Theoretical foundations and applied instruments to develop a system for intelligent fleet planning and decision support in the Arctic shipping
项目来源
项目主持人
项目受资助机构
立项年度
立项时间
项目编号
项目级别
研究期限
受资助金额
学科
学科代码
基金类别
参与者
参与机构
One of these scientific problems is the intellectual planning of the Arctic fleet operation at tactical level,as well as modeling its development over a long-term strategic horizon.It is no longer possible to plan an ever-increasing number of ships based on simple expert-analytical methods.The ongoing digitalization and computerization of this sphere require the development of specialized and science-based solutions.Indeed,the traffic of the Northern Sea Route(NSR),which in 2010 was about 8 MTPA(Million tons per annum),in 2020 increased to 33 MTPA,and by 2030 must reach enormous 160 MTPA.The number of large ice-going transport vessels will have to increase from the current 50 to about 200-250 ships.Therefore,the task of intelligent planning of the joint operation of ships and icebreakers is becoming one of the most urgent scientific problems.
An illustration of the practical significance of this research field is that,starting from 2017-2019,all the largest companies that operate the Arctic fleet began to create their own situation centers designed to monitor and plan the operation of ships.However,IT specialists that work on the creation of such centers are aimed mainly at developing a software infrastructure in the field of monitoring and management control.Therefore,these projects hardly ever have a research component aimed at solving the scientific problem described above.For this reason,Russia is experiencing an acute shortage of applied scientific research focused on the creation of new intelligent solutions and means of information support and planning of Arctic shipping.
Within the framework of this project,we will develop a set of new models and solve a number of scientific problems related to various subject areas and aimed at the intellectualization of the Arctic shipping,namely:
• application of combinatorial optimization methods in the tasks of Arctic fleet planning,
• stochastic spatiotemporal modeling of the dynamics of ice conditions and its application to increase the spatiotemporal resolution of deterministic climate models,
• creation of models for predicting the operation parameters of ships and caravans in ice based on analytical approaches and artificial intelligence methods,
• development of methods for direct optimization design of ice-going ships to ensure the versatility and efficiency of design solutions,
• creation of new methods for simultaneous optimization of the speed and trajectory of the vessel in ice under the uncertainty of ice parameters.
The scientific novelty of the project is due to the combination of these areas to solve the described interdisciplinary scientific problem.Theoretical and applied solutions that will be obtained within the framework of the proposed project are of a great practical value and can be implemented in the form of specialized services integrated into digital platforms for intelligent support of Arctic shipping.
Expected results:The project will result in new scientific and methodological solutions in the field of intelligent planning of Arctic fleet operation:
1.To solve the problem of a joined planning of ships and icebreakers,we will apply combinatorial optimization methods on the graph and take into account the multiple types of ships,as well as their different propulsion performance.The solutions obtained are supposed to be further used as the basis for specialized digital services that can be applied in practical tasks.
2.We will use the approaches of scenario-based stochastic spatiotemporal modeling of local ice parameters to predict the future navigational ice conditions and form typified ice maps.This task is necessary to form the scenarios of changes in the navigational ice situation in the Arctic on the horizon up to 2050,which has a direct impact on the required number of icebreakers and transport ships.
З.The project involves the creation and validation of the models to predict parameters of ship and caravan operation in ice based on the results of experiments in the ice basin,as well as the artificial intelligence methods.The importance of this problem is due to the fact that all the practical results of the Arctic fleet modeling and planning are directly related to the accuracy and adequacy of the models of ship operation in changing ice conditions.The results of work in this area are expected to be used in various scientific and practical studies on the modeling of Arctic marine transport systems.
4.In order to improve the quality of the initial design of Arctic ships and increase their energy efficiency,the we plan to develop methods for the optimization ship design analysis and create new algorithmic solutions to implement shipbuilding CAD systems of a conceptual type.The results of solving this problem will form the basis for practical solutions that are relevant for Russian shipbuilding design bureaus.
5.Within the framework of the project,we will pay special attention to the development of new methods of ice routing and improvement of previously developed solutions.The work will be carried out taking into account the experience of the authors in industrial projects.In particular,we will propose solutions for the problem of joined optimization of the trajectory and speed of the vessel on each segment.It is planned to carry out a comprehensive validation of the obtained solutions based on the full-scale data.
The described results correspond to the advanced world level of research in this area,and in terms of the practical component are many times greater than similar foreign developments.This is due to the fact that at present Russia is the only country that has practical experience in Arctic shipping and actively develops the solutions in the field of its intellectualization.Access to up-to-date data will be provided due to the involvement of our scientific team in industrial projects.
