Search

Recent research has demonstrated that the TRophic IndeX (TRIX) is informative on the ecological quality of Mediterranean port waters and can be estimated by the processing of multispectral observations collected in situ. The current study investigates the alternative use of multispectral data acquired by medium-high spatial resolution optical satellite sensors, i.e. the Landsat-8 (L8) Operational Land Imager (OLI) and the Sentinel-2 (S2) MultiSpectral Instrument (MSI). The study analyzes the impact of the main factors influencing TRIX estimation using datasets collected in several Mediterranean ports and particularly in those of Civitavecchia and Viareggio (Central Italy). The experimental results indicate that the spectral configurations of OLI and MSI have a marginal impact on TRIX estimation, while major effects are caused by the different spatial and temporal features of the two sensors. The enhanced spatial properties of MSI are important particularly in the smaller port of Viareggio; the higher acquisition frequency of this sensor brings significant advantages for operational monitoring applications. Overall, the accuracy of TRIX estimation based on in situ spectral measurements is reduced significantly by the use of OLI images and only marginally by that of MSI images. Both image types represent an advancement for the operational monitoring of port waters.

Aridity and drought, which are determined by climatic and temporary water scarcity, respectively, are important limiting factors for plant gross primary production. These phenomena are commonly assessed and/or monitored by means of weather indices, most of which are based on observations of precipitation and potential evapotranspiration. The estimation of such indices over large areas can be carried out using multiple datasets, i.e., those derived from weather stations, satellite images, and ground radars. The possibility of using interpolated or remotely sensed datasets in place of ground measurements was currently investigated for Tuscany, a region in Central Italy, showing complex and heterogeneous environmental features. The former weather datasets were first evaluated versus corresponding ground measurements. Next, the basic weather variables were combined and cumulated over 30–60 days to yield synthetic indicators of water deficit, which were assessed in the same way. Finally, these indicators were evaluated to predict the soil water conditions of a meadow and an olive grove during the 2021 summer period. The results obtained indicate that the use of the multi-source weather datasets induces only a minor deterioration of the water stress indicators and is therefore efficient to monitor the water status of different ecosystems with high spatial (200 m) and temporal (daily) details.

Recent studies have demonstrated that the soil water content (SWC) of Mediterranean ecosystems can be simulated by combining ground data and remote sensing observations of Normalized Difference Vegetation Index (NDVI). The application of this approach in heterogeneous and fragmented areas, however, requires the use of spatio-temporal fusion (STF) methods to properly account for the actual NDVI variability of the examined ecosystems. One of these methods, which was specifically developed to produce annual NDVI data series in Mediterranean regions, is currently applied to MODIS and TM/ETM+ images taken over a highly fragmented green urban area in Florence (Central Italy). The performances of this STF method, called SEVIS, are indirectly evaluated by comparing local SWC measurements to simulations driven by the original (MODIS) and fused (MODIS+TM/ETM+) NDVI datasets. The results obtained confirm the critical dependence of the applied SWC simulation strategy on the efficient accounting for the actual NDVI evolution of the observed ecosystem. In particular, the use of the fused NDVI dataset corrects almost completely for the strong SWC underestimation produced by the original MODIS images during the summer dry period, significantly improving all accuracy statistics (r2 from 0.564 to 0.855, RMSE from 0.101 to 0.044 cm3 cm−3 and MBE from −0.046 to 0.000 cm3 cm−3).

Actual evapotranspiration (ETA) is a major term of site water balance whose knowledge is essential for numerous purposes. The classical ETA estimation approach based on the use of multitemporal crop coefficients (Kc) cannot be applied in water-limited environments without proper correction. Such correction can be theoretically obtained by means of soil water content (SWC) measurements, which, however, are affected by several drawbacks, due to both their technical and operational characteristics. The current paper proposes a method to normalize annual SWC datasets and integrate them in an ETA estimation procedure suitable for monitoring both agricultural and natural Mediterranean ecosystems. Differently from previous approaches, the SWC normalization is obtained using data-specific information, which renders the new method mostly insensitive to the mentioned problems. The method is first described and then applied in three case studies representative of different Mediterranean ecosystems (i.e., grassland, coniferous, and deciduous forests). The results are evaluated versus latent heat measurements taken by eddy covariance flux towers. Satisfactory accuracy is obtained in all three case studies, with advantages and limitations which are discussed in the final concluding sections.

