Unseen Events Research Articles

Promoting Machine Abilities of Discovering and Utilizing Knowledge in a Unified Zero-shot Learning Paradigm

Knowledge discovery and utilization are two essential cognitive processes that enable humans to understand the world and extract new insights from their surroundings. These processes have motivated machine learning studies, particularly zero-shot learning (ZS), which seeks to identify unseen concepts through the use of side information. Previous ZS studies primarily focused on utilizing existing knowledge to infer unseen events, yet they overlook the crucial process of knowledge discovery and the integrated modeling of these knowledge-aware processes. In this study, we present a comprehensive ZS learning approach that explores and evaluates the machine's abilities of discovering and utilizing knowledge. More specifically, to emulate human-like knowledge discovery and utilization processes, we propose a novel visual-aware ZS knowledge graph completion task for evaluation, incorporating a traditional ZS image classification task. Technically, we develop a unified ZS learning paradigm named Cognitive Learner (CoLa) to foster the two knowledge-aware abilities. Including a knowledge representation learning (KRL) module and a knowledge adaptation (KA) module, CoLa adapts well to the two specified tasks with the corresponding data. Extensive experiments on large-scale datasets demonstrate CoLa models’ outstanding performance over compared methods in the two ZS tasks, illustrating their superior ability of discovering and utilizing knowledge.

Fabricated lies are more likely to be mistaken for truth over time

AbstractWhen providing eyewitness testimony, people sometimes fabricate lies that supplement the truth by embellishing or adding new information. This study investigated whether participants confuse their fabricated lies for actually witnessed events over time. In two experiments employing different eyewitness events, participants viewed an event and were then asked to lie about unseen details and events. Memory was assessed after either a 1‐week (E1a & E2) or a 4‐week (E1b & E2) retention interval. In both experiments, participants falsely reported witnessing their lies after a 4‐week retention interval, but only one experiment (E2) obtained evidence for these memory errors at the shorter retention interval of 1‐week. In addition, when assessed repeatedly, lies that participants correctly rejected as not witnessed at the 1‐week retention interval were later incorrectly endorsed as witnessed when tested again at the 4‐week retention interval, thus showing that distinguishing lies from truth became more difficult over time.

CHRONOS: A Schema-Based Event Understanding and Prediction System

Chronological and Hierarchical Reasoning Over Naturally Occurring Schemas (CHRONOS) is a system that combines language model-based natural language processing with symbolic knowledge representations to analyze and make predictions about newsworthy events. CHRONOS consists of an event-centric information extraction pipeline and a complex event schema instantiation and prediction system. Resulting predictions are detailed with arguments, event types from Wikidata, schema-based justifications, and source document provenance. We evaluate our system by its ability to capture the structure of unseen events described in news articles and make plausible predictions as judged by human annotators.

Try with Simpler – An Evaluation of Improved Principal Component Analysis in Log-based Anomaly Detection

With the rapid development of deep learning (DL), the recent trend of log-based anomaly detection focuses on extracting semantic information from log events (i.e., templates of log messages) and designing more advanced DL models for anomaly detection. Indeed, the effectiveness of log-based anomaly detection can be improved, but these DL-based techniques further suffer from the limitations of more heavy dependency on training data (such as data quality or data labels) and higher costs in time and resources due to the complexity and scale of DL models, which hinder their practical use. On the contrary, the techniques based on traditional machine learning or data mining algorithms are less dependent on training data and more efficient, but produce worse effectiveness than DL-based techniques which is mainly caused by the problem of unseen log events (some log events in incoming log messages are unseen in training data) confirmed by our motivating study. Intuitively, if we can improve the effectiveness of traditional techniques to be comparable with advanced DL-based techniques, log-based anomaly detection can be more practical. Indeed, an existing study in the other area (i.e., linking questions posted on Stack Overflow) has pointed out that traditional techniques with some optimizations can indeed achieve comparable effectiveness with the state-of-the-art DL-based technique, indicating the feasibility of enhancing traditional log-based anomaly detection techniques to some degree. Inspired by the idea of “try-with-simpler”, we conducted the first empirical study to explore the potential of improving traditional techniques for more practical log-based anomaly detection. In this work, we optimized the traditional unsupervised PCA (Principal Component Analysis) technique by incorporating a lightweight semantic-based log representation in it, called SemPCA , and conducted an extensive study to investigate the potential of SemPCA for more practical log-based anomaly detection. By comparing seven log-based anomaly detection techniques (including four DL-based techniques, two traditional techniques, and SemPCA ) on both public and industrial datasets, our results show that SemPCA achieves comparable effectiveness as advanced supervised/semi-supervised DL-based techniques while being much more stable under insufficient training data and more efficient, demonstrating that the traditional technique can still excel after small but useful adaptation.