One of these scientific problems is the intellectual planning of the Arctic fleet operation at tactical level,as well as modeling its development over a long-term strategic horizon.It is no longer possible to plan an ever-increasing number of ships based on simple expert-analytical methods.The ongoing digitalization and computerization of this sphere require the development of specialized and science-based solutions.Indeed,the traffic of the Northern Sea Route(NSR),which in 2010 was about 8 MTPA(Million tons per annum),in 2020 increased to 33 MTPA,and by 2030 must reach enormous 160 MTPA.The number of large ice-going transport vessels will have to increase from the current 50 to about 200-250 ships.Therefore,the task of intelligent planning of the joint operation of ships and icebreakers is becoming one of the most urgent scientific problems.
An illustration of the practical significance of this research field is that,starting from 2017-2019,all the largest companies that operate the Arctic fleet began to create their own situation centers designed to monitor and plan the operation of ships.However,IT specialists that work on the creation of such centers are aimed mainly at developing a software infrastructure in the field of monitoring and management control.Therefore,these projects hardly ever have a research component aimed at solving the scientific problem described above.For this reason,Russia is experiencing an acute shortage of applied scientific research focused on the creation of new intelligent solutions and means of information support and planning of Arctic shipping.
Within the framework of this project,we will develop a set of new models and solve a number of scientific problems related to various subject areas and aimed at the intellectualization of the Arctic shipping,namely:
• application of combinatorial optimization methods in the tasks of Arctic fleet planning,
• stochastic spatiotemporal modeling of the dynamics of ice conditions and its application to increase the spatiotemporal resolution of deterministic climate models,
• creation of models for predicting the operation parameters of ships and caravans in ice based on analytical approaches and artificial intelligence methods,
• development of methods for direct optimization design of ice-going ships to ensure the versatility and efficiency of design solutions,
• creation of new methods for simultaneous optimization of the speed and trajectory of the vessel in ice under the uncertainty of ice parameters.
The scientific novelty of the project is due to the combination of these areas to solve the described interdisciplinary scientific problem.Theoretical and applied solutions that will be obtained within the framework of the proposed project are of a great practical value and can be implemented in the form of specialized services integrated into digital platforms for intelligent support of Arctic shipping.
Expected results:The project will result in new scientific and methodological solutions in the field of intelligent planning of Arctic fleet operation:
1.To solve the problem of a joined planning of ships and icebreakers,we will apply combinatorial optimization methods on the graph and take into account the multiple types of ships,as well as their different propulsion performance.The solutions obtained are supposed to be further used as the basis for specialized digital services that can be applied in practical tasks.
2.We will use the approaches of scenario-based stochastic spatiotemporal modeling of local ice parameters to predict the future navigational ice conditions and form typified ice maps.This task is necessary to form the scenarios of changes in the navigational ice situation in the Arctic on the horizon up to 2050,which has a direct impact on the required number of icebreakers and transport ships.
З.The project involves the creation and validation of the models to predict parameters of ship and caravan operation in ice based on the results of experiments in the ice basin,as well as the artificial intelligence methods.The importance of this problem is due to the fact that all the practical results of the Arctic fleet modeling and planning are directly related to the accuracy and adequacy of the models of ship operation in changing ice conditions.The results of work in this area are expected to be used in various scientific and practical studies on the modeling of Arctic marine transport systems.
4.In order to improve the quality of the initial design of Arctic ships and increase their energy efficiency,the we plan to develop methods for the optimization ship design analysis and create new algorithmic solutions to implement shipbuilding CAD systems of a conceptual type.The results of solving this problem will form the basis for practical solutions that are relevant for Russian shipbuilding design bureaus.
5.Within the framework of the project,we will pay special attention to the development of new methods of ice routing and improvement of previously developed solutions.The work will be carried out taking into account the experience of the authors in industrial projects.In particular,we will propose solutions for the problem of joined optimization of the trajectory and speed of the vessel on each segment.It is planned to carry out a comprehensive validation of the obtained solutions based on the full-scale data.
The described results correspond to the advanced world level of research in this area,and in terms of the practical component are many times greater than similar foreign developments.This is due to the fact that at present Russia is the only country that has practical experience in Arctic shipping and actively develops the solutions in the field of its intellectualization.Access to up-to-date data will be provided due to the involvement of our scientific team in industrial projects.
