Transformer models coupled with a simplified molecular line entry system (SMILES) have recently proven to be a powerful combination for solving challenges in cheminformatics. These models, however, are often developed specifically for a single application and can be very resource-intensive to train. In this work we present the Chemformer model—a Transformer-based model which can be quickly applied to both sequence-to-sequence and discriminative cheminformatics tasks. Additionally, we show that self-supervised pre-training can improve performance and significantly speed up convergence on downstream tasks. On direct synthesis and retrosynthesis prediction benchmark datasets we publish state-of-the-art results for top-1 accuracy. We also improve on existing approaches for a molecular optimisation task and show that Chemformer can optimise on multiple discriminative tasks simultaneously. Models, datasets and code will be made available after publication.
Purpose-led Publishing is a coalition of three not-for-profit publishers in the field of physical sciences: AIP Publishing, the American Physical Society and IOP Publishing.
Together, as publishers that will always put purpose above profit, we have defined a set of industry standards that underpin high-quality, ethical scholarly communications.
We are proudly declaring that science is our only shareholder.
ISSN: 2632-2153
Machine Learning: Science and Technology is a multidisciplinary open access journal that bridges the application of machine learning across the sciences with advances in machine learning methods and theory as motivated by physical insights.
Open all abstracts, in this tab
Ross Irwin et al 2022 Mach. Learn.: Sci. Technol. 3 015022
Tanujit Chakraborty et al 2024 Mach. Learn.: Sci. Technol. 5 011001
Generative adversarial networks (GANs) have rapidly emerged as powerful tools for generating realistic and diverse data across various domains, including computer vision and other applied areas, since their inception in 2014. Consisting of a discriminative network and a generative network engaged in a minimax game, GANs have revolutionized the field of generative modeling. In February 2018, GAN secured the leading spot on the 'Top Ten Global Breakthrough Technologies List' issued by the Massachusetts Science and Technology Review. Over the years, numerous advancements have been proposed, leading to a rich array of GAN variants, such as conditional GAN, Wasserstein GAN, cycle-consistent GAN, and StyleGAN, among many others. This survey aims to provide a general overview of GANs, summarizing the latent architecture, validation metrics, and application areas of the most widely recognized variants. We also delve into recent theoretical developments, exploring the profound connection between the adversarial principle underlying GAN and Jensen–Shannon divergence while discussing the optimality characteristics of the GAN framework. The efficiency of GAN variants and their model architectures will be evaluated along with training obstacles as well as training solutions. In addition, a detailed discussion will be provided, examining the integration of GANs with newly developed deep learning frameworks such as transformers, physics-informed neural networks, large language models, and diffusion models. Finally, we reveal several issues as well as future research outlines in this field.
Ivan S Novikov et al 2021 Mach. Learn.: Sci. Technol. 2 025002
The subject of this paper is the technology (the 'how') of constructing machine-learning interatomic potentials, rather than science (the 'what' and 'why') of atomistic simulations using machine-learning potentials. Namely, we illustrate how to construct moment tensor potentials using active learning as implemented in the MLIP package, focusing on the efficient ways to automatically sample configurations for the training set, how expanding the training set changes the error of predictions, how to set up ab initio calculations in a cost-effective manner, etc. The MLIP package (short for Machine-Learning Interatomic Potentials) is available at https://mlip.skoltech.ru/download/.
Mario Krenn et al 2020 Mach. Learn.: Sci. Technol. 1 045024
The discovery of novel materials and functional molecules can help to solve some of society's most urgent challenges, ranging from efficient energy harvesting and storage to uncovering novel pharmaceutical drug candidates. Traditionally matter engineering–generally denoted as inverse design–was based massively on human intuition and high-throughput virtual screening. The last few years have seen the emergence of significant interest in computer-inspired designs based on evolutionary or deep learning methods. The major challenge here is that the standard strings molecular representation SMILES shows substantial weaknesses in that task because large fractions of strings do not correspond to valid molecules. Here, we solve this problem at a fundamental level and introduce SELFIES (SELF-referencIng Embedded Strings), a string-based representation of molecules which is 100% robust. Every SELFIES string corresponds to a valid molecule, and SELFIES can represent every molecule. SELFIES can be directly applied in arbitrary machine learning models without the adaptation of the models; each of the generated molecule candidates is valid. In our experiments, the model's internal memory stores two orders of magnitude more diverse molecules than a similar test with SMILES. Furthermore, as all molecules are valid, it allows for explanation and interpretation of the internal working of the generative models.