Optimal Resiliency‐Oriented Scheduling Framework for Integrated Power‐Gas‐Transportation Networks Based on Model Predictive Control Approach to Increase Electric Load Supply

Today’s societies need a sustainable supply of energy more than ever, whereas unseen events challenge the electric power supply. The coordinated operation of a power‐gas‐transportation system can decrease the effects of such faults in the distribution level. This paper proposes a model predictive control approach for dynamic load restoration in an integrated energy system. The coordination of electric and gas networks besides the mobile energy storage (MES) units provides a novel resilient alternative to serve active and reactive loads. First, the location and time of drastic events are identified as the initialization phase in this paper using a vulnerability analysis by a master–slave problem to find the weak points of the electric grid. Then, a rolling horizon model predictive control‐based approach is proposed to make corrective decisions to serve loads. Meanwhile, a new linearization approach for the Weymouth equation has been proposed based on the binary expansion method. The proposed linear resiliency‐oriented scheduling problem is tested on IEEE 33‐bus and IEEE 69‐bus integrated with a seven‐node gas distribution grid and a six‐station transportation railway. The analysis revealed that the coordination between electric and gas resources minimizes the not‐supplied load; MES units act as certain emergency tools to serve the critical loads.

Beyond the local climate change uplift – The importance of changes in spatial structure on future fluvial flood risk in Great Britain

Widespread spatially coherent flood events can cause severe damage and disruption. Climate change has the potential to change the severity and frequency of such events. Despite this, assessment of future fluvial flood risk typically gives little to no consideration to potential changes in the spatial structure of future events. To understand the significance of this gap, climate model simulations are coupled with a national hydrological model to identify event spatially coherent present and future flood events. A statistical Empirical Copula is used to generate a large number of unseen events and linked to a national flood risk simulation model. The research finds that including changes in the spatial structure of flood events materially increases projected changes in risk when compared to conventional approaches based on local uplifts alone; increasing the projected change in Expected Annual Damage across Great Britain by a factor of ~ 1.5. The event-based approach is also shown to provide new insights into the extreme distribution fluvial risk including single event damage, damage seasons, and damage years. The results suggest the 1-in-100-year winter flood may increase from £1.3b to £2.1b, and the 1-in-100 year single event damage may rise from £1.1b today to £1.7b by the 2080s given a 4 °C rise in Global Mean Surface Temperature (assuming current adaptation policies continue and no population growth). Consequently, the findings suggest a much greater emphasis is needed on spatial ‘flood events’ if future risk is to be understood and adaptation responses appropriately framed.Graphical abstract

Statistics of sudden stratospheric warmings using a large model ensemble

AbstractUsing a large ensemble of initialised retrospective forecasts (hindcasts) from a seasonal prediction system, we explore various statistics relating to sudden stratospheric warmings (SSWs). Observations show that SSWs occur at a similar frequency during both El Niño and La Niña northern hemisphere winters. This is contrary to expectation, as the stronger stratospheric polar vortex associated with La Niña years might be expected to result in fewer of these extreme breakdowns. Here we show that this similar frequency may have occurred by chance due to the limited sample of years in the observational record. We also show that in these hindcasts, winters with two SSWs, a rare event in the observational record, on average have an increased surface impact. Multiple SSW events occur at a lower rate than expected if events were independent but somewhat surprisingly, our analysis also indicates a risk, albeit small, of winters with three or more SSWs, as yet an unseen event.

