Forecasting of future intermodal traffic demand is very important for decision making in ports operations management. The use accurate prediction tools an issue that awakens a lot interest among transport researchers. Intermodal freight forecasting plays role management and the planning principal port activities. Hence, study carried out under motivation knowing modeling flows could facilitate infrastructure optimize resources facilities. advanced models essential to improve level-service...

Predicting air quality is a very important task, as it known to have significant impact on health. The Bay of Algeciras (Spain) highly industrialised area with one the largest superports in Europe. During period 2017–2019, different data were recorded monitoring stations bay, forming database 131 variables (air pollutants, meteorological information, and vessel data), which predicted station using long short-term memory models. Four approaches been developed make SO2 NO2 forecasts 1 h 4...

In recent years, despite a decline in international trade and disruptions the supply chain caused by COVID-19, main container terminals Latin America Caribbean (LAC) have increased their volumes. This growth has necessitated significant adaptations seaports authorities to meet new demands. Consequently, there been focused analysis on performance, efficiency, competitiveness, particularly most relevant logistical aspects. this paper, multi-objective hybrid approach was employed. The Principal...

Abstract The main goal of this work is to obtain reliable predictions pollutant concentrations related maritime traffic (SO 2 , PM 10 NO X and NO) in the Bay Algeciras, located Andalusia, south Spain. Furthermore, objective predict future air quality levels principal traffic-related pollutants Algeciras as a function rest pollutants, meteorological variables, vessel data. In sense, three scenarios were analysed for comparison, namely Alcornocales Park cities La Línea Algeciras. A database...

In this work, different classification models were proposed to predict the pitting corrosion status of AISI 316 L stainless steel according environmental conditions and breakdown potential values. order study material, polarization tests undertaken in conditions: varying chloride ion concentration, pH temperature. Two techniques presented: k nearest neighbor (KNN) artificial neural networks (ANNs). The parameters for classifiers set based on a compromise between recall precision using...

Abstract The forecasting of the freight transportation, especially short‐term case, is an important topic in daily supply chain management. Intermodal transportation subject to multiple complex calendar effects arising port environment. use prediction methods provides information that may be helpful as a decision‐making tool management and planning operations processes ports. This work addresses problem on basis by novel two‐stage scheme combination offer reliable predictions fresh weight...

This study aims to produce accurate predictions of the NO2 concentrations at a specific station monitoring network located in Bay Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory (LSTMs) were used create forecasting models. Additionally, new prediction method was proposed combining LSTMs using rolling window scheme with cross-validation procedure for time series (LSTM-CVT). Two different strategies followed regarding input variables: from...

Predicting the levels of a pollutant in given area is an open problem, mainly because historical data are typically available at certain locations, where monitoring stations located, but not all locations area. This work presents approach based on developing predictions each points immission station available; this case, shallow Artificial Neural Networks, ANNs, and then using simple geostatistical interpolation algorithm (Inverse Distance Weighted, IDW), map constructed over entire study...

This study presents a methodology for determining port economic hinterlands through comprehensive logistics optimization. The research advances traditional geographical approaches by developing an integrated cost model that considers maritime transport, inland transportation, warehousing expenses, and time-dependent factors. Testing this on the Spanish system (with three main ports: Valencia, Algeciras, Barcelona), we demonstrate how product characteristics origins significantly influence...

Abstract Motivated to reduce the costs incurred by corrosion in material science, this article presents a combined model based on artificial neural networks (ANNs) predict pitting status of 316L austenitic stainless steel. This offers advantage automatically determining material. In work, was predicted, with environmental conditions considered, addition values breakdown potential estimated previously, but without having use polarization tests. The generalization ability verified evaluation...

The number of goods which passes through a border inspection post (BIP) may cause important congestion problems and delays in the port system, having an effect level service port. Therefore, prediction daily subject to BIPs seems be potential solution. This study proposes two-stage procedure better predict freight inspections. In first stage, Kohonen self-organising map (SOM) is employed decompose whole data into smaller regions display similar statistical characteristics. second support...

The breakdown potential is a crucial factor in the study of pitting corrosion resistance stainless steel. This work aims to demonstrate advantage different chemometric techniques estimate austenitic In order predict behaviour steel, total 60 samples this alloy were subjected electrochemical tests varying chloride ion concentration, pH and temperature. experimental values potential, addition tested environmental factors, used construct predictive models based on support vector machines...

The prediction of freight congestion (cargo peaks) is an important tool for decision making and it this paper’s main object study. Forecasting flows can be a useful the whole logistics chain. In work, complete methodology presented in order to obtain best model predict situations at ports. modeled as classification problem different approaches are tested (k-Nearest Neighbors, Bayes classifier Artificial Neural Networks). A panel experts (post–hoc methods Friedman test) has been developed...

Predictive numerical models in the study of ground-borne vibrations generated by railway systems have traditionally relied on subsystem partition approach (segmented). In such a method, loads are individually applied, and cumulative effect rolling stock is obtained through superposition. While this method serves to mitigate computational costs, it may not fully capture complex interactions involved vibrations—especially frequency domain. Recent advancements computation software enabled...

Hyperspectral technology has been playing a leading role in monitoring oil spills marine environments, which is an issue of international concern. In the case local areas, hyperspectral small dimensions ideal solution. This research explores use encoded signatures to develop automated classifiers capable discriminating between polluted and clean water distinguishing various types oil. The overall objective leverage these be able improve performance conventional systems that rely solely on...

Potentiodynamic polarisation tests have been widely used to evaluate pitting corrosion behaviour of stainless steels. This technique involves two principal steps: the interpretation curve and microscopic analysis material surface. Therefore, analysing influence all possible environmental conditions on can be complex. To deal with this problem, automatic models based Bayes classifier (BC) support vector machines (SVMs) techniques are presented in work. The variables involved corrosion:...