Philippe Schwaller et al 2021 Mach. Learn.: Sci. Technol. 2 015016
Artificial intelligence is driving one of the most important revolutions in organic chemistry. Multiple platforms, including tools for reaction prediction and synthesis planning based on machine learning, have successfully become part of the organic chemists' daily laboratory, assisting in domain-specific synthetic problems. Unlike reaction prediction and retrosynthetic models, the prediction of reaction yields has received less attention in spite of the enormous potential of accurately predicting reaction conversion rates. Reaction yields models, describing the percentage of the reactants converted to the desired products, could guide chemists and help them select high-yielding reactions and score synthesis routes, reducing the number of attempts. So far, yield predictions have been predominantly performed for high-throughput experiments using a categorical (one-hot) encoding of reactants, concatenated molecular fingerprints, or computed chemical descriptors. Here, we extend the application of natural language processing architectures to predict reaction properties given a text-based representation of the reaction, using an encoder transformer model combined with a regression layer. We demonstrate outstanding prediction performance on two high-throughput experiment reactions sets. An analysis of the yields reported in the open-source USPTO data set shows that their distribution differs depending on the mass scale, limiting the data set applicability in reaction yields predictions.
Steven Dahdah and James Richard Forbes 2024 Mach. Learn.: Sci. Technol. 5 025038
This paper proposes a method to identify a Koopman model of a feedback-controlled system given a known controller. The Koopman operator allows a nonlinear system to be rewritten as an infinite-dimensional linear system by viewing it in terms of an infinite set of lifting functions. A finite-dimensional approximation of the Koopman operator can be identified from data by choosing a finite subset of lifting functions and solving a regression problem in the lifted space. Existing methods are designed to identify open-loop systems. However, it is impractical or impossible to run experiments on some systems, such as unstable systems, in an open-loop fashion. The proposed method leverages the linearity of the Koopman operator, along with knowledge of the controller and the structure of the closed-loop (CL) system, to simultaneously identify the CL and plant systems. The advantages of the proposed CL Koopman operator approximation method are demonstrated in simulation using a Duffing oscillator and experimentally using a rotary inverted pendulum system. An open-source software implementation of the proposed method is publicly available, along with the experimental dataset generated for this paper.
Moritz Hoffmann et al 2022 Mach. Learn.: Sci. Technol. 3 015009
Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables, dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software. Deeptime can be found under https://deeptime-ml.github.io/.
Arsenii Senokosov et al 2024 Mach. Learn.: Sci. Technol. 5 015040
Image classification, a pivotal task in multiple industries, faces computational challenges due to the burgeoning volume of visual data. This research addresses these challenges by introducing two quantum machine learning models that leverage the principles of quantum mechanics for effective computations. Our first model, a hybrid quantum neural network with parallel quantum circuits, enables the execution of computations even in the noisy intermediate-scale quantum era, where circuits with a large number of qubits are currently infeasible. This model demonstrated a record-breaking classification accuracy of 99.21% on the full MNIST dataset, surpassing the performance of known quantum–classical models, while having eight times fewer parameters than its classical counterpart. Also, the results of testing this hybrid model on a Medical MNIST (classification accuracy over 99%), and on CIFAR-10 (classification accuracy over 82%), can serve as evidence of the generalizability of the model and highlights the efficiency of quantum layers in distinguishing common features of input data. Our second model introduces a hybrid quantum neural network with a Quanvolutional layer, reducing image resolution via a convolution process. The model matches the performance of its classical counterpart, having four times fewer trainable parameters, and outperforms a classical model with equal weight parameters. These models represent advancements in quantum machine learning research and illuminate the path towards more accurate image classification systems.
Leopoldo Sarra et al 2024 Mach. Learn.: Sci. Technol. 5 025029
Despite rapid progress in the field, it is still challenging to discover new ways to leverage quantum computation: all quantum algorithms must be designed by hand, and quantum mechanics is notoriously counterintuitive. In this paper, we study how artificial intelligence, in the form of program synthesis, may help overcome some of these difficulties, by showing how a computer can incrementally learn concepts relevant to quantum circuit synthesis with experience, and reuse them in unseen tasks. In particular, we focus on the decomposition of unitary matrices into quantum circuits, and show how, starting from a set of elementary gates, we can automatically discover a library of useful new composite gates and use them to decompose increasingly complicated unitaries.