Adaptive Prognostics: A reliable RUL approach

Prognostic methodologies have found increasing use the last decade and provide a platform for remaining useful life (RUL) predictions of engineering systems utilizing condition monitoring data. Of particular interest is the reliable RUL prediction of engineering assets that either underperform or outperform due to unexpected phenomena that might occur during the operational life. These assets are often referred as outliers and the prediction of their RUL is a challenging task. The challenge is to accurately predict the RUL of an outlier without taking into account outlier’s condition monitoring data in the training process but just in the testing process. As a result, the lifetime of the testing asset is shorter (left outlier) or longer (right outlier) than the training process’ lifetimes.
 This study addresses this challenge by proposing a new adaptive model; the Similarity Learning Hidden Semi Markov Model (SLHSMM), which is an extension of the Non-Homogenous Hidden Semi Markov Model (NHHSMM). The SLHSMM uses a similarity function, such as Minkowski distances, in order firstly to quantify the similarity between the testing asset and each training asset and secondly to adapt the trained parameters of the NHHSMM. To demonstrate the effectiveness of the proposed adaptive methodology, composite structures have been used as a validation engineering asset. In particular, the training data set consists of strain data collected from open-hole carbon–epoxy specimens, which were subjected to fatigue loading only, while the testing data set consists of strain data collected from specimens that were subjected to fatigue and in-situ impact loading, which can be considered as an unexpected phenomenon and unseen event regarding the training process. 
 Utilizing the aforementioned strain data the SLHSMM RUL predictions and the NHHSMM RUL predictions were compared, so as to verify that the SLHSMM provides better prognostics than the NHHSMM. SLHSMM provides better predictions in comparison to the NHHSMM for all the test cases, demonstrating its capability to adapt to unexpected phenomena and integrate unforeseen data to the prognostics course.

Noah: Reinforcement-Learning-Based Rate Limiter for Microservices in Large-Scale E-Commerce Services.

Modern large-scale online service providers typically deploy microservices into containers to achieve flexible service management. One critical problem in such containerbased microservice architectures is to control the arrival rate of requests in the containers to avoid containers from being overloaded. In this article, we present our experience of rate limit for the containers in Alibaba, one of the largest e-commerce services in the world. Given the highly diverse characteristics of containers in Alibaba, we point out that the existing rate limit mechanisms cannot meet our demand. Thus, we design Noah, a dynamic rate limiter that can automatically adapt to the specific characteristic of each container without human efforts. The key idea of Noah is to use deep reinforcement learning (DRL) that automatically infers the most suitable configuration for each container. To fully embrace the advantages of DRL in our context, Noah addresses two technical challenges. First, Noah uses a lightweight system monitoring mechanism to collect container status. In this way, it minimizes the monitoring overhead while ensuring a timely reaction to system load changes. Second, Noah injects synthetic extreme data when training its models. Thus, its model gains knowledge on unseen special events and hence remains highly available in extreme scenarios. To guarantee model convergence with the injected training data, Noah adopts task-specific curriculum learning to train the model from normal data to extreme data gradually. Noah has been deployed in the production of Alibaba for two years, serving more than 50 000 containers and around 300 types of microservice applications. Experimental results show that Noah can well adapt to three common scenarios in the production environment. It effectively achieves better system availability and shorter request response time compared with four state-of-the-art rate limiters.

Developing Low‐Likelihood Climate Storylines for Extreme Precipitation Over Central Europe

AbstractHeavy precipitation and associated flooding during the cold season, such as the 1993 flood in central Europe (CEU), are a major threat to society and ecosystems. Due to the lack of long homogenous climate data and methodological frameworks, it is challenging to estimate how extreme precipitation could get and what the physical drivers are. This study presents two complementary strategies to extrapolate beyond the precipitation records: (a) statistical estimates based on fitting generalized extreme value distributions, providing their probabilistic information on return periods and, (b) ensemble boosting, a model‐based re‐initialization of heavy precipitation in large ensembles, providing a physical coherent storyline in space and time, however, with no direct quantification of its probability. Both show that 3‐day accumulated precipitation maxima can be substantially exceeded over CEU of around 30%–40%, but even higher magnitudes cannot be ruled out in the near future. An empirical orthogonal function analysis reveals that certain sea level pressure patterns, partly reminding of atmospheric rivers are more often associated with heavy precipitation than more moderate events. Additionally, ensemble boosting is a suitable tool for case studies to analyze how extreme heavy precipitation as for the event in 1993 can be simulated. By boosting a 1993‐analog, one‐quarter of the resulting storylines show increased rainfall than observed, due to a stronger north‐south pressure gradient that may have exacerbated the flooding. Overall, the precipitation estimates demonstrate that ensemble boosting is a complementary method to statistical tools and suitable for stress testing, for example, infrastructure protection measures against potentially unseen heavy precipitation events.

