Temporal Robustness Research Articles

STCM-GCN: a spatial-temproal prediction method for traffic crashes under road network constraints

Existing research faces challenges in accurately predicting crashes due to the unreasonable selection of spatial units, biased crash data collection, and insufficient integration of multi-source data. To address these issues, Graph Neural Networks (GNNs) for node classification are employed to predict crashes at macroscopic road level. Crash alarm data are incorporated as a supplement to official archive data to ensure the spatial–temporal distribution's authenticity and to mitigate data sparsity. Additionally, traffic violation data are included as a feature to enrich risk information. Finally, a multi-graph deep learning framework (STCM-GCN) with spatial, temporal, and spatial–temporal modules has been developed. Data from Shenzhen, China, demonstrates that the STCM-GCN outperforms baseline models and has a reasonable structure. The inclusion of crash alarm data and traffic violations contributes to performance improvement. Additionally, the model exhibits spatial–temporal robustness, and the analysis of computational efficiency provides comprehensive insights into the model's capabilities.

Mitigating Risks in Cone Beam Computed Tomography Guided Online Adaptive Radiation Therapy: A Preventative Reference Planning Review Approach

PurposeOnline adaptive radiotherapy (oART) treatment planning requires evaluating the temporal robustness of reference plans, anticipating the potential changes during treatment courses that may even lead to risks unique to the adaptive workflow. This study conducted a risk analysis of the CBCT-guided adaptive workflow and is the first to assess an adaptive specific reference planning review that mitigates risk in the planning process to prevent events and treatment deficiencies during adaptation. Methods and MaterialsA quality management team of medical physicists, residents, physicians, and radiation therapists performed a fault tree analysis, and failure mode and effects analysis (FMEA). Fault trees were created for under/overdosing targets, treatment deficiencies, as well as assisted in identifying failure modes for the FMEA. Treatment deficiency was defined to include a non-ideal oART plan resulting in treatment with a lower quality plan (either oART or scheduled plan), treatment delay, or cancelling treatment for the day. A reference planning checklist was created to catch failure modes before reaching the patient. Risk priority numbers (RPN=Severity*Detectability*Occurrence) were scored with and without the reference planning checklist to quantify risk mitigation. A root cause analysis was conducted for an event where an adaptive plan failed to generate. ResultsThe reference planning checklist (with items covering patient background, contouring/planning robustness for anatomy variability, and machine limitations) reduced the RPN for all failure modes. Only 1 failure mode with a risk priority number >150 occurred with the reference planning checklist compared to 29 failure modes without, including 14 adaptive specific failure modes. Contouring, planning, setup, scheduling, and documentation errors were identified during the fault tree analysis. 29/70 errors were adaptive specific. The reference planning checklist could address 23/33 for over/under dosing and 28/37 errors for treatment deficiency. The root cause analysis highlighted the need for checking setup prior to adaptive plan delivery, and time-out checklist. ConclusionsThe reference planning checklist improved detection of the failure modes and improves the quality and robustness of the plans produced for oART. It is ideally performed before physician plan review to prevent last minute re-plan (before or after first adaptive treatment) and delay of patient start. The checklist presented can be modified based on failures specific to individual clinics and utilized at various planning steps based on available resources.

Residual Temporal Convolutional Network With Dual Attention Mechanism for Multilead-Time Interpretable Runoff Forecasting.

As a pivotal subfield within the domain of time series forecasting, runoff forecasting plays a crucial role in water resource management and scheduling. Recent advancements in the application of artificial neural networks (ANNs) and attention mechanisms have markedly enhanced the accuracy of runoff forecasting models. This article introduces an innovative hybrid model, ResTCN-DAM, which synergizes the strengths of deep residual network (ResNet), temporal convolutional networks (TCNs), and dual attention mechanisms (DAMs). The proposed ResTCN-DAM is designed to leverage the unique attributes of these three modules: TCN has outstanding capability to process time series data in parallel. By combining with modified ResNet, multiple TCN layers can be densely stacked to capture more hidden information in the temporal dimension. DAM module adeptly captures the interdependencies within both temporal and feature dimensions, adeptly accentuating relevant time steps/features while diminishing less significant ones with minimal computational cost. Furthermore, the snapshot ensemble method is able to obtain the effect of training multiple models through one single training process, which ensures the accuracy and robustness of the forecasts. The deep integration and collaborative cooperation of these modules comprehensively enhance the model's forecasting capability from various perspectives. Ablation studies conducted validate the efficacy of each module, and through multiple sets of comparative experiments, it is shown that the proposed ResTCN-DAM has exceptional and consistent performance across varying lead times. We also employ visualization techniques to display heatmaps of the model's weights, thereby enhancing the interpretability of the model. When compared with the prevailing neural network-based runoff forecasting models, ResTCN-DAM exhibits state-of-the-art accuracy, temporal robustness, and interpretability, positioning it at the forefront of contemporary research.