Pablo Lemos et al 2023 Mach. Learn.: Sci. Technol. 4 045002
We present an approach for using machine learning to automatically discover the governing equations and unknown properties (in this case, masses) of real physical systems from observations. We train a 'graph neural network' to simulate the dynamics of our Solar System's Sun, planets, and large moons from 30 years of trajectory data. We then use symbolic regression to correctly infer an analytical expression for the force law implicitly learned by the neural network, which our results showed is equivalent to Newton's law of gravitation. The key assumptions our method makes are translational and rotational equivariance, and Newton's second and third laws of motion. It did not, however, require any assumptions about the masses of planets and moons or physical constants, but nonetheless, they, too, were accurately inferred with our method. Naturally, the classical law of gravitation has been known since Isaac Newton, but our results demonstrate that our method can discover unknown laws and hidden properties from observed data.
Open all abstracts, in this tab
Aya Messai et al 2024 Mach. Learn.: Sci. Technol. 5 025052
Meningitis, characterized by meninges and cerebrospinal fluid inflammation, poses diagnostic challenges due to diverse clinical manifestations. This work introduces an explainable AI automatic medical decision methodology that determines critical features and their relevant values for the differential diagnosis of various meningitis cases. We proceed with knowledge acquisition to define the rules for this research. Currently, we have established the etiological diagnosis of Meningococcaemia, Meningococcal Meningitis, Tuberculous Meningitis, Aseptic Meningitis, Haemophilus influenzae Meningitis, and Pneumococcal Meningitis. The data preprocessing was conducted after collecting data from samples with meningitis diseases at Setif Hospital in Algeria. Tree-based ensemble methods were then applied to assess the model's performance. Finally, we implement an XAI agnostic explainability approach based on the SHapley Additive exPlanations technique to attribute each feature's contribution to the model's output. Experiments were conducted on the collected dataset and the SINAN database, obtained from the Brazilian Government's Health Information System on Notifiable Diseases, which comprises 6729 patients aged over 18 years. The Extreme Gradient Boosting model was chosen for its superior performance metrics (Accuracy: 0.90, AUROC: 0.94, and F1-score: 0.98). Setif's hospital data revealed notable performance metrics (Accuracy: 0.7143, F1-Score: 0.7857). This study's findings showcase each feature's contribution to the model's predictions and diagnosis. It also reveals critical biomarker ranges associated with distinct types of Meningitis. Significant diagnostic effect was found for Meningococcal Meningitis with elevated neutrophil levels (40%) and balanced lymphocyte levels (40%–60%). Tuberculous Meningitis demonstrated low neutrophil levels (60%) and elevated lymphocyte levels (60%). H. influenzae meningitis exhibited a predominance of neutrophils (80%), while Aseptic meningitis showed lower neutrophil levels (40%) and lymphocyte levels within the range of 50%–60%. The majority of the AI automatic medical decision results are twinned with validation by our team of infectious disease experts, confirming the alignment of algorithmic diagnoses with clinical practices.
Kevin Zeng et al 2024 Mach. Learn.: Sci. Technol. 5 025053
While many phenomena in physics and engineering are formally high-dimensional, their long-time dynamics often live on a lower-dimensional manifold. The present work introduces an autoencoder framework that combines implicit regularization with internal linear layers and L2 regularization (weight decay) to automatically estimate the underlying dimensionality of a data set, produce an orthogonal manifold coordinate system, and provide the mapping functions between the ambient space and manifold space, allowing for out-of-sample projections. We validate our framework's ability to estimate the manifold dimension for a series of datasets from dynamical systems of varying complexities and compare to other state-of-the-art estimators. We analyze the training dynamics of the network to glean insight into the mechanism of low-rank learning and find that collectively each of the implicit regularizing layers compound the low-rank representation and even self-correct during training. Analysis of gradient descent dynamics for this architecture in the linear case reveals the role of the internal linear layers in leading to faster decay of a 'collective weight variable' incorporating all layers, and the role of weight decay in breaking degeneracies and thus driving convergence along directions in which no decay would occur in its absence. We show that this framework can be naturally extended for applications of state-space modeling and forecasting by generating a data-driven dynamic model of a spatiotemporally chaotic partial differential equation using only the manifold coordinates. Finally, we demonstrate that our framework is robust to hyperparameter choices.