Hierarchical Event Grounding

Event grounding aims at linking mention references in text corpora to events from a knowledge base (KB). Previous work on this task focused primarily on linking to a single KB event, thereby overlooking the hierarchical aspects of events. Events in documents are typically described at various levels of spatio-temporal granularity. These hierarchical relations are utilized in downstream tasks of narrative understanding and schema construction. In this work, we present an extension to the event grounding task that requires tackling hierarchical event structures from the KB. Our proposed task involves linking a mention reference to a set of event labels from a subevent hierarchy in the KB. We propose a retrieval methodology that leverages event hierarchy through an auxiliary hierarchical loss. On an automatically created multilingual dataset from Wikipedia and Wikidata, our experiments demonstrate the effectiveness of the hierarchical loss against retrieve and re-rank baselines. Furthermore, we demonstrate the systems' ability to aid hierarchical discovery among unseen events. Code is available at https://github.com/JefferyO/Hierarchical-Event-Grounding

Scalable Pythagorean Mean based Incident Detection in Smart Transportation Systems

Modern smart cities need smart transportation solutions to quickly detect various traffic emergencies and incidents in the city to avoid cascading traffic disruptions. To materialize this, roadside units and ambient transportation sensors are being deployed to collect speed data that enables the monitoring of traffic conditions on each road segment. In this paper, we first propose a scalable data-driven anomaly-based traffic incident detection framework for a city-scale smart transportation system. Specifically, we propose an incremental region growing approximation algorithm for optimal Spatio-temporal clustering of road segments and their data; such that road segments are strategically divided into highly correlated clusters. The highly correlated clusters enable identifying a Pythagorean Mean-based invariant as an anomaly detection metric that is highly stable under no incidents but shows a deviation in the presence of incidents. We learn the bounds of the invariants in a robust manner such that anomaly detection can generalize to unseen events, even when learning from real noisy data. Second, using cluster-level detection, we propose a folded Gaussian classifier to pinpoint the particular segment in a cluster where the incident happened in an automated manner. We perform extensive experimental validation using mobility data collected from four cities in Tennessee, compare with the state-of-the-art ML methods, to prove that our method can detect incidents within each cluster in real-time and outperforms known ML methods.

Potential for surprising heat and drought events in wheat-producing regions of USA and China

Previous analyses of the possibility of global breadbasket failures have extrapolated risks based on historical relationships between climate and yields. However, climate change is causing unprecedented events globally, which could exceed critical thresholds and reduce yields, even if there is no historical precedent. This means that we are likely underestimating climate risks to our food system. In the case of wheat, parts of the USA and China show little historical relationship between yields and temperature, but extreme temperatures are now possible that exceed critical physiological thresholds in wheat plants. UNprecedented Simulated Extreme ENsemble (UNSEEN) approaches use large ensembles to generate plausible unprecedented events, which can inform our assessment of the risk to crops. We use the UNSEEN approach with a large ensemble of archived seasonal forecasts to generate thousands of plausible events over the last 40 years and compare the results with historically observed extreme temperature and precipitation. In the US midwest, extreme temperatures that would have happened approximately 1-in-100-years in 1981 now have a return period of 1-in-6 years, while in China, the current return period is on the order of 1-in-16 years. This means that in the US midwest, extreme temperatures that used to have a 1% chance to occur in 1981 now have a 17% chance to occur in any given year, while in China, the chance increased from 1% to 6%. Record-breaking years exceeding critical thresholds for enzymes in the wheat plant are now more likely than in the past, and these record-breaking hot years are associated with extremely dry conditions in both locations. Using geopotential height and wind anomalies from the UNSEEN ensemble, we demonstrate that strong winds over land pull dry air towards the regions these during extremely hot and dry unseen events. We characterize plausible extremes from the UNSEEN ensemble that can be used to help imagine otherwise unforeseen events, including a compound event in which high impacts co-occur in both regions, informing adaptation planning in these regions. Recent temperature extremes, especially in the US midwest, are unlikely to be a good proxy for what to expect in the next few years of today’s climate, and local stakeholders might perceive their risk to be lower than it really is. We find that there is a high potential for surprise in these regions if people base risk analyses solely on historical datasets.

