing model, multiple linear regression model, and backpropagation neural network model are established. Five factors are selected as influential factors. They are total retail sales of consumer goods, gross domestic product of the local city, import and export trade volume, total output value of the second industry and total fixed assets investment. The growth and the raw datasets are used in the prediction, respectively. The datasets from 1990 to 2011 are chosen to build models and the ones from 2012 to 2017 are used to assess the performance of the models. By comparison, the backpropagation neural network model is applicable to both Shanghai Port and Lianyungang Port for container throughput forecasting. The volume of container throughput at both ports from 2018 to 2020 is predicted.

A Comparison of Traditional and Neural Networks Forecasting Techniques for Container Throughput at Bangkok Port

Veerachai GOSASANG,Watcharavee CHANDRAPRAKAIKUL,Supaporn KIATTISIN 한국해운물류학회 2011 The Asian journal of shipping and Logistics Vol.27 No.3

However, forecasts of container throughput growth and development of Bangkok Port, the significant port of Thailand, have been scant and the findings are divergence. Moreover, the existing literature emphasizes only two forecasting methods, namely time series and regression analysis. The aim of this paper is to explore Multilayer Perceptron (MLP) and Linear Regression for predicting future container throughput at Bangkok Port. Factors affecting cargo throughput at Bangkok Port were identified and then collected from Bank of Thailand, Office of the National Economic and Social Development Board, World Bank, Ministry of Interior, and Energy Policy and Planning Office. These factors were entered into MLP and Linear Regression forecasting models that generated a projection of cargo throughput. Subsequently, the results were measured by root mean squared error (RMSE) and mean absolute error (MAE). Based on the results, this research provides the best application of forecasting technique which is Neural Network – Multilayer Perceptron technique for predicting container throughput at Bangkok Port.

A study on forecasting model of container cargo throughput of Vietnam's seaport

Tan Vinh Nguyen,Hoang Phuong Nguyen 국제이네비해양경제학회 2020 International Journal of e-Navigation and Maritime Vol.14 No.1

Seaports play a huge role in Vietnam's economy, being a border gate for economic and cultural exchanges with outsiders, especially the role of goods circulation. Container cargoes are one of the types of goods with large and increasing volume through Vietnam seaports. However, the heterogeneity between the seaport and the connected infrastructure greatly affects the capacity and efficiency of port investment. This is also one of the main causes leading to a shortage of goods, excess ports in some port areas. The root cause is that the planning has not kept up with the growth of the amount of goods arriving at the port, because the issue of forecasting the volume of goods through the port is not accurate. Therefore, it is necessary to develop models of forecasting container cargo through the ports with general, scientific, and high accuracy to serve the strategy, planning and development of seaport system; the work of planning and investment in the development of seaports, shipping fleets and other auxiliary transport infrastructure works. The purpose of this study is to build suitable forecasting models with high accuracy and reliability on the total volume of container cargo throughput of the Vietnamese seaport system. Based on the methods of a statistical survey, synthesis, regression analysis, and correlation to evaluate the influence of factors on container cargo volume through Vietnam's seaports in the period of 2004-2019. By incorporating more economic factors into the regression model, the paper focuses on forecasting container cargo through the Vietnamese seaport systems, going into cargo-based forecasting in tons and TEUs. The results of this study contribute to complete the rationale for forecasting, especially forecasts related to the shipping industry and the forecast for container cargo throughput of the seaport. Finally, selecting models for forecasting container cargo volume throughput of seaports by Vietnamese conditions.