Cameron J LaMack and Eric M Schearer 2024 Mach. Learn.: Sci. Technol. 5 025051
This paper explores the use of Gaussian process regression for system identification in control engineering. It introduces two novel approaches that utilize the data from a measured global system error. The paper demonstrates these approaches by identifying a simulated system with three subsystems, a one degree of freedom mass with two antagonist muscles. The first approach uses this whole-system error data alone, achieving accuracy on the same order of magnitude as subsystem-specific data ( of total model errors). This is significant, as it shows that the same data set can be used to identify unique subsystems, as opposed to requiring a set of data descriptive of only a single subsystem. The second approach demonstrated in this paper mixes traditional subsystem-specific data with the whole system error data, achieving up to 98.71% model improvement.
M Klein et al 2024 Mach. Learn.: Sci. Technol. 5 025050
Under different plasma conditions and electric fields in a complex plasma the plasma particles organize themselves in a string-like or chain-like manner. A phase transition from string-like to an isotropic particle distribution is observed at different electrical conditions. The streaming of charged ions around plasma particles with the surrounding electric field gives the plasma its electrorheological properties. The visibility of individual particles in a complex plasma opens up the opportunity to examine properties and phase transitions of such electrorheological fluids in detail. Because of the limited one-dimensional symmetry, determining the configuration of a particle and recognizing strings in particle distributions is not always straightforward. Several approaches have already been used to analyse particle clouds while either considering each particle locally or considering the particle cloud as a whole without providing information about single particle configurations. This paper presents a new machine learning approach that takes advantage of particle distributions over the entire particle cloud and detects all string-like particles at once, using a convolutional neural network in form of an encoder-decoder network with asymmetric kernel convolutions. This not only enhances the result quality but also accelerates the evaluation process, possibly enabling real-time analyses on electrorheological phase transitions, while achieving an accuracy of over 95% on manually labelled data.
Harvey Cao et al 2024 Mach. Learn.: Sci. Technol. 5 025049
Quantum many-body scarred systems contain both thermal and non-thermal scar eigenstates in their spectra. When these systems are quenched from special initial states which share high overlap with scar eigenstates, the system undergoes dynamics with atypically slow relaxation and periodic revival. This scarring phenomenon poses a potential avenue for circumventing decoherence in various quantum engineering applications. Given access to an unknown scar system, current approaches for identification of special states leading to non-thermal dynamics rely on costly measures such as entanglement entropy. In this work, we show how two dimensionality reduction techniques, multidimensional scaling and intrinsic dimension estimation, can be used to learn structural properties of dynamics in the PXP model and distinguish between thermal and scar initial states. The latter method is shown to be robust against limited sample sizes and experimental measurement errors.
Open all abstracts, in this tab
Tanujit Chakraborty et al 2024 Mach. Learn.: Sci. Technol. 5 011001
Generative adversarial networks (GANs) have rapidly emerged as powerful tools for generating realistic and diverse data across various domains, including computer vision and other applied areas, since their inception in 2014. Consisting of a discriminative network and a generative network engaged in a minimax game, GANs have revolutionized the field of generative modeling. In February 2018, GAN secured the leading spot on the 'Top Ten Global Breakthrough Technologies List' issued by the Massachusetts Science and Technology Review. Over the years, numerous advancements have been proposed, leading to a rich array of GAN variants, such as conditional GAN, Wasserstein GAN, cycle-consistent GAN, and StyleGAN, among many others. This survey aims to provide a general overview of GANs, summarizing the latent architecture, validation metrics, and application areas of the most widely recognized variants. We also delve into recent theoretical developments, exploring the profound connection between the adversarial principle underlying GAN and Jensen–Shannon divergence while discussing the optimality characteristics of the GAN framework. The efficiency of GAN variants and their model architectures will be evaluated along with training obstacles as well as training solutions. In addition, a detailed discussion will be provided, examining the integration of GANs with newly developed deep learning frameworks such as transformers, physics-informed neural networks, large language models, and diffusion models. Finally, we reveal several issues as well as future research outlines in this field.
Jakub Rydzewski et al 2023 Mach. Learn.: Sci. Technol. 4 031001
Analyzing large volumes of high-dimensional data requires dimensionality reduction: finding meaningful low-dimensional structures hidden in their high-dimensional observations. Such practice is needed in atomistic simulations of complex systems where even thousands of degrees of freedom are sampled. An abundance of such data makes gaining insight into a specific physical problem strenuous. Our primary aim in this review is to focus on unsupervised machine learning methods that can be used on simulation data to find a low-dimensional manifold providing a collective and informative characterization of the studied process. Such manifolds can be used for sampling long-timescale processes and free-energy estimation. We describe methods that can work on datasets from standard and enhanced sampling atomistic simulations. Unlike recent reviews on manifold learning for atomistic simulations, we consider only methods that construct low-dimensional manifolds based on Markov transition probabilities between high-dimensional samples. We discuss these techniques from a conceptual point of view, including their underlying theoretical frameworks and possible limitations.