Prophecies in The Holy Qur’an Attesting Its Divine Origin

A fundamental pillar in the Islamic faith is the belief that Allah is the only Being who knows how the unseen events and facts will exactly happen in the future. Therefore, it was reasonable to find prophecies in the Qur’an as evidence to prove that this book is the truth from God. The present article aimed to shed the light on the major prophecies mentioned in the Holy Qur’an testifying for its truthfulness as a religious book sent from God to his last and final messenger, Prophet Muhammad peace and blessings upon him (PBUH). Eight Qur’anic prophecies were categorized and discussed in this article. The first category comprised prophecies that came true during the Prophetic life span, which we referred to as “near-future happenings”. The second category included events that have come true after Prophet Muhammad PBUH has passed away which we termed “far-future happenings”. The third category included far-future news that was foretold to uncover an ancient event. The fourth category covers two undeniable consistent facts that become more evident as time passes. Appropriate understanding of these prophecies is essential for every Muslim to present and prove Islam to people as the religion of truth.
 
 Keywords: Prophecy, Qur’an, proof, divine, origin.

Microgrid energy scheduling under uncertain extreme weather: Adaptation from parallelized reinforcement learning agents

Microgrids are useful solutions for integrating renewable energy resources and providing seamless green electricity to minimize carbon footprint. In recent years, extreme weather events happened often worldwide and caused significant economic and societal losses. Such events bring uncertainties to the microgrid energy scheduling problems and increase the challenges of microgrid operation. Traditional optimization approaches suffer from the inaccuracy of the uncertain microgrid model and the unseen events. Existing reinforcement learning (RL) - based approaches are also hampered by the limited generalization and the increasing computational burden when stochastic formulations are required to accommodate the uncertainties. This paper proposes a new parallelized reinforcement learning (PRL) method based on the probabilistic events to handle the microgrid energy uncertainties. Specifically, several local learning agents are employed to interact with pertinent microgrid environments in a distributed manner and report outcomes to the global agent, which will optimize microgrid energy resources online during extreme events. The stochastic microgrid energy optimization problem is reformulated to include all possible scenarios with probabilities. The advantage estimate functions of learning agents are designed with a backward sweep to transfer the outcomes to the value function updating process. Two simulation studies, stochastic optimization and online testing, are performed to compare with several existing RL approaches. Results substantiate that the proposed PRL method can achieve up to 20% optimization performance improvement with 4 and 28 times less computation cost than Q-learning with experience replay and multi-agent Q-learning approaches, respectively.

Grasping the scale of events: Voices from Chernobyl between the historical and the monumental

ABSTRACT The paper discusses the significance new forms of literary narration can have on the representation of groundbreaking historical events. Based initially on Hayden White’s work and his term modernist event, we argue that new kinds of events need new ways of writing history. However, neither has White given any concrete persuasive examples of how his paradigmatic historical work might look like nor have his critics given enough attention to his considerations on the matter. By focusing our analysis on Svetlana Alexievich’s literary work and specifically on her book Voices from Chernobyl, we try to achieve exactly this: to analyze the innovative literary features that Alexievich develops in the testimonial narratives she builds and to highlight the importance they have for representing the past. For this purpose, we take a closer look at the thematic connection of the testimonies and the sense of non-linearity they create; comment on her success to approach in this way the ‘unseen event’ and bring the reader closer to the horrific and confusing reality that the witnesses describe; and show how literary techniques like the use of parataxis can efficiently grasp and mediate the differences in the temporal scale of hard-to-comprehend historical events and their consequences. Especially examining how Alexievich deals with this temporal particularity in her narrative, the paper suggests new ways to deal with the complex temporalities and discontinuities that go beyond modern historical thinking.

Pre-birth acquisition of personhood: Incremental accrual of attributes as the framework for individualization by serial and concurrently acting developmental factors.

Discrete events and processes influence development of individual humans. Attribution of personhood to any individual human being cannot be disconnected from the underlying biological events and processes of early human development. Nonetheless, the philosophical, sociological and legal components that are integral to the meaning of the term as commonly used cannot be deduced from biology alone. The challenge for biomedical scientists to inform discussion in this arena then rests on profiling the key biological events and processes that must be assessed when considering how one might objectively reason about the task of superimposing the concept of personhood onto the developing biological entity of a potential human being. Endogenous genetic and epigenetic events and exogenous developmental milieu processes diversify developmental trajectories of potential individual humans prior to livebirth. First, fertilization and epigenetic resetting of each individual's organismic clock to time zero (t = 0) at the gastrulation/primitive streak stage (day 15 of embryogenesis), are two discrete unseen biological events that impact a potential individual human's attributes. Second, those two discrete unseen biological events are immersed in the continuous developmental process spanning pre-fertilization and gestation, further driving individualization of diverse attributes of each future human before the third discrete and blatant biological event of parturition and livebirth. Exposures of the gravida to multiple diverse exogenous exposures means that morphogenesis and physiogenesis of every embryo/fetus has individualized attributes for its future human lifespan. Our proposed framework based on the biological discrete events and processes spanning pre-fertilization and prenatal development, implies that personhood should be incrementally attributed, and societal protections should be graduated and applied progressively across the pre-birth timespan.