Multi-lead-time short-term runoff forecasting based on Ensemble Attention Temporal Convolutional Network

In the realm of ecological management and human activities within river basins, short-term runoff forecasting plays a pivotal role. Addressing this need, this paper introduces an innovative framework for short-term runoff forecasting: the Ensemble Attention Temporal Convolutional Network (EA-TCN). The cornerstone of this innovation lies in the effective amalgamation of Temporal Convolutional Network (TCN), lightweight attention mechanism, and ensemble learning strategy. This integration synergistically enhances the model’s overall performance in terms of accuracy, efficiency, and robustness. TCN forms the foundation of this framework, where its efficient architecture, characterized by shared parameters and parallel computation, significantly boosts computational efficiency. Its employment of causal and dilated convolutions adeptly captures long-term dependencies within time series inputs. The incorporated lightweight attention mechanism further augments the TCN, enabling EA-TCN to precisely discern complex relationship in temporal data, particularly exhibiting remarkable temporal robustness across various forecasting horizons—a feat challenging for conventional forecasting approaches. Additionally, the integration of the Snapshot ensemble method within the framework allows for simulating the effect of training multiple models through one single training process, thus further elevating the model’s accuracy and robustness. Rigorous ablation and comparative experiments conducted on the US Columbia River dataset substantiate our claims. The results not only validate the individual merits of each component within EA-TCN but also illuminate the significant advantages of their collective application. Our comprehensive assessment unequivocally demonstrates the framework’s exceptional performance in short-term runoff forecasting, positioning it as a state-of-the-art solution in this field. We will further discuss its impact of vocation education in this industry.

Tracking Socio-Economic Development in Rural India over Two Decades Using Satellite Imagery

Longitudinal analysis of socio-economic development at sub-national scales can reveal valuable insights about which areas tend to develop faster than others and why. However, such analysis is difficult to conduct with traditional data sources such as censuses and surveys which are not repeated frequently and may require assumptions for imputation of values at non-surveyed locations. Indicators of socio-economic development based on satellite data have emerged as a proxy to track development at fine spatial and temporal scales. We build a model using daytime and nightlights satellite data to estimate an index of socio-economic development at the village level in India. We evaluate our model for temporal robustness and use it to produce estimates at three time points over a two-decade period. We then use these estimates to understand the effect on village-level development of factors such as the geographic distance of a village to hubs of economic activity and the inequality of development in the district. Our findings provide evidence of the possible impact that policy changes during this period have had on village development.

Evaluation of a phosphate kinetics model in hemodialysis therapy-Assessment of the temporal robustness of model predictions.

In-depth understanding of intra- and postdialytic phosphate kinetics is important to adjust treatment regimens in hemodialysis. We aimed to modify and validate a three-compartment phosphate kinetic model to individual patient data and assess the temporal robustness. Intradialytic phosphate samples were collected from the plasma and dialysate of 12 patients during two treatments (HD1 and HD2). 2-h postdialytic plasma samples were collected in four of the patients. First, the model was fitted to HD1 samples from each patient to estimate the mass transfer coefficients. Second, the best fitted model in each patient case was validated on HD2 samples. The best model fits were determined from the coefficient of determination (R2 ) values. When fitted to intradialytic samples only, the median (interquartile range) R2 values were 0.985 (0.959-0.997) and 0.992 (0.984-0.994) for HD1 and HD2, respectively. When fitted to both intra- and postdialytic samples, the results were 0.882 (0.838-0.929) and 0.963 (0.951-0.976) for HD1 and HD2, respectively. Eight patients demonstrated a higher R2 value for HD2 than for HD1. The model seems promising to predict individual plasma phosphate in hemodialysis patients. The results also show good temporal robustness of the model. Further modifications and validation on a larger sample are needed.