Abstract The ongoing quest to discover new phenomena at the LHC necessitates the continuous development of algorithms and technologies. Established approaches like machine learning, along with emerging technologies such as quantum computing show promise in the enhancement of experimental capabilities. In this work, we propose a strategy for anomaly detection tasks at the LHC based on unsupervised quantum machine learning, and demonstrate its effectiveness in identifying new phenomena. The designed quantum models-an unsupervised kernel machine and two clustering algorithms-are trained to detect new-physics events using a latent representation of LHC data, generated by an autoencoder designed to accommodate current quantum hardware limitations on problem size. For kernel-based anomaly detection, we implement an instance of the model on a quantum computer, and we identify a regime where it significantly outperforms its classical counterparts. We show that the observed performance enhancement is related to the quantum resources utilised by the model.

Abstract We present a machine learning approach for model-independent new physics searches. The corresponding algorithm is powered by recent large-scale implementations of kernel methods, nonparametric learning algorithms that can approximate any continuous function given enough data. Based on the original proposal by D’Agnolo and Wulzer (Phys Rev D 99(1):015014, 2019, arXiv:1806.02350 [hep-ph]), the model evaluates the compatibility between experimental data and a reference model, by implementing a hypothesis testing procedure based on the likelihood ratio. Model-independence is enforced by avoiding any prior assumption about the presence or shape of new physics components in the measurements. We show that our approach has dramatic advantages compared to neural network implementations in terms of training times and computational resources, while maintaining comparable performances. In particular, we conduct our tests on higher dimensional datasets, a step forward with respect to previous studies.

We present a family of conditional dual auto-encoders (CoDAEs) for generic and model-independent new physics searches at colliders. New physics signals, which arise from new types of particles and interactions, are considered in our study as anomalies causing deviations in data with respect to expected background events. In this work, we perform a normal-only anomaly detection, which employs only background samples, to search for manifestations of a dark version of strong force applying (variational) auto-encoders on raw detector images, which are large and highly sparse, without leveraging any physics-based pre-processing or strong assumption on the signals. The proposed CoDAE has a dual-encoder design, which is general and can learn an auxiliary yet compact latent space through spatial conditioning, showing a neat improvement over competitive physics-based baselines and related approaches, therefore also reducing the gap with fully supervised models. It is the first time an unsupervised model is shown to exhibit excellent discrimination against multiple dark shower models, illustrating the suitability of this method as an accurate, fast, model-independent algorithm to deploy, e.g. in the real-time event triggering systems of large hadron collider experiments such as ATLAS and CMS.

Three machine learning models are used to perform jet origin classification. These models are optimized for deployment on a field-programmable gate array device. In this context, we demonstrate how latency and resource consumption scale with the input size and choice of algorithm. Moreover, the models proposed here are designed to work on the type of data and under the foreseen conditions at the CERN large hadron collider during its high-luminosity phase. Through quantization-aware training and efficient synthetization for a specific field programmable gate array, we show that $\mathcal{O}(100)$ ns inference of complex architectures such as Deep Sets and Interaction Networks is feasible at a relatively low computational resource cost.

In the context of the rapid changes that have occurred in recent years, characterized by veritable 'black swans' such as the COVID-19 pandemic and extreme weather events that are occurring with increasing frequency, the issue of climate change has come into the focus of banking regulators and supervisors. Therefore banking institutions, if they are subject to the Single Supervisory Mechanism, have been called upon to develop (and, subsequently, to integrate into their business practices) methodologies for the identification, quantification and management of such risks, mainly under the profiles of: • Transition Risk, associated with policies undertaken by governments to foster climate change mitigation and adaptation; • Physical Risk, associated with the occurrence of extreme climatic events and its impact on the bank's assets. This paper analyzes one of the most significant hazards within the Physical Risk domain, which is Flood Risk. The measurement is focused on the prospective evolution of the flood events on a portfolio of mortgages secured by residential properties. The impact of this risk driver is subsequently reflected through the movement of appropriate transmission mechanisms on the LGD and PD parameters relating to the exposures in the scope. Finally, the effect on loan adjustments is provided, by recalculating the expected losses that result from the stressed projections. The flood risk projection is executed on a long-term timeframe, developing over 3 climate scenarios up to 2050. The choice of this hazard is due to its relevance in terms of frequency of events and harmfulness, a relevance that is confirmed by its inclusion in both the top-down climate stress testing exercises carried out by the ECB and in the bottom-up climate stress testing exercise promoted by the ECB itself in 2022 and carried out by the SSM Banks. A comprehensive simulation framework, structured as follows, is then presented: • a macro-climate scenario simulation engine; • the downscaling of these scenarios to obtain localized climate effects on individual properties; • the transmission of these effects into a depreciation formula for the individual property; • the LGD stress associated with the devaluation of the collateral property, and the PD stress that goes along with it, obtained by correlation.