A transformer-based approach for novel fault detection and fault classification/diagnosis in manufacturing: A rotary system application

Owing to the rapid development of Industry 4.0, new sensing and communication technologies have made vast amounts of untapped process data available. In order to transform such data assets into strong insights and knowledge that support manufacturing decisions, condition-based maintenance (CBM) and fault detection and diagnosis (FDD) have become effective ways to enhance equipment reliability and reduce costs. A successful data-driven FDD method must not only be capable of identifying the types of known faults, but also in detecting unseen or uncharacterized events during manufacturing system operation. To this end, this paper presents a Transformer-based classifier that can efficiently identify different known types and severity levels of fault conditions, in addition to novel fault detection. In this method, time-frequency spectrograms transformed from raw vibration signals are input to the classifier for known fault classification. Utilizing the advanced feature extracting performance of the classifier, a simple yet effective technique based on Mahalanobis distance is adopted to detect whether the fault comes from a previously unseen fault condition. When a novel condition is detected, the model is subsequently retrained using the novel data in an incremental learning manner. The proposed method is verified by an experimental case study with data collected from a testbed that has many features representative of common manufacturing equipment. The results demonstrated that the proposed method has superior performance in both fault diagnosis and novelty identification when compared with the baseline models and a cutting-edge model.

A metric-learning method for few-shot cross-event rumor detection

With the rapid development of social media, quickly detecting rumors on social media has become vitally crucial. However, there exists the following challenges. 1) Rumors are always flooded with time-critical events, where large-scale labeled datasets are difficult to obtain. 2) Although historic events have sufficient labels, the performance of models tends to degrade on the newly emergent events due to event difference shift. Facing these challenges, in this study, we attempt to leverage the idea of few-shot learning which aims to quickly acquire knowledge on unseen events with a few labeled samples by sufficiently learning from old events with a number of verified samples. Different from few-shot learning tasks in the literature, rumors in the same class of different events (no matter historical events or new events) are likely to contain coincident features in their embedding space. Therefore, we validate two classical metric learning methods, the prototypical network (PN) and the relation network (RN) which are able to capture the class-level representations in few-shot learning settings, to explore the effectiveness of metric learning methods for cross-event rumor detection. Our proposed model contains two stages corresponding to Base-Classifier pre-trained module and Base-Meta training module. The Base-Classifier pre-trained module is a classification model trained on old events. Then its last layer for class prediction is removed and the remains of the module is viewed as an encoder. The Base-Meta training module fine-tunes the encoder, meanwhile trains a selected metric learning model with episodic training strategies on old events. Empirical tests on novel events have showed that our model can outperform the state-of-the-art baseline models on the benchmark cross-event rumor datasets PHEME5 and PHEME9. What’s more, the model can improve the performance of cross-data rumor detection, where the model is trained on Twitter15, but tested on Twitter16.

A Foreshortened Future and the Trauma of a Dying Earth in Christopher Nolan’s Tenet

An experience of anxiety is caused by the anticipation of unseen future events, especially in the context of ecological trauma, where the prospect of a world without humans in the distant future is often portrayed through mediated cinematic memories. As a result of anthropological intervention on our planet, it is feared that humanity will cease to exist unless steps are taken to prevent it. Furthermore, as climate change intensifies, humans are left with more questions regarding their future. One recent film that addresses this issue is Christopher Nolan’s Tenet (2020). The film explores the concept of a dying Earth in the future, whose inhabitants seek help from the past to restore the planet’s balance by reversing entropy. Despite failing to provide any remedy by revealing ‘What’s happened happened’, a viewpoint that Christopher Nolan, as an auteur, has already presented in his previous film Interstellar (2014), the film leaves the audience with the question, what is the purpose of projecting an unseen trauma? By evaluating the events that contributed to the image of a crumbling Earth in the film, this paper seeks to examine the concept of future trauma as an indication of post-traumatic stress disorder while simultaneously exploring it as a film that acknowledges Nolan’s own anxiety over the decline of a medium he cherishes.