MA-SARNet: A one-shot nowcasting framework for SAR image prediction with physical driving forces

Remote sensing imagery is one of the most widely used data sources for large-scale Earth observations with consistent spatial and temporal quality. However, the current usage scenarios of Earth’s surface remote sensing images, such as those generated from Landsat, Sentinel 2, and SAR, are largely limited to retrospective tasks, as they are often used to reconstruct existing phenomena, such as land use change, flood inundation, and wildfire. This study proposes MA-SARNet, a one-shot nowcasting framework built with a modified MA-Net structure and ResNet50 as the backbone, to predict the backscatter values of Synthetic-Aperture Radar (SAR) images using the previous SAR observations, precipitation, soil moisture, and geomorphic data layers as input. The model was trained, validated, and tested with SAR images collected during the catastrophic 2019 Midwest U.S. Floods that affected several states on the Missouri and Mississippi River tributaries. Compared to the benchmark performance, model predictions show an increase of 31.9% and 17.8% for the mean and median AAI (Assemble Accuracy Index) and an increase of 37.9% and 15.1% for the mean and median NSE (Nash-Sutcliffe Efficiency) on the test set. Results showed that the flood extent derived from backscatter predictions has less misclassifications caused by pixel-level noise compared to the flood map derived using the real backscatters. Results from spatial and temporal robustness tests demonstrate that the model has sufficient generalization potential and does not require further fine-tuning to work with new data, and therefore proves its usefulness in real-time Earth surface prediction tasks that are aimed at fast response to and mitigation for upcoming floods on a tight time schedule.

Towards trustworthy multi‐modal motion prediction: Holistic evaluation and interpretability of outputs

AbstractPredicting the motion of other road agents enables autonomous vehicles to perform safe and efficient path planning. This task is very complex, as the behaviour of road agents depends on many factors and the number of possible future trajectories can be considerable (multi‐modal). Most prior approaches proposed to address multi‐modal motion prediction are based on complex machine learning systems that have limited interpretability. Moreover, the metrics used in current benchmarks do not evaluate all aspects of the problem, such as the diversity and admissibility of the output. The authors aim to advance towards the design of trustworthy motion prediction systems, based on some of the requirements for the design of Trustworthy Artificial Intelligence. The focus is on evaluation criteria, robustness, and interpretability of outputs. First, the evaluation metrics are comprehensively analysed, the main gaps of current benchmarks are identified, and a new holistic evaluation framework is proposed. Then, a method for the assessment of spatial and temporal robustness is introduced by simulating noise in the perception system. To enhance the interpretability of the outputs and generate more balanced results in the proposed evaluation framework, an intent prediction layer that can be attached to multi‐modal motion prediction models is proposed. The effectiveness of this approach is assessed through a survey that explores different elements in the visualisation of the multi‐modal trajectories and intentions. The proposed approach and findings make a significant contribution to the development of trustworthy motion prediction systems for autonomous vehicles, advancing the field towards greater safety and reliability.

Property-Based Brittleness Analysis of Temporal Networks

A new framework is proposed to analyze the brittleness of task networks with respect to an arbitrary set of user-specified properties, such as dynamic controllability or minimum battery state of charge of a rover. The proposed algorithms allow the detection and enumeration of activities that, with modest task execution duration variation, make the success of execution no longer guaranteed in terms of the given set of properties. A metric for measuring an activity’s brittleness, defined as the degree of acceptable deviation from its nominal duration that preserves the desired user-specified properties, is introduced and how that measurement is mapped to task network structure is described. Complementary to existing work on temporal robustness analysis, which informs how likely a task network is to succeed or not under temporal controllability constraints, the new analysis and metric not only generalize robustness analysis to a set of user-defined properties (as opposed to strong or dynamic controllability, for instance), but they also go deeper to pinpoint the sources of potential brittleness. An analyzer is developed, which helps human designers and/or automated task network generators focus on and address sources of undesirable brittleness. The approach is applied in Mars rover and biomanufacturing operations scenarios.

Analysis of Temporal Robustness in Massive Machine Type Communications

The evolution of fifth generation (5G) networks needs to support the latest use cases, which demand robust network connectivity for the collaborative performance of the network agents, like multi-robot systems and vehicle to anything (V2X) communication. Unfortunately, the user device’s limited communication range and battery constraint confirm the unfitness of known robustness metrics suggested for fixed networks, when applied to time-switching communication graphs. Furthermore, the calculation of most of the existing robustness metrics involves non-deterministic polynomial (NP)-time complexity, and hence are best-fitted only for small networks. Despite a large volume of works, the complete analysis of a low-complexity temporal robustness metric for a communication network is absent in the literature, and the present work aims to fill this gap. More in detail, our work provides a stochastic analysis of network robustness for a massive machine type communication (mMTC) network. The numerical investigation corroborates the exactness of the proposed analytical framework for temporal robustness metric. Along with studying the impact on network robustness of various system parameters, such as cluster head (CH) probability, power threshold value, network size, and node failure probability, we justify the observed trend of numerical results probabilistically.

