Improving maritime traffic emission estimations on missing data with CRBMs

Abstract

Maritime traffic emissions are a major concern to governments as they heavily impact the Air Quality in coastal cities. Ships use the Automatic Identification System (AIS) to continuously report position and speed among other features, and therefore this data is suitable to be used to estimate emissions, if it is combined with engine data. However, important ship features are often inaccurate or missing. State-of-the-art complex systems, like CALIOPE at the Barcelona Supercomputing Center, are used to model Air Quality. These systems can benefit from AIS based emission models as they are very precise in positioning the pollution. Unfortunately, these models are sensitive to missing or corrupted data, and therefore they need data curation techniques to significantly improve the estimation accuracy. In this work, we propose a methodology for treating ship data using Conditional Restricted Boltzmann Machines (CRBMs) plus machine learning methods to improve the quality of data passed to emission models that can also be applied to other GPS and time-series problems. Results show that we can improve the default methods proposed to cover missing data. In our results, we observed that using our method the models boosted their accuracy to detect otherwise undetectable emissions. In particular, we used a real data-set of AIS data, provided by the Spanish Port Authority, to estimate that thanks to our method, the model was able to detect 45% of additional emissions, representing 152 tonnes of pollutants per week in Barcelona and propose new features that may enhance emission modeling.

Self-Supervised Learning for Data Scarcity in a Fatigue Damage Prognostic Problem

“…Currently, data scarcity represents a scientific bottleneck in many engineering fields (e.g. in healthcare [7], in energy [8], water and environmental engineering [9,10], etc. ), which makes it difficult to apply the latest Machine Learning (ML) methods.…”

Distributed cloud-edge analytics and machine learning for transportation emissions estimation

“…In that case, it was seen that having local models performed better than sending all the data to the central node and training globally when network connectivity issues happen. In this sense, we go a step further and extend this idea of training local models with local synchronization, as proposed in Gutierrez et al [111]. In this work, models were trained locally and then averaged to obtain a synchronized model.…”

“…It also provides low bandwidth usage, as only models are required to be transferred and, generally, they should not be big. In our previous work [111] the model initialization and the FL rounds effect was not taken into consideration, therefore this work will cover it.…”