James Stokes et al 2023 Mach. Learn.: Sci. Technol. 4 021001
This article aims to summarize recent and ongoing efforts to simulate continuous-variable quantum systems using flow-based variational quantum Monte Carlo techniques, focusing for pedagogical purposes on the example of bosons in the field amplitude (quadrature) basis. Particular emphasis is placed on the variational real- and imaginary-time evolution problems, carefully reviewing the stochastic estimation of the time-dependent variational principles and their relationship with information geometry. Some practical instructions are provided to guide the implementation of a PyTorch code. The review is intended to be accessible to researchers interested in machine learning and quantum information science.
Bahram Jalali et al 2022 Mach. Learn.: Sci. Technol. 3 041001
The phenomenal success of physics in explaining nature and engineering machines is predicated on low dimensional deterministic models that accurately describe a wide range of natural phenomena. Physics provides computational rules that govern physical systems and the interactions of the constituents therein. Led by deep neural networks, artificial intelligence (AI) has introduced an alternate data-driven computational framework, with astonishing performance in domains that do not lend themselves to deterministic models such as image classification and speech recognition. These gains, however, come at the expense of predictions that are inconsistent with the physical world as well as computational complexity, with the latter placing AI on a collision course with the expected end of the semiconductor scaling known as Moore's Law. This paper argues how an emerging symbiosis of physics and AI can overcome such formidable challenges, thereby not only extending AI's spectacular rise but also transforming the direction of engineering and physical science.
April M Miksch et al 2021 Mach. Learn.: Sci. Technol. 2 031001
Recent advances in machine-learning interatomic potentials have enabled the efficient modeling of complex atomistic systems with an accuracy that is comparable to that of conventional quantum-mechanics based methods. At the same time, the construction of new machine-learning potentials can seem a daunting task, as it involves data-science techniques that are not yet common in chemistry and materials science. Here, we provide a tutorial-style overview of strategies and best practices for the construction of artificial neural network (ANN) potentials. We illustrate the most important aspects of (a) data collection, (b) model selection, (c) training and validation, and (d) testing and refinement of ANN potentials on the basis of practical examples. Current research in the areas of active learning and delta learning are also discussed in the context of ANN potentials. This tutorial review aims at equipping computational chemists and materials scientists with the required background knowledge for ANN potential construction and application, with the intention to accelerate the adoption of the method, so that it can facilitate exciting research that would otherwise be challenging with conventional strategies.
Open all abstracts, in this tab
Srikanth et al
The demand for specialized hardware to train AI models has increased in tandem with the increase in the model complexity over the recent years. Graphics Processing Unit (GPU) is one such hardware that is capable of paralellizing operations performed on a large chunk of data. Companies like Nvidia, AMD, and Google have been constantly scaling-up the hardware performance as fast as they can. Nevertheless, there is still a gap between the required processing power and processing capacity of the hardware. To increase the hardware utilization, the software has to be optimized too. In this paper, we present some general GPU optimization techniques we used to efficiently train the optiGAN model, a Generative Adversarial Network that is capable of generating multidimensional probability distributions of optical photons at the photodetector face in radiation detectors, on an 8GB Nvidia Quadro RTX 4000 GPU. We analyze and compare the performances of all the optimizations based on the execution time and the memory consumed using the Nvidia Nsight Systems profiler tool. The optimizations gave approximately a 4.5x increase in the runtime performance when compared to a naive training on the GPU, without compromising the model performance. Finally we discuss optiGANs future work and how we are planning to scale the model on GPUs.