Evaluation of Feature Selection Methods for Preserving Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine.

Temporal dataset shift can cause degradation in model performance as discrepancies between training and deployment data grow over time. The primary objective was to determine whether parsimonious models produced by specific feature selection methods are more robust to temporal dataset shift as measured by out-of-distribution (OOD) performance, while maintaining in-distribution (ID) performance. Our dataset consisted of intensive care unit patients from MIMIC-IV categorized by year groups (2008-2010, 2011-2013, 2014-2016, and 2017-2019). We trained baseline models using L2-regularized logistic regression on 2008-2010 to predict in-hospital mortality, long length of stay (LOS), sepsis, and invasive ventilation in all year groups. We evaluated three feature selection methods: L1-regularized logistic regression (L1), Remove and Retrain (ROAR), and causal feature selection. We assessed whether a feature selection method could maintain ID performance (2008-2010) and improve OOD performance (2017-2019). We also assessed whether parsimonious models retrained on OOD data performed as well as oracle models trained on all features in the OOD year group. The baseline model showed significantly worse OOD performance with the long LOS and sepsis tasks when compared with the ID performance. L1 and ROAR retained 3.7 to 12.6% of all features, whereas causal feature selection generally retained fewer features. Models produced by L1 and ROAR exhibited similar ID and OOD performance as the baseline models. The retraining of these models on 2017-2019 data using features selected from training on 2008-2010 data generally reached parity with oracle models trained directly on 2017-2019 data using all available features. Causal feature selection led to heterogeneous results with the superset maintaining ID performance while improving OOD calibration only on the long LOS task. While model retraining can mitigate the impact of temporal dataset shift on parsimonious models produced by L1 and ROAR, new methods are required to proactively improve temporal robustness.

Combined Left and Right Temporal Robustness for Control Under STL Specifications

Many modern autonomous systems, particularly multi-agent systems, are time-critical and need to be robust against timing uncertainties. Previous works have studied left and right time robustness of signal temporal logic specifications by considering time shifts in the predicates that are either only to the left or only to the right. We propose a combined notion of temporal robustness which simultaneously considers left and right time shifts. For instance, in a scenario where a robot plans a trajectory around a pedestrian, this combined notion can now capture uncertainty of the pedestrian arriving earlier or later than anticipated. We first derive desirable properties of this new notion with respect to left and right time shifts and then design control laws for linear systems that maximize temporal robustness using mixed-integer linear programming. Finally, we present two case studies to illustrate how the proposed temporal robustness accounts for timing uncertainties.

Temporal Robustness of Temporal Logic Specifications: Analysis and Control Design

We study the temporal robustness of temporal logic specifications and show how to design temporally robust control laws for time-critical control systems. This topic is of particular interest in connected systems and interleaving processes such as multi-robot and human-robot systems where uncertainty in the behavior of individual agents and humans can induce timing uncertainty. Despite the importance of time-critical systems, temporal robustness of temporal logic specifications has not been studied, especially from a control design point of view. We define synchronous and asynchronous temporal robustness and show that these notions quantify the robustness with respect to synchronous and asynchronous time shifts in the predicates of the temporal logic specification. It is further shown that the synchronous temporal robustness upper bounds the asynchronous temporal robustness. We then study the control design problem in which we aim to design a control law that maximizes the temporal robustness of a dynamical system. Our solution consists of a Mixed-Integer Linear Programming (MILP) encoding that can be used to obtain a sequence of optimal control inputs. While asynchronous temporal robustness is arguably more nuanced than synchronous temporal robustness, we show that control design using synchronous temporal robustness is computationally more efficient. This tradeoff can be exploited by the designer depending on the particular application at hand. We conclude the article with a variety of case studies.