1.Changes in the Ice Cover of the Russian Arctic Seas in the 21st Century Based on the Results of Climate Models of the CMIP6 Project
- 关键词：
- reduced sea ice cover; MPI-ESM1-2-HR; AWI-CM-1-1-MR; CMIP6;EXTENT
- Tsedrik, S. V.;May, R. I.
- 《IZVESTIYA ATMOSPHERIC AND OCEANIC PHYSICS》
- 2025年
- 61卷
- SUPPL2期
- 期刊
Ice cover is one of the main parameters describing the state of various water areas. The simplicity of calculation determines the frequency of using the indicator in research both for reading the seasonal course and interannual changes in the state of the ice cover and for verifying model data or reanalysis data. In this paper, ice cover is calculated based on five data sources. The comparison is based on satellite data from the NSIDC DAAC archives (October 26, 1978, to March 31, 2023; spatial resolution is 25 x 25 km, temporal resolution is 1 day; the data were collected by SMMR, SSM/I, and SSMI/S sensors on the DMSP program satellites, as well as the Nimbus-7 satellite and OSISAF (product code OSI-401-d; March 1, 2005, to present; spatial resolution is 10 x 10 km and temporal resolution is 1 day; the data were collected by the SSMI/S sensor on the DMSP program satellites). Model data from the international CMIP (Coupled Model Intercomparison Project) project are used for comparison and verification. Of the more than 40 models of the sixth phase of the project, two were selected that provided the necessary data and were suitable in terms of spatial and temporal resolution: MPI-ESM1-2-HR and AWI-CM-1-1-MR of the Max Planck Institute and the Alfred Wegener Institute, respectively. For all obtained coverage series, the mean, standard deviation, range, correlation intervals, trend coefficients, and standard error were estimated relative to the NSIDC series for the data intersection period of September 19, 2016 to June 31, 2023, in each of the Russian Arctic seas, as well as for the water area as a whole. Using the statistical characteristics, satellite data on ice cover were compared with the results of modeling in accordance with different socioeconomic trajectories (Shared Socioeconomic Pathways (SSPs)) for both models, the quality of ice cover modeling was assessed, and scenarios were selected that most closely matched the satellite data for both the entire Russian Arctic water area and for individual seas. Based on the optimal scenarios, possible changes in ice content were predicted.
...2.Spatiotemporal Stationarity of Laptev Sea Polynyas
- 关键词：
- flaw polynya; Laptev Sea; polygons; sea ice; landfast ice
- Timofeeva, A. B.;Rubchenia, A. V.;May, R. I.
- 《IZVESTIYA ATMOSPHERIC AND OCEANIC PHYSICS》
- 2025年
- 61卷
- SUPPL2期
- 期刊
This study examines the seasonal and interannual variability of the location and area of flaw polynyas in the Laptev Sea. It uses Arctic and Antarctic Research Institute (AARI) regional charts of ice conditions in the SIGRID-3 format covering the years from 1997 to 2023 as initial data. The analysis is based on an algorithm developed previously for calculating the frequency of occurrence of multiple vector polygon intersections. To visualize areas with a 50% polynya occurrence frequency, a series of monthly charts was produced for December through May. The annual average time series for this indicator reveals a positive trend. Seasonally, the polynyas exhibit a distinct pattern, beginning as open and extensive features in the western part of the sea. During spring, this pattern reverses, with the eastern polynyas increasing in extent as the western ones decline. This positive trend is observed in both parts of the sea throughout the season, with significant values noted during the spring months (April and May) in the western area. This is particularly important, as the polynya during this period marks the beginning of summer melting, which can have significant implications. By analyzing all polynyas polygons from the period under study (1997-2023), we identified polygons of recurring polynyas (with a 75% occurrence frequency) and stable polynyas (with a 50% occurrence frequency). It was discovered that the criterion for recurring polynyas corresponds only to a small section along the fast ice of Teresa Klavenes and Thaddeus bays. Notably, the Western New Siberian polynya has a 50% occurrence frequency and is located in a narrow strip northwest of Kotelny Island. Previous studies indicate that this section is part of the Great Siberian Polynya; however, it is evident that its development has been limited in recent decades. In contrast, the sections of the Northeastern Taimyr and Anabar-Lena polynyas are significantly larger and exhibit high occurrence frequencies. This scenario may be linked to changes in large-scale atmospheric circulation and the dominance of western circulation patterns.