Prophet 모형을 활용한 국내 중소형 컨테이너항만 물동량 예측에 관한연구: 인천, 평택・당진, 울산항을 중심으로

김준기,류동근,남형식 인문사회 21 2022 인문사회 21 Vol.13 No.1

A Study on Forecasting of Small & Medium Sized Container Port Throughput in South Korea Using Prophet Model:Focused on Incheon, Pyeongtaek-Dangjin and Ulsan PortJunki Kim, Dongkeun Ryoo, & Hyungsik Nam Abstract: The container throughout handled by a port authority is still a relevant KPI to measure the efficiency and commercial success of ports worldwide. This study aims to predict the container throughput for the ports of Incheon, Pyeongtaek-Dangjin, and Ulsan ports in the Republic Of Korea. A mix of models including Prophet, LSTM, and SARIMA are used to forecast container volumes. After training the model with data from January 2001 to June 2016 of the target port, the container throughput from July 2016 to June 2021 was predicted, and the performance of the model was verified by comparing it with the actual volume. The findings show that when the throughput data yields seasonality, the Prophet model is effective in considering the ease of implementation and the operation time. Second, the study highlights the effectiveness to use jointly the Prophet and LSTM models when there is no clear indication of seasonality in the throughput dataset. Key Words: Container Port, Throughput Forecasting, Prophet, LSTM, SARIMA Prophet 모형을 활용한 국내 중소형 컨테이너항만 물동량 예측에 관한연구: 인천, 평택・당진, 울산항을 중심으로김 준 기*ㆍ류 동 근**ㆍ남 형 식*** 요약: 기존 항만물동량 예측 관련 연구의 주된 대상은 부산항 또는 국내 전체 항만이었고, 중소형 항만을 대상으로 한 연구는 활발히 이뤄지지 않았다. 본 연구는 Prophet, LSTM, SARIMA 모형을 사용하여 국내 중소형 컨테이너 항만 중 인천, 평택・당진, 울산항을 대상으로 물동량을 예측하였다. 대상 항만의 2001년 1월~2016년 6월의 자료로 모형을 학습시킨 뒤, 2016년 7월~2021년 6월까지의 물동량을 예측했고, 이를 실제 물동량과 비교하여 모형의 성능을 검증했다. 분석 결과, 첫째, 물동량 자료에 계절성이 나타나는 경우, 구현의 용이성과 연산시간을 고려하였을 때, Prophet 모형이 효과적임을 확인하였다. 둘째, 물동량 자료에 뚜렷한 계절성이 나타나지 않는 경우, Prophet 모형과 LSTM 모형을 함께 활용하는 것이 효과적임을 확인하였다. 핵심어: 컨테이너항만, 물동량 예측, Prophet, LSTM, SARIMA □ 접수일: 2022년 1월 12일, 수정일: 2022년 1월 28일, 게재확정일: 2022년 2월 20일* 주저자, 한국해양대학교 해운경영학과 석사과정(First Author, Master’s Course, Korea Maritime & Ocean Univ., Email: jkkim@g.kmou.ac.kr)** 공동저자, 한국해양대학교 교수(Co-author, Professor, Korea Maritime & Ocean Univ., Email: dkryoo@kmou.ac.kr)*** 교신저자, 한국해양대학교 물류・환경・도시인프라공학부(물류시스템공학전공) 교수(Corresponding Author, Professor, Korea Maritime & Ocean Univ., Email: hsnam@kmou.ac.kr)

An Application of Genetic Programming in Nonlinear Combining Forecasting

Yingxiao Zhou,Peng Zhao 보안공학연구지원센터 2016 International Journal of Hybrid Information Techno Vol.9 No.6

It has been deemed as an effective tool of forecasting performance improvement to combine different component forecasting models. However, current nonlinear combining models are not able to meet the requirement of high forecasting accuracy in practice. To tackle this challenge, this paper constructs a hybrid, named genetic programming and least squared estimation based nonlinear combining method (GPLSE-NC), of a standard genetic programming (GP) algorithm and the least square estimation (LSE) method, based on which a new nonlinear combined forecasting model is proposed. To verify the feasibility of the proposed model, based on the container throughput data of Shanghai Port from January 2004 to November 2015, 4 different forecasting models are constructed and compared with the proposed GPLSE-NC combining model in terms of three forecasting performance evaluation criteria. The empirical results show significant superiority of the GPLSE-NC model over its rivals, which reveals that the proposed model has a great potential to be a powerful nonlinearly combine forecasting approach.

Forecasting the Busan Container Volume Using XGBoost Approach based on Machine Learning Model