Evaluating the generalisability of neural rumour verification models

Research on automated social media rumour verification, the task of identifying the veracity of questionable information circulating on social media, has yielded neural models achieving high performance, with accuracy scores that often exceed 90%. However, none of these studies focus on the real-world generalisability of the proposed approaches, that is whether the models perform well on datasets other than those on which they were initially trained and tested. In this work we aim to fill this gap by assessing the generalisability of top performing neural rumour verification models covering a range of different architectures from the perspectives of both topic and temporal robustness. For a more complete evaluation of generalisability, we collect and release COVID-RV, a novel dataset of Twitter conversations revolving around COVID-19 rumours. Unlike other existing COVID-19 datasets, our COVID-RV contains conversations around rumours that follow the format of prominent rumour verification benchmarks, while being different from them in terms of topic and time scale, thus allowing better assessment of the temporal robustness of the models. We evaluate model performance on COVID-RV and three popular rumour verification datasets to understand limitations and advantages of different model architectures, training datasets and evaluation scenarios. We find a dramatic drop in performance when testing models on a different dataset from that used for training. Further, we evaluate the ability of models to generalise in a few-shot learning setup, as well as when word embeddings are updated with the vocabulary of a new, unseen rumour. Drawing upon our experiments we discuss challenges and make recommendations for future research directions in addressing this important problem.

Temporal robustness assessment framework for city-scale bus transit networks

Despite the prevalence of bus transit networks in urban public transportation, they are very susceptible to disruptions that can have negative implications, accompanied by severe socioeconomic consequences and service quality consequences. In addition, since bus transit system is comprised of stops, routes, and passengers, any disruptions in the bus network can trigger chain reaction disruption scenarios, leading to cascade failures across the entire network. Unlike the existing literature, the present study evaluates the robustness of bus transit network considering the varied hourly operation. The robustness assessment is evaluated using a weighted network considering losses in bus frequency and passenger flow, both are essential to inform service quality improvement. Some of the key findings include the observed significant variation in the hourly performance of the network compared to the daily performance when a failure occurs. Moreover, the network is more robust during on-peak hours and mid-peak compared to off-peak hours. However, the network is sensitive to losing service frequency compared passenger flow when a failure happens. These insights could be used to inform a robustness-based spatiotemporal design of bus transit networks.

TEMPORALLY TRANSFERABLE MACHINE LEARNING MODEL FOR TOTAL SUSPENDED MATTER RETRIEVAL FROM SENTINEL-2

Abstract. The empirical (regression-based) models have long been used for retrieving water quality parameters from optical imagery by training a model between image spectra and collocated in-situ data. However, a need clearly exists to examine and enhance the temporal transferability of models. The performance of a model trained in a specific period can deteriorate when applied at another time due to variations in the composition of constituents, atmospheric conditions, and sun glint. In this study, we propose a machine learning approach that trains a neural network using samples distributed in space and time, enabling the temporal robustness of the model. We explore the temporal transferability of the proposed neural network and standard band ratio models in retrieving total suspended matter (TSM) from Sentinel-2 imagery in San Francisco Bay. Multitemporal Sentinel-2 imagery and in-situ data are used to train the models. The transferability of models is then examined by estimating the TSM for imagery acquired after the training period. In addition, we assess the robustness of the models concerning the sun glint correction. The results imply that the neural network-based model is temporally transferable (R2 ≈ 0.75; RMSE ≈ 7 g/m3 for retrievals up to 70 g/m3) and is minimally impacted by the sun glint correction. Conversely, the ratio model showed relatively poor temporal robustness with high sensitivity to the glint correction.

Specifiable robustness in reactive synthesis

When synthesizing a system from a given specification, there is room for automatically adding various requirements, hence improving the resulting system. One such requirement covered extensively in past literature is that of robustness. In particular, the system can fail to read the inputs correctly from the environment, and the environment can fail to satisfy our assumptions about its behavior. Nevertheless, we want the system to still satisfy the specification even under these failures, in some limited way. It has to be limited because it is typically too strong of a requirement to realize the property regardless of the inputs and the environment’s assumptions. In this work, we propose a simple and flexible framework for synthesizing robust systems, where the user defines the required robustness via a temporal robustness specification. For example, the user may specify that the environment is eventually reliable, or input misreadings cannot occur more than k consecutive steps and synthesize a system under this assumption. Furthermore, our framework enables us to specify a temporal recovery specification, which describes how the designer expects the system to recover after a failure of the environment assumptions. We show examples of robust systems that we synthesized with this method using our synthesis tool Party.