Kipp et al
The anomalous Hall effect has been front and center in solid state research and material science for over a century now, and the complex transport phenomena in nontrivial magnetic textures have gained an increasing amount of attention, both in theoretical and experimental studies. However, a clear path forward to capturing the influence of magnetization dynamics on anomalous Hall effect even in smallest frustrated magnets or spatially extended magnetic textures is still intensively sought after. In this work, we present an expansion of the anomalous Hall tensor into symmetrically invariant objects, encoding the magnetic configuration up to arbitrary power of spin. We show that these symmetric invariants can be utilized in conjunction with advanced regularization techniques in order to build models for the electric transport in magnetic textures which are, on one hand, complete with respect to the point group symmetry of the underlying lattice, and on the other hand, depend on a minimal number of order parameters only. Here, using a four-band tight-binding model on a honeycomb lattice, we demonstrate that the developed method can be used to address the importance and properties of higher-order contributions to transverse transport. The efficiency and breadth enabled by this method provides an ideal systematic approach to tackle the inherent complexity of response properties of noncollinear magnets, paving the way to the exploration of electric transport in intrinsically frustrated magnets as well as large-scale magnetic textures.
Desai et al
This research underscores the profound impact of data cleansing, ensuring dataset integrity and providing a structured foundation for unravelling unraveling convoluted connections between diverse physical properties and cytotoxicity. As the scientific community delves deeper into this interplay, it becomes clear that precise data purification is a fundamental aspect of investigating parameters within datasets. The study presents the need for data filtration in the background of Artificial Intelligence and Machine Learning (AI/ (ML) that has widened its horizon into the field of biological application through the amalgamation of predictive systems and algorithms that delve into the intricate characteristics of cytotoxicity of nanoparticles. The reliability and accuracy of models in the ML AI/ML landscape hinge on the quality of input data, making data cleansing a critical component of the pre-processing pipeline. The main encounter faced here is the lengthy, broad and complex datasets that has have to be toned down for further studies. Through a thorough data cleansing process, this study addresses the complexities arising from diverse sources, resulting in a refined dataset. The filtration process employs K-meansK-means clustering to derive centroids, revealing the correlation between the physical properties of nanoparticles, viz, concentration, zeta potential, hydrodynamic diameter, morphology, and absorbance andwavelength, and cytotoxicity outcomes measured in terms of cell viability. The cell lines considered for determining the centroid values that predicts the cytotoxicity of silver nanoparticles are human and animal cell lines which were categorized as normal and carcinoma type. The objective of the study is to simplify the high-dimensional data for accurate analysis of the parameters that affect the cytotoxicity of silver NPs through finding out the centroids. 
Otto et al
The number of satellites in orbit around Earth is increasing rapidly, with
the risk of collision rising accordingly. Trends of the global population of satellites
need to be analyzed to test the viability and impact of proposed rules and laws
affecting the satellite population and collision avoidance strategies. This requires
large scale simulations of satellites that are propagated on long timescales to compute
the large amounts of actionable close encounters (called conjunctions), which could
lead to collisions. Rigorously checking for conjunctions by computing future states of
orbits is computationally expensive due to the large amount of objects involved and
conjunction filters are thus used to remove non-conjuncting orbit pairs from the list
of possible conjunctions. In this work, we explore the possibility of machine learning
based conjunction filters using several algorithms such as eXtreme Gradient Boosting,
TabNet and (physics-informed) neural networks and deep operator networks. To show
the viability and the potential of machine learning based filters, these algorithms are
trained to predict the future state of orbits. For the physics-informed approaches,
multiple partial differential equations are set up using the Kepler equation as a basis.
The empirical results demonstrate that physics-informed deep operator networks are
capable of predicting the future state of orbits using these equations (RMSE: 0.136) and
outperform eXtreme Gradient Boosting (RMSE: 0.568) and TabNet (RMSE: 0.459).
We also propose a filter based on the trained deep operator network which is shown
to outperforms the filter capability of the commonly used perigee-apogee test and the
orbit path filter on a synthetic dataset, while being on average 3.2 times faster to
compute than a rigorous conjunction check.
Kumar et al
Physics Informed Neural Networks (PINNs) have been achieving ever newer feats of solving complicated PDEs numerically while offering an attractive trade-off between accuracy and speed of inference. A particularly challenging aspect of PDEs is that there exist simple PDEs which can evolve into singular solutions in finite time starting from smooth initial conditions. In recent times some striking experiments have suggested that PINNs might be good at even detecting such finite-time blow-ups. In this work, we embark on a program to investigate this stability of PINNs from a rigorous theoretical viewpoint. Firstly, we derive generalization bounds for PINNs for Burgers' PDE, in arbitrary dimensions, under conditions that allow for a finite-time blow-up. Then we demonstrate via experiments that our bounds are significantly correlated to the l2-distance of the neurally found surrogate from the true blow-up solution, when computed on sequences of PDEs that are getting increasingly close to a blow-up.