Abstract We present an end-to-end reconstruction algorithm to build particle candidates from detector hits in next-generation granular calorimeters similar to that foreseen for the high-luminosity upgrade of the CMS detector. The algorithm exploits a distance-weighted graph neural network, trained with object condensation, a graph segmentation technique. Through a single-shot approach, the reconstruction task is paired with energy regression. We describe the reconstruction performance in terms of efficiency as well as in terms of energy resolution. In addition, we show the jet reconstruction performance of our method and discuss its inference computational cost. To our knowledge, this work is the first-ever example of single-shot calorimetric reconstruction of $${\mathcal {O}}(1000)$$ O ( 1000 ) particles in high-luminosity conditions with 200 pileup.

Abstract We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties as nuisance parameters for hypothesis testing that is routinely employed in high-energy physics. After presenting the conceptual foundations of our method, we first illustrate all aspects of its implementation and extensively study its performances on a toy one-dimensional problem. We then show how to implement it in a multivariate setup by studying the impact of two typical sources of experimental uncertainties in two-body final states at the LHC.

Measurement(s) Simulations of LHC collisions in real-time processing data format Technology Type(s) PYTHIA, DELPHES, private python code Factor Type(s) phi • eta • pT

Abstract The production of dark matter particles from confining dark sectors may lead to many novel experimental signatures. Depending on the details of the theory, dark quark production in proton-proton collisions could result in semivisible jets of particles: collimated sprays of dark hadrons of which only some are detectable by particle collider experiments. The experimental signature is characterised by the presence of reconstructed missing momentum collinear with the visible components of the jets. This complex topology is sensitive to detector inefficiencies and mis-reconstruction that generate artificial missing momentum. With this work, we propose a signal-agnostic strategy to reject ordinary jets and identify semivisible jets via anomaly detection techniques. A deep neural autoencoder network with jet substructure variables as input proves highly useful for analyzing anomalous jets. The study focuses on the semivisible jet signature; however, the technique can apply to any new physics model that predicts signatures with anomalous jets from non-SM particles.

Abstract In general-purpose particle detectors, the particle-flow algorithm may be used to reconstruct a comprehensive particle-level view of the event by combining information from the calorimeters and the trackers, significantly improving the detector resolution for jets and the missing transverse momentum. In view of the planned high-luminosity upgrade of the CERN Large Hadron Collider (LHC), it is necessary to revisit existing reconstruction algorithms and ensure that both the physics and computational performance are sufficient in an environment with many simultaneous proton–proton interactions (pileup). Machine learning may offer a prospect for computationally efficient event reconstruction that is well-suited to heterogeneous computing platforms, while significantly improving the reconstruction quality over rule-based algorithms for granular detectors. We introduce MLPF, a novel, end-to-end trainable, machine-learned particle-flow algorithm based on parallelizable, computationally efficient, and scalable graph neural network optimized using a multi-task objective on simulated events. We report the physics and computational performance of the MLPF algorithm on a Monte Carlo dataset of top quark–antiquark pairs produced in proton–proton collisions in conditions similar to those expected for the high-luminosity LHC. The MLPF algorithm improves the physics response with respect to a rule-based benchmark algorithm and demonstrates computationally scalable particle-flow reconstruction in a high-pileup environment.

Abstract We discuss a method that employs a multilayer perceptron to detect deviations from a reference model in large multivariate datasets. Our data analysis strategy does not rely on any prior assumption on the nature of the deviation. It is designed to be sensitive to small discrepancies that arise in datasets dominated by the reference model. The main conceptual building blocks were introduced in D’Agnolo and Wulzer (Phys Rev D 99 (1), 015014. https://doi.org/10.1103/PhysRevD.99.015014 . arXiv:1806.02350 [hep-ph], 2019). Here we make decisive progress in the algorithm implementation and we demonstrate its applicability to problems in high energy physics. We show that the method is sensitive to putative new physics signals in di-muon final states at the LHC. We also compare our performances on toy problems with the ones of alternative methods proposed in the literature.

In this community review report, we discuss applications and techniques for fast machine learning (ML) in science—the concept of integrating powerful ML methods into the real-time experimental data processing loop to accelerate scientific discovery. The material for the report builds on two workshops held by the Fast ML for Science community and covers three main areas: applications for fast ML across a number of scientific domains; techniques for training and implementing performant and resource-efficient ML algorithms; and computing architectures, platforms, and technologies for deploying these algorithms. We also present overlapping challenges across the multiple scientific domains where common solutions can be found. This community report is intended to give plenty of examples and inspiration for scientific discovery through integrated and accelerated ML solutions. This is followed by a high-level overview and organization of technical advances, including an abundance of pointers to source material, which can enable these breakthroughs.

Abstract Using detailed simulations of calorimeter showers as training data, we investigate the use of deep learning algorithms for the simulation and reconstruction of single isolated particles produced in high-energy physics collisions. We train neural networks on single-particle shower data at the calorimeter-cell level, and show significant improvements for simulation and reconstruction when using these networks compared to methods which rely on currently-used state-of-the-art algorithms. We define two models: an end-to-end reconstruction network which performs simultaneous particle identification and energy regression of particles when given calorimeter shower data, and a generative network which can provide reasonable modeling of calorimeter showers for different particle types at specified angles and energies. We investigate the optimization of our models with hyperparameter scans. Furthermore, we demonstrate the applicability of the reconstruction model to shower inputs from other detector geometries, specifically ATLAS-like and CMS-like geometries. These networks can serve as fast and computationally light methods for particle shower simulation and reconstruction for current and future experiments at particle colliders.

Abstract We introduce the DNNLikelihood, a novel framework to easily encode, through deep neural networks (DNN), the full experimental information contained in complicated likelihood functions (LFs). We show how to efficiently parametrise the LF, treated as a multivariate function of parameters of interest and nuisance parameters with high dimensionality, as an interpolating function in the form of a DNN predictor. We do not use any Gaussian approximation or dimensionality reduction, such as marginalisation or profiling over nuisance parameters, so that the full experimental information is retained. The procedure applies to both binned and unbinned LFs, and allows for an efficient distribution to multiple software platforms, e.g. through the framework-independent ONNX model format. The distributed DNNLikelihood can be used for different use cases, such as re-sampling through Markov Chain Monte Carlo techniques, possibly with custom priors, combination with other LFs, when the correlations among parameters are known, and re-interpretation within different statistical approaches, i.e. Bayesian vs frequentist. We discuss the accuracy of our proposal and its relations with other approximation techniques and likelihood distribution frameworks. As an example, we apply our procedure to a pseudo-experiment corresponding to a realistic LHC search for new physics already considered in the literature.

Abstract We investigate the performance of a jet identification algorithm based on interaction networks (JEDI-net) to identify all-hadronic decays of high-momentum heavy particles produced at the LHC and distinguish them from ordinary jets originating from the hadronization of quarks and gluons. The jet dynamics are described as a set of one-to-one interactions between the jet constituents. Based on a representation learned from these interactions, the jet is associated to one of the considered categories. Unlike other architectures, the JEDI-net models achieve their performance without special handling of the sparse input jet representation, extensive pre-processing, particle ordering, or specific assumptions regarding the underlying detector geometry. The presented models give better results with less model parameters, offering interesting prospects for LHC applications.

We investigate how to improve new physics detection strategies exploiting variational autoencoders and normalizing flows for anomaly detection at the Large Hadron Collider. As a working example, we consider the DarkMachines challenge dataset. We show how different design choices (e.g., event representations, anomaly score definitions, network architectures) affect the result on specific benchmark new physics models. Once a baseline is established, we discuss how to improve the anomaly detection accuracy by exploiting normalizing flow layers in the latent space of the variational autoencoder.

The Earth mover’s distance (EMD) is a useful metric for image recognition and classification, but its usual implementations are not differentiable or too slow to be used as a loss function for training other algorithms via gradient descent. In this paper, we train a convolutional neural network (CNN) to learn a differentiable, fast approximation of the EMD and demonstrate that it can be used as a substitute for computing-intensive EMD implementations. We apply this differentiable approximation in the training of an autoencoder-inspired neural network (encoder NN) for data compression at the high-luminosity LHC at CERN The goal of this encoder NN is to compress the data while preserving the information related to the distribution of energy deposits in particle detectors. We demonstrate that the performance of our encoder NN trained using the differentiable EMD CNN surpasses that of training with loss functions based on mean squared error.

Much hope for finding new physics phenomena at microscopic scale relies on the observations obtained from High Energy Physics experiments, like the ones performed at the Large Hadron Collider (LHC). However, current experiments do not indicate clear signs of new physics that could guide the development of additional Beyond Standard Model (BSM) theories. Identifying signatures of new physics out of the enormous amount of data produced at the LHC falls into the class of anomaly detection and constitutes one of the greatest computational challenges. In this article, we propose a novel strategy to perform anomaly detection in a supervised learning setting, based on the artificial creation of anomalies through a random process. For the resulting supervised learning problem, we successfully apply classical and quantum support vector classifiers (CSVC and QSVC respectively) to identify the artificial anomalies among the SM events. Even more promising, we find that employing an SVC trained to identify the artificial anomalies, it is possible to identify realistic BSM events with high accuracy. In parallel, we also explore the potential of quantum algorithms for improving the classification accuracy and provide plausible conditions for the best exploitation of this novel computational paradigm.

In high energy physics, one of the most important processes for collider data analysis is the comparison of collected and simulated data. Nowadays the state-of-the-art for data generation is in the form of Monte Carlo (MC) generators. However, because of the upcoming high-luminosity upgrade of the Large Hadron Collider (LHC), there will not be enough computational power or time to match the amount of needed simulated data using MC methods. An alternative approach under study is the usage of machine learning generative methods to fulfill that task. Since the most common final-state objects of high-energy proton collisions are hadronic jets, which are collections of particles collimated in a given region of space, this work aims to develop a convolutional variational autoencoder (ConVAE) for the generation of particle-based LHC hadronic jets. Given the ConVAE’s limitations, a normalizing flow (NF) network is coupled to it in a two-step training process, which shows improvements on the results for the generated jets. The ConVAE+NF network is capable of generating a jet in $18.30 \pm 0.04\,\,{\mu\text{s}}$ , making it one of the fastest methods for this task up to now.

More than a thousand 8″ silicon sensors will be visually inspected to look for anomalies on their surface during the quality control preceding assembly into the High-Granularity Calorimeter for the CMS experiment at CERN. A deep learning-based algorithm that pre-selects potentially anomalous images of the sensor surface in real time was developed to automate the visual inspection. The anomaly detection is done by an ensemble of independent deep convolutional neural networks: an autoencoder and a classifier. The algorithm was deployed and has been continuously running in production, and data gathered were used to evaluate its performance. The pre-selection reduces the number of images requiring human inspection by 85%, with recall of 97%, and saves 15 person-hours per a batch of a hundred sensors. Data gathered in production can be used for continuous learning to improve the accuracy incrementally.

Abstract We explore the use of graph networks to deal with irregular-geometry detectors in the context of particle reconstruction. Thanks to their representation-learning capabilities, graph networks can exploit the full detector granularity, while natively managing the event sparsity and arbitrarily complex detector geometries. We introduce two distance-weighted graph network architectures, dubbed GarNet and GravNet layers, and apply them to a typical particle reconstruction task. The performance of the new architectures is evaluated on a data set of simulated particle interactions on a toy model of a highly granular calorimeter, loosely inspired by the endcap calorimeter to be installed in the CMS detector for the High-Luminosity LHC phase. We study the clustering of energy depositions, which is the basis for calorimetric particle reconstruction, and provide a quantitative comparison to alternative approaches. The proposed algorithms provide an interesting alternative to existing methods, offering equally performing or less resource-demanding solutions with less underlying assumptions on the detector geometry and, consequently, the possibility to generalize to other detectors.

Abstract Using variational autoencoders trained on known physics processes, we develop a one-sided threshold test to isolate previously unseen processes as outlier events. Since the autoencoder training does not depend on any specific new physics signature, the proposed procedure doesn’t make specific assumptions on the nature of new physics. An event selection based on this algorithm would be complementary to classic LHC searches, typically based on model-dependent hypothesis testing. Such an algorithm would deliver a list of anomalous events, that the experimental collaborations could further scrutinize and even release as a catalog, similarly to what is typically done in other scientific domains. Event topologies repeating in this dataset could inspire new-physics model building and new experimental searches. Running in the trigger system of the LHC experiments, such an application could identify anomalous events that would be otherwise lost, extending the scientific reach of the LHC.

Graph neural networks have been shown to achieve excellent performance for several crucial tasks in particle physics, such as charged particle tracking, jet tagging, and clustering. An important domain for the application of these networks is the FGPA-based first layer of real-time data filtering at the CERN Large Hadron Collider, which has strict latency and resource constraints. We discuss how to design distance-weighted graph networks that can be executed with a latency of less than one μs on an FPGA. To do so, we consider a representative task associated to particle reconstruction and identification in a next-generation calorimeter operating at a particle collider. We use a graph network architecture developed for such purposes, and apply additional simplifications to match the computing constraints of Level-1 trigger systems, including weight quantization. Using the hls4ml library, we convert the compressed models into firmware to be implemented on an FPGA. Performance of the synthesized models is presented both in terms of inference accuracy and resource usage.