Exploring the Temporal Cues to Enhance Video Retrieval on Standardized CDVA

As the demand for large-scale video analysis increases, video retrieval research is also becoming more active. In 2014, ISO/IEC MPEG began standardizing compact descriptors for video analysis, known as CDVA, and it is now adopted as a standard. However, the standardized CDVA is not easily compared to other methods because the MPEG-CDVA dataset used for performance verification is not disclosed, despite the fact that follow-up studies are underway with multiple versions of the CDVA experimental model. In addition, analyses of modules constituting the CDVA framework are insufficient in previous studies. Therefore, we conduct self-evaluations of CDVA to analyze the impact of each module on the retrieval task. Furthermore, to overcome the obstacles identified through these self-evaluations, we suggest temporal nested invariance pooling, abbreviated as TNIP, which implies temporal robustness realized by improving nested invariance pooling, abbreviated as NIP, one of the features in CDVA. Finally, benchmarks of the existing CDVA and the proposed approach are provided on several public datasets. Through this, we show that the CDVA framework is capable of boosting the retrieval performance if utilizing the proposed approach.

Robustness of a parsimonious subsurface drainage model at the French national scale

Abstract. Drainage systems are currently implemented on agricultural plots subjected to temporary or permanent waterlogging issues. Drained plots account for 9 % of all arable soils in France. As such, the need for accurate hydrological modeling is crucial, especially in an unstable future context affected by climate change. The aim of this paper is to assess the capacity of the SIDRA-RU hydrological drainage model to represent the variability in pedoclimatic conditions within French metropolitan areas and to demonstrate the utility of this model as a long-term management tool. The model is initially calibrated using the KGE′ criterion as an objective function (OF) on a large and unique database encompassing 22 plots spread across France and classified according to three main soil textures (silty, silty–clay, and clayey). The performance of SIDRA-RU is evaluated by monitoring both the set of KGE′ calibration values and the quality of simulations on each plot with respect to high and low discharges, as well as the annual drained water balance. Next, the temporal robustness of the model is assessed by conducting, on selected plots, the split-sample test capable of satisfying the data requirements. Results show that the SIDRA-RU model accurately simulates drainage discharge, especially on silty soils. The performance on clayey soils is slightly weaker than that on silty soils yet remains acceptable. Similarly, the split-sample test indicates that SIDRA-RU is temporally robust on all three soil textures. Consequently, the SIDRA-RU model closely replicates the diversity of French drained soil and could be used for its long-term management potential.

Time domain principal component analysis for rapid, real-time 2D MRI reconstruction from undersampled data.

A rapid real-time 2D accelerated method was developed for magnetic resonance imaging (MRI) using principal component analysis (PCA) in the temporal domain. This method employs a moving window of previous dynamic frames to reconstruct the current, real-time frame within this window. This technique could be particularly useful in real-time tracking applications such as in MR-guided radiotherapy, where low latency real-time reconstructions are essential. The method was tested retrospectively on 15 fully-sampled data sets of lung patient data acquired on a 3T Philips Achieva system. High frequency data are incoherently undersampled, while the central low-frequency data are always acquired to characterize the temporal fluctuations through PCA. The undersampling pattern is derived in such a way that all of k-space is acquired within a pre-determined number of frames. The missing data in the current frame are then filled in by fitting the temporal characterizations to the acquired undersampled data, using a pre-determined number of PCs. A subset of six patients was used to test the contour ability of the images. Various accelerations between 3x and 8x were tested along with the optimal number of PCs for fitting. A comparison was also performed with previous work from our group proposed by Dietz etal. as well as with a standard low resolution acquisition. In order to determine how the method would perform at lower signal to noise ratio (SNR), noise levels of 2×, 4×, and 6× were added to the 3T data. Metrics such as normalised mean square error and Dice coefficient were used to measure the reconstruction image quality and contour ability. The proposed method demonstrated good temporal robustness as consistent metrics were detected for the duration of the imaging session. It was found that the optimal number of PCs for temporal fitting was dependent on the acceleration rate. For the data tested, five PCs were found to be optimal at the acceleration rates of 3× and 4×. This number decreases to three at accelerations of 5× and 6× and further decreases to two at an acceleration rate of 8×, likely due to greater instability with fewer acquired data points. The use of too many PCs for fitting increased the chances of noisy reconstruction which affected contourability. The proposed 2D real-time MR acceleration method demonstrated greater robustness in the metrics over time when compared with previous real-time PCA methods using metrics such as normalised mean squared error, peak SNR and structural similarity up to an acceleration of 8x. Improved temporal robustness of image structure contourability and accurate definition was also demonstrated using several metrics including the Dice coefficient. Reconstruction of raw acquired data can be performed at approximately 50ms per frame using an Intel core i5 CPU. The method has the advantage of being very flexible in terms of hardware requirements as it can operate successfully on a single coil channel and does not require specialized computing power to implement in real-time.