...3.Formation and Consolidation of a First-year Ridge Based on Nine Months of Observations at the Drifting Station "North Pole-41"
- 关键词：
- Ice ridge; morphometry; consolidated layer; porosity; ice blocks;ICE RIDGES
- Guzenko, Roman B.;Gavrilov, Yuri G.;Kharitonov, Victor V.;Khotchenkov, Stepan V.;May, Ruslan I.
- 《INTERNATIONAL JOURNAL OF OFFSHORE AND POLAR ENGINEERING》
- 2025年
- 35卷
- 2期
- 期刊
The paper presents the results of a study of the morphometry of a first-year ice ridge formed in November during the drift of the "North Pole-41" station from December to August using thermal drilling and thermistor strings. The dynamics of the consolidated layer thickness include an increase in the thickness in winter-spring, continued consolidation in the first half of summer, and subsequent melting. Keel consolidation increased from 31% in early January to complete freezing in early August; the contribution of summer processes to the increase of the consolidated layer thickness during the period of its maximum development was 8%.
...4.Landfast Ice Occurrence Frequency in the Laptev Sea by Electronic Ice Charts
- 关键词：
- Laptev Sea; landfast ice (fast ice); polygons analysis; fast ice areadecrease;EXTENT
- Timofeeva, Anna B.;May, Ruslan I.;V. Rubchenia, Andrey
- 《INTERNATIONAL JOURNAL OF OFFSHORE AND POLAR ENGINEERING》
- 2025年
- 35卷
- 2期
- 期刊
Landfast ice of the Laptev Sea was analyzed with the help of the previously developed effective algorithm for calculating the frequency of occurrence of an unlimited number of vector polygon intersections. Arctic and Antarctic Research Institute (AARI) electronic ice charts for 1997-2022 were used as initial data. As a result, occurrence frequency charts of fast ice distribution were obtained and analyzed. The seasonal variations and the growth of fast ice during the winter period were considered in detail; the probability was calculated and charted for each ten-day period. Interannual variability was estimated. The relation of fast ice and bathymetry were analyzed.
...5.Parametric Identification of the Stochastic Generator of Weather Windows from Regular Meteorological Data
- 《RUSSIAN METEOROLOGY AND HYDROLOGY》
- 2025年
- 50卷
- 2期
- 期刊
Production interruption caused by an unfavorable combination of weather factors have a significant impact on the integral performance of objects and systems operating outdoors, which should be properly taken into consideration in their simulation models ("digital twins"). The paper proposes a method for stochastic modeling of a random process of "weather windows" dynamics in continuous time, i.e., with an arbitrary time resolution. Discrete records of regular meteorological observations are used to identify the parameters of this continuous stochastic generator. The proposed technique makes it possible to obtain an accurate model description of the random process from indirect and incomplete measurements, provided that certain assumptions about its nature are met. Examples and prospects of using the proposed approach in simulation models of marine transport systems are considered.
...6.Hybrid cell-wave algorithm for ship routing in ice under spatiotemporal constraints
- 关键词：
- Ship routing; Ship transit model; Wave-based algorithm; Time of arrival;Isochrone;OPTIMIZATION
- Topaj, Alex;Tarovik, Oleg
- 《OCEAN ENGINEERING》
- 2025年
- 326卷
- 期
- 期刊
The rapid development of Arctic shipping requires the implementation of new and effective methods for ship routing in ice and open water aimed at reducing emissions and improving transport efficiency. This article presents a new original hybrid algorithm for finding a path in a nonhomogeneous and nonstationary medium. The pathfinding approach is based on a wave propagation principle, while the method to reduce the number of points in a wave front utilizes cell-based techniques. The developed algorithm allows joint optimization of ship trajectory, shaft power and mode of movement using a criterion of conditional cost that summarizes the costs of ship freight, fuel, and icebreaker assistance. The algorithm considers additional spatiotemporal constraints, such as the zones of prohibited navigation and ship arrival within a specified time limit. At the same time, the approach remains within the two-dimensional representation of a routing problem that ensures its good computational efficiency. The results of several case studies demonstrate a principal correspondence of the approach to the real practice of ice navigation. The routing method can be implemented as a functional built-in module in automated systems for decision support and management in Arctic and open water shipping.
