Weather Downtime Prediction in a South African Port Environment
Sea ports act as a gateway for a country’s imports and exports. Delays of vessels at the anchorage due to adverse weather events are becoming increasingly problematic. This paper investigates using weather data to accurately predict delays experienced by
- PDF / 3,746,056 Bytes
- 15 Pages / 439.37 x 666.142 pts Page_size
- 7 Downloads / 197 Views
3
Department of Industrial and Systems Engineering, University of Pretoria, Pretoria, South Africa [email protected] 2 Department of Industrial Engineering, Stellenbosch University, Stellenbosch, South Africa [email protected] School of Information and Communication Technology, Griffith University, Southport, Australia [email protected]
Abstract. Sea ports act as a gateway for a country’s imports and exports. Delays of vessels at the anchorage due to adverse weather events are becoming increasingly problematic. This paper investigates using weather data to accurately predict delays experienced by ships at the port anchorage by means of both regression (delay duration) and classification (delay impact). The data sets consist of five years of weather information and vessel weather delay data obtained for a South African port. The weather information consist of three data sources, including rainfall, wind and wave data. An artificial neural network was found to perform the best in the prediction of vessel weather delay duration for both three day and weekly data sets and a random forest performed the best in predicting likelihood of weekly vessel weather delays. Keywords: Machine learning environment
1
· Downtime prediction · Port
Introduction
The World Economic Forum (WEF) Global Risk Report of 2018 ranked extreme weather events (sea level rise, strong winds, storms, floods, extreme heat, extreme cold, and drought) and climate change related risks among the top global risks in the world in terms of likelihood and consequence over the next ten year horizon [8]. These changes in climate are expected to manifest in increased frequency and severity of extreme weather events [26]. Southern African regions are expected to become drier and hotter in future [26]. It is important to quantify the impact of extreme weather conditions to preempt the impact of the extremes and to plan effectively [26]. The ability to predict weather delays in the port environment will have both direct and indirect benefits to the sea port. The direct benefits include improved planning activities, such as better allocation of berth slots and resources c Springer Nature Switzerland AG 2020 M. Bramer and R. Ellis (Eds.): SGAI-AI 2020, LNAI 12498, pp. 241–255, 2020. https://doi.org/10.1007/978-3-030-63799-6_19
242
N. C. Musisinyani et al.
due to reduced uncertainties, and the indirect benefit will be the increased competitive edge that can be realized by providing more reliable services to the carriers. Many studies have been conducted for estimated time of arrival (ETA) from one port to another, however, there are limited studies on vessel delays in the port due to adverse weather. From the literature, wave height and wind speed are the most common weather data for sea port and terminal research. However, other weather variables such as precipitation, sea level pressure, visibility and temperature have also been used. Various simulation, optimisation, and machine learning techniques have been used for prediction of ETA for rail,
Data Loading...
