Application Scenarios Research Articles

Methodology of a Comprehensive Approach to the Analysis, Structuring, and Aggregation of Data Based on the Requirements of Resource-Intensive Applications

The work presents a methodology for in-depth data description for resource-intensive applied tasks, particularly in the field of materials science. It consists of three basic stages. In the first stage, quantitative and semantic requirements are formalized, and working datasets are defined, which can be classified as reference, structured, instrumental, or experimental-computational, depending on the source. These datasets are stored in a specialized research area for further investigation. The second stage involves the analysis and hierarchical structuring of the accumulated information content. This allows for the refinement and comparison of data, storage of different sets, and the application of various processing tools. In the third stage, the data is aggregated and represented as objects in the domain area according to the database schema of the application support system. The steps outlined in the proposed methodology enable full utilization of the specialized research area of informational content for building object models of application scenarios, structuring the domain data representation schema, and forming event-information forms. The practical application of this methodology in the examined subject area clarified the requirements, criteria, and filters for information search, data description, parameter cataloging, and their verification when solving a number of practical tasks. The software implementation of this approach could be oriented towards a web platform for local and cloud technologies, allowing remote collaborative access to content requirements and solution catalogs with role-based access for different categories of researchers and users.

Analysis and Optimization of the Noise Reduction Performance of Sound-Absorbing Materials in Complex Environments

The acoustic performance of sound barrier absorption materials utilized in substations is subject to variations due to factors such as sandstorms, corrosion, and rainfall. In this study, a model of the absorbing material was developed based on the Delany–Bazley model using COMSOL simulation software, version 5.6. The influence of porosity and material thickness on the absorption coefficient was analyzed, and the patterns of change were summarized. The results indicated that porosity significantly affected the entire analysis frequency range, while material thickness had a more pronounced impact in the low-frequency range. Building upon these findings, a blended fiber absorption material was formulated through research efforts. Experimental results demonstrated that the aluminum fiber diameter measured 30 microns, while the aramid fiber diameter was 12 microns; additionally, their mass ratio was established at 3:1. The material thickness was determined to be 10 cm with a face density of 2500 g/m2, resulting in optimal absorption performance. Durability tests revealed that this material could sustain effective acoustic performance across various complex environments. Finally, simulations and analyses regarding noise reduction effects were conducted within actual application scenarios; it was found that the noise reduction capability of the blended fiber sound barrier absorption material exceeded that of glass wool by 4.78 dB.

Nano-fuels-driven self-sacrificed ZIF-8@Apt integrated chip coupled with a DNAzyme system for the isolation and detection of glioblastoma-derived extracellular vesicles

Plasma extracellular vesicles (EVs) have emerged as promising biomarkers for the early diagnosis of glioblastoma. However, rapid and efficient isolation and detection of tumor-specific EV subsets from plasma remains challenging. To address this, we developed an innovative integrated chip based on self-sacrificial metal–organic frameworks and the epidermal growth factor receptor (EGFR) aptamers called ZIF-8@EGFR aptamer (ZIF-8@Apt), which further coupled with a “nano-fuels”-driven DNAzyme amplification strategy. The core functionality of the constructed chip lies in