...7.A benchmark study on ship speed prediction models in arctic conditions: Machine learning, process-based and hybrid approaches
- 关键词：
- Fleet operations;Forecasting;Ice;Liquefied natural gas;Ships;Arctic navigation;Benchmark study;Condition;Hybrid approach;Ice conditions;LNG carriers;Machine-learning;Ship speed;Speed prediction models;Yamalmax LNG carrier
- Tarovik, Oleg;Eremenko, Danila;Topaj, Alex
- 《Ocean Engineering》
- 2024年
- 311卷
- 期
- 期刊
Ship speed forecasting in harsh and uncertain ice conditions is a core technology enabling Arctic fleet planning at strategical, tactical, and operational levels of maritime logistics. In this benchmark study, we examine five alternative models that differ by their nature (process-oriented, data-driven, and hybrid approaches) and set of predictors (combinations of AIS and ice parameters). To develop these models, AIS data on YamalMax LNG carriers and ice data from diagnostic charts were merged in a joint dataset covering the period 2017–2022. A detailed description of this dataset is given in the article, including spatiotemporal variability of ice parameters and ship speed. Actual and predicted speeds are compared by five statistical indicators not only in the case of speed estimation at a point, but also when calculating average speed over long-distance route segments. The article analyses the difference in accuracy of speed predictions in various geographical areas of the Arctic and during different seasons. The degree of influence of model parameters is estimated using a SHAP approach. Several conclusions about the architecture of forecasting models and their predictors are drawn as a result. © 2024 Elsevier Ltd
...8.Comparison of Data of Atmospheric Reanalyses of the 20th Century with Results of Meteorological Observations of GL Brusilov's Expedition on the St. Anna Schooner during the Forced Drift in 1912-1914
- 关键词：
- 20th century reanalyses; verification; St. Anna; vector correlation;root-mean-square error of vectors
- May, R. I.;Tsedrik, S. V.;Ermolov, E. O.
- 《IZVESTIYA ATMOSPHERIC AND OCEANIC PHYSICS》
- 2024年
- 60卷
- 5期
- 期刊
This paper presents results of comparing the ERA-20C and NOAA-CIRES-DOE 20th Century Reanalysis Version 3 atmospheric reanalyses of the 20th century with data of meteorological observations made during the forced drift of the St. Anna schooner in 1912-1914 in Arctic. Synchronous time series of atmospheric pressure, air temperature, wind speed and direction were compared using correlation analysis and estimates of the mean error (bias) and root-mean-square error (RMSE). To compare wind data, specialized techniques for analyzing vector series were used. For all meteorological characteristics, the NOAA-CIRES-DOE 20th Century Version 3 reanalysis shows higher values of correlation and the lowest RMSE values. The minimum mean error values for atmospheric pressure and air temperature data are shown by the ERA-20C reanalysis. It has been established that there is a systematic deviation of approximately 12 degrees-15 degrees between the wind measurement data and the reanalysis wind.
...9.Stochastic Modeling of Sea Ice Concentration to Assess Navigation Conditions along the Northern Sea Route
- 关键词：
- ice concentration; sea ice generator; stochastic modeling; iceconditions; Markov chain; Arctic navigation;WEATHER GENERATOR; RANDOM-FIELDS; SIMULATION; PRECIPITATION
- May, R. I.;Guzenko, R. B.;Tarovik, O. V.;Topaj, A. G.;Yulin, A. V.
- 《IZVESTIYA ATMOSPHERIC AND OCEANIC PHYSICS》
- 2023年
- 59卷
- SUPPL 1期
- 期刊
This article describes a probabilistic model (stochastic generator) of spatiotemporal variability of sea ice concentration. The values of the concentration are generated at the nodes of the spatial grid with 10-km resolution; the model time step is 1 day. The change in ice concentration with time (temporal variability) is modeled on the basis of a matrix of transient probabilities (discrete Markov chain), each row of which is a distribution function of the conditional probability of changes in the concentration. Spatial variability is determined by empirical probability fields, with which the observed changes in fields of concentration are associated with known conditional probability distribution functions. To identify the parameters of the stochastic generator, satellite data from the OSI SAF project for 1987-2019 were used. The generator takes into account seasonal, interannual, and climatic variability. Interannual and climatic variability are determined on the basis of a stochastic model of changes in the types of ice coverage. In order to verify the developed stochastic generator, we compare the statistical indicators of observed and calculated ice fields. The results show that the field-average absolute error of statistical characteristics of the ice concentration (average and standard deviation) does not exceed 3.3%. The discrepancy between the correlation intervals of ice coverage calculated from the model and measured ice concentration fields does not exceed 2 days. The variograms of the modeled and observed fields have a similar form and close values. As an example, we determine the duration of navigation of Arc4 ice class ships between the Barents and Kara seas using synthetic fields of the concentration reproduced by the stochastic generator.
...