Below is the uncorrected machine-read text of this chapter, intended to provide our own search engines and external engines with highly rich, chapter-representative searchable text of each book. Because it is UNCORRECTED material, please consider the following text as a useful but insufficient proxy for the authoritative book pages.
57 Closing Session Main Concepts, Research Needs and Gaps, and Lessons Learned Sandra Knight, WaterWonks, LLC, Conference Planning Committee Chair, presiding Kathryn McIntosh, U.S. Army Corps of Engineers, recording his session brought forward key concepts from the plenary and breakout sessions shown in Table 5, highlighting research needs and gaps and lessons learned to help inform but not direct future activity for MTS R&D within the context of multimodal freight analytics. These concepts emerged from individual presentations and discussions by panelists, presenters, and participants. No agreement or consensus is intended or implied, and the order in which the concepts are listed does not imply prioritization or their relative level of importance. TABLE 5. Key Concepts from the Conference. Session 1A Data Analytics: Maritime and Freight 1 Key Concepts â¢ Both North Carolina and Ohio are educating planners and decision makers on the importance of freight using data analysis and visualization to help communicate â Economic impacts of freight, â Locations of freight activity, and â Identification of locations (even outside of the state) that would benefit from investments. â¢ Two presenters noted that their analysis is showing that states might sometimes need to invest in infrastructure outside their own state to have positive impacts on freight movements and the supply chain in their own state. â¢ Combining data sets from multiple sources is usually necessary to tell a compelling story. â¢ Making data available in a timely manner to a large group of stakeholders is an ongoing challenge. Improving publicâprivate partnerships, policies, and trusted data exchanges is important. Finding a way to anonymize data so that data can be used to inform public policy without negatively affecting business is a need. â¢ Conducting look-back analysis is challenging, and many agencies want to predict future conditions. New work resulting from NCHRP Report 739 and NCHRP Report 19 and NCFRP Research Report 37 is creating web-based access to models that help agencies generate estimates of demand for freight. Continued on next page. T
58 TABLE 5 (continued). Key Concepts from the Conference. Session 1B Data Analytics: Inland Waterways Key Concepts â¢ Much more can be done with existing, publicly available data. Current software can be used to tease information out of databases that enable a better understanding of how the inland waterway system is performing at the lock level and as a system. â¢ The ability to evaluate the state of the inland waterway system and the reaction by users to major events requires access to trip data from USACE and the Waybill data from the Surface Transportation Board. Unless the analyst is working for a federal agency, these data sets are typically not available. AIS data are available, but must be purchased. â¢ Several analytical processes have been developed to be applied across a broader geographical scope: â A lockâs role in the system and its importance to the system, â Shipper cost burden caused by lock closure, â Graphical representations that show a lockâs traffic patterns across the country and its network effect, and â Rail capacity concentration index for a selected corridor. â¢ Use of AIS data can help establish baseline travel times and show how a disruption to the system affects those times and how long it takes to return to normal. â¢ USACE is developing an AIS-based travel time map, which should be available online sometime in early- to mid-2019. Session 1C Decision Support: Resilience Key Concepts â¢ Marine transportation places a critical role in economic and community resilience. â¢ Because there are gaps in data, enhanced understanding still may not lead to better decision- making. â¢ Barriers to improving resilience in ports range from funding constraints to lack of risk awareness to fragmented administrations, and from geographical constraints to communication issues. â¢ Resilience of data and ability to communicate are as critical as the resilience of the infrastructure, as demonstrated by lessons learned from Puerto Rico. â¢ Regional predictions are not always suitable to local details. A key limiting parameter is elevation data. â¢ Analytics from AIS and other data sources can help analyze failures and improve planning. â¢ Seaports and airports on islands are highly vulnerable to coastal storms and sea level rise, creating escalating challenges for response and recovery. â¢ Analytics can inform policy. For example, vessel routing was used to evaluate Jones Act restrictions after Hurricane Sandy. Session 2A Data Analytics: Maritime and Freight 2 Key Concepts â¢ Transportation is key for moving commodities to market, facilitating global trade, and supporting the world economy. â¢ Models help set prices and/or minimize costs, accounting for underlying factors. â¢ Assumptions are made when models are being developed and run and can lead to more questions. â¢ Models (e.g., flow, optimization) depend on data availability and quality, definitions, and computing power. Continued on next page.
59 TABLE 5 (continued). Key Concepts from the Conference. Session 2B Decision Support: Managing Flows Key Concepts â¢ Data and advanced analytics can inform decisions. More information can be derived from current data sources by applying advanced analytics, which can help to tell the freight story better. â¢ Standards and methods are important because the information will be different depending on the methods used. For example, Quettica found that FAF can be misused and does not relate to trade data from some other sources, so understanding the source data and methodology for correctly using that data is an important consideration. The methodology used can provide different results. â¢ Marine data, like AIS and other sources, provide important information. Applying advanced analytics can provide information about performance from travel time to risk. â¢ USACE is working on a platform to share data between public and private sectors. It would be an immediate exchange as events occur to provide a data loop between the sectors. Session 2C Data Analytics: Port Performance Key Concepts â¢ A solution to port productivity is to increase crane productivity through number of cranes and sophisticated spreaders. â¢ AIS data are shedding new light on port operations. Using AIS information, ports can allocate work to vessel arrival to minimize overtime costs. The goal is to minimize cost, not minimize dwell times. â¢ AIS data can be used to evaluate port mobility. Differences exist between water and roadway measures, and vessel type is important in evaluating mobility. â¢ Ports are using emulation to simulate operations in their TOSs to build and synchronize jobs and tasks. Session 2D Decision Support: Safety Key Concepts â¢ The lack of available near-miss/accident causation data in maritime necessitates proxy methodologies and qualitative analysis to determine correlations, trends and predictions and to solve for data gaps. â¢ The USCG MISLE database has limitations and tremendous opportunity, including potential for deeper mining and analysis, especially if coupled with AIS data. â¢ The methodologies from the presentations have promise for use as pre- and postregulation indicators of benefits and effectiveness. Subchapter M implementation is an example. â¢ It could be useful to translate the results of these studies from pure data and findings to messaging for policymakers, rulemaking justification, best practices for waterways management by harbor safety committee, industry operators integration and union training organizations. Session 3A Data Analytics: Maritime and Freight 3 Key Concepts â¢ Many emerging technologies can be harnessed to describe and understand freight and maritime activity. â¢ As transportation companies invest in and make use of technology, new sources of data become available for researchers. The data and any associated operations applied are also exposed to cyber-security risk. â¢ One of the challenges will be integrating more traditional data sources with analytical techniques and the new, emerging data. Continued on next page.
60 TABLE 5 (continued). Key Concepts from the Conference. Session 3B Big Data and Machine Learning: Maritime Applications Key Concepts â¢ Big data applications, including Blockchain and machine learning algorithms, can and are being leveraged to improve maritime transportation. Understanding transportation-specific language, security features, and freight-flow scalability is required. â¢ Multiple and accurate data streams are important to improve machine learning applications for transportation and freight flows. â¢ Access to correct and consistent data (e.g., O-D, vessel status) is key to building a robust foundation for big data applications. Session 3C Decision Support: Environmental Key Concepts â¢ Air emissions modeling was improved by the use of cleaned AIS data integrated with IHS vessel data. Integration included combining vessel type with more specific vessel type/engine combinations, actual engine loads (versus defaults), highly detailed spatial and temporal resolution, and exclusion of state waters activities. No spatial allocation or assumptions were required because activity was calculated in place. â¢ Merging AIS and USCG data for modeling maritime air emissions allows for both spatial and temporal location of maritime source air emissions and provides accurate counts of most vessels, as well as clear indicators of vessel paths, speeds, and time spent in various travel modes that drive engine use assumptions. This lends itself to scenario analyses to obtain reasonable granular estimates of air emissions to compare the baseline and scenario conditions and provides for emissions profiles that reflect the maritime uses such as type and intensity for different areas. â¢ Understanding multiattribute performance of intermodal maritime cargos provides opportunities for implementing modal shifts for cargo to reduce air emission, energy conception, and cost, including warehousing by Right-shoring, Right-steaming, Right-routing, Right-timing, Right- bundling, and Right-mode mixing. A shift has occurred since the 2010 recession to more localized warehousing. After reviewing the key concepts in Table 5, attendees were asked to consider a series of overarching questions based on the information presented at the conference and the coalescence of this information as it related to conference goals and objectives. Responses are summarized in Table 6. The bulleted items in this table were provided by individual attendees and are listed in the order that they were given. Again, no agreement or consensus is intended or implied, and the order in which the concepts are listed does not imply prioritization or their relative level of importance.
61 TABLE 6. Closing Catalyzing Ideas from Conference Attendees. Question What does a transformed MTS look like in the future (5 to 10 years)? Responses â¢ Seamless interaction between producers and users â¢ Integrated system of sensors that are both publicly and privately owned â¢ Interoperability of the data and understanding how that drives optimization of economics â¢ Public policymakers receiving clear, concise, holistic data to support and respond to the needs of the system â¢ More incentives to drive greener MTS â¢ Automated systems with more automated data retrieval and collection â¢ Decision-making that is supported by AI Question What are the key challenges and disruptive influences inhibiting improved multimodal freight analytics and modeling? Now? In the future? Responses â¢ Stovepipe policies (horizontal and vertical), siloed R&D research â¢ Data protection and data sharing â¢ Continuing degradation of the infrastructure â¢ Better analytics and mining capability of existing data sets â¢ Breaking the silos â¢ Inaccuracies in existing data sets â¢ No slack in the system â¢ All modes needed in the room â¢ Improved ability to look across the supply chainsâmore granularity â¢ More data standards â¢ More consideration of cybersecurity â¢ More consideration of bottlenecks Question What contributions or role can we make as co-producers from our respective positions in the private-sector, government, nongovernmental organizations and academia? Responses â¢ Use data to understand why it is important to have a multimodal network â¢ Ask the right questions to get the appropriate answers â¢ Make use of open source to coproduce data and solutions â¢ Ensure appropriate timing of data production, for example, produce more timely federal data â¢ Encourage data standardization at the federal level â¢ Understand the questions and why they are asked and what is really wanted or needed â¢ Coproduce research with the end user to improve results and products â¢ Provide model language for nondisclosure agreements and contracting Continued on next page.
62 TABLE 6 (continued). Closing Catalyzing Ideas from Conference Attendees. Question What promising new or emerging technologies and/or methodologies would you most want? Responses â¢ Uber-style system that can be adapted to port/rail operations â¢ Automationâ24/7 operations â¢ Improved navigation of policy issues and/or roadblocks â¢ Use of robotics to transform the industry without reducing workforce â¢ Optical recognition technology â¢ Green technology â¢ Portable backup data sources â¢ Secure, reliable and trusted data interchange (Blockchain as a possibility) â¢ Interoperable data collection systems across states and ports â¢ Common language â¢ Training and interaction with new technology â¢ Turning unstructured text into machine readable format â¢ Fog computing and edge technologies Question What are the highest priority R&D gaps or needs? Responses â¢ Domestic and international, multimodal, fluid, routable, network models â¢ Interdisciplinary system â¢ Process or organization that brings the research community together with the supply chain to understand what is going on now â¢ Reduced time from data collection to use in communication of results and research â¢ Resources â¢ Cross-disciplinary education â¢ Use of appropriate crowd data as intelligence â¢ Capture and understanding of 2nd-order impacts on the economy â¢ Research that involves other federal partners, sharing and using sensitive data â¢ Sharing data and better communication across agencies Question What are the opportunities now and in the future to integrate systems and coproduce solutions? Responses â¢ Avoiding duplicating the same methods â¢ Increasing the speed of finding and communicating new methods â¢ Bringing the maritime freight community into the discussion of emergencies and resilience â¢ Developing and communicating data products, graphics, and visuals to influence policy â¢ Educating and informing policymakers on how to use data for decisions â¢ Addressing the generational division in understanding and communicating data (data in tables versus dashboards and visualizations) â¢ Ensuring interdisciplinary approach to addressing problems Question Anything that we missed? Responses â¢ The impact of the termination of a national cooperative freight research program
63 IN CLOSING This conference, as did past conferences, continued to be a catalyst for innovation and collaboration in the MTS and resulted in a multitude of ideas and well-informed points for consideration. The active participation of policymakers, transportation agency practitioners, academia, private-sector stakeholders, and consultants provided insight into opportunities and challenges facing the maritime community as well as an understanding of emerging research and technologies that will be important to transforming the MRS through multimodal freight analytics.