웬티프엉타인,조규성 한국사물인터넷학회 2024 한국사물인터넷학회 논문지 Vol.10 No.1

Container volume is a very important factor in accurate evaluation of port performance, and accurate prediction of effective port development and operation strategies is essential. However, it is difficult to improve the accuracy of container volume prediction due to rapid changes in the marine industry. To solve this problem, it is necessary to analyze the impact on port performance using the Internet of Things (IoT) and apply it to improve the competitiveness and efficiency of Busan Port. Therefore, this study aims to develop a prediction model for predicting the future container volume of Busan Port, and through this, focuses on improving port productivity and making improved decision-making by port management agencies. In order to predict port container volume, this study introduced the Extreme Gradient Boosting (XGBoost) technique of a machine learning model. XGBoost stands out of its higher accuracy, faster learning and prediction than other algorithms, preventing overfitting, along with providing Feature Importance. Especially, XGBoost can be used directly for regression predictive modelling, which helps improve the accuracy of the volume prediction model presented in previous studies. Through this, this study can accurately and reliably predict container volume by the proposed method with a 4.3% MAPE (Mean absolute percentage error) value, highlighting its high forecasting accuracy. It is believed that the accuracy of Busan container volume can be increased through the methodology presented in this study.

SARIMAX 모형을 이용한 부산항 컨테이너 물동량 예측

이근철,이희정,구훈영 한국경영과학회 2023 經營 科學 Vol.40 No.2

In this study, we consider the problem of forecasting monthly container throughput of Busan port, the largest port in South Korea. We proposed a forecasting model based on SARIMAX (Seasonal AutoRegressive Integrated Moving Average with eXogenous variables), a well-known traditional time-series model in which an appropriate exogenous variable is embedded to take into consideration the effect of COVID-19 during the pandemic era. The orders of the various terms included in the SARIMAX model were determined through the Box-Jenkins based approach, and the impact of COVID-19 was quantified by incorporating the number of the US cases as the exogenous variable. The 24 months spanning 2021 and 2022 were predicted using the proposed SARIMAX model, and the forecast results were compared with those of other existing prediction methods. The results showed that the SARIMAX model had the best predictive performance in terms of MAPE and RMSE among the tested methods.

A Comparative Study of Multivariate Forecasting Models for Container Throughput

Awah, P. C.,Mabika, C. A.,Hwayoung Kim 국제이네비해양경제학회 2024 International Journal of e-Navigation and Maritime Vol.22 No.-

승법계절 ARIMA 모형에 의한 부산항 컨테이너 물동량 추정과 예측

이재득(Ghae-Deug Yi) 한국항만경제학회 2013 韓國港灣經濟學會誌 Vol.29 No.3

본 연구는 1992년부터 2011년까지 월별자료를 사용하여 여러 가지 시계열 추정모델과 승법 계절 ARIMA 모형을 설정하여 부산항의 컨테이너 물동량을 추정하고 예측하였다. 여러 가지 모델로 추정한 결과 부산항의 컨테이너 물동량과 물동량 변동 모두 계절을 승법한 ARIMA 모델 (1,0,1)X(1,0,1) 12로 추정하였을 때, 추정결과와 Akaike information, Schwarz, Hannan-Quin 기준 등으로 보아, 가장 좋은 ARIMA 추정과 예측 모형으로 나타났다. 그리하여 부산항 물동량 추정의 최적모형인 ARIMA (1,0,1)X(1,0,1) 12 모형에 의해 향후 8년간 96개월에 대한 부산항 물동량 미래 예측치(2013-2020년)를 월별로 추정하여 예측한 결과 2013년부터 부산의 물동량은 연도별로 조금씩 지속적으로 증가하는 추세를 보일 것으로 나타났다. ARIMA (1,0,1)X(1,0,1) 12 모형에 의한 부산항의 컨테이너 물동량의 연도별 예측량은 2013년 1천 891만 TEU, 2014년 2천 34만 TEU, 2015년 2천 188만 TEU, 2016년 2천 353만 TEU, 2017년 2천 531만 TEU, 2018년 2천 722만 TEU 그리고 2020년 3천 148만 TEU등으로 나타났다. This paper estimates and forecasts the container throughput of Busan port using the monthly data for years 1992-2011. To do this, this paper uses the several seasonal multiplicative ARIMA models. Among several ARIMA models, the seasonal multiplicative ARIMA model (1,0,1)X(1,0,1) 12 is selected as the best model by AIC, SC and Hannan-Quin information criteria. According to the forecasting values of the selected seasonal multiplicative ARIMA model (1,0,1)X(1,0,1) 12, the container throughput of Busan port for 2013-2020 will increase steadily annually, but there will be some volatile variations monthly due to the seasonality and other factors. Thus, to forecast the future container throughput of Busan port and to develop the Busan port efficiently, we need to use and analyze the seasonal multiplicative ARIMA model (1,0,1)X(1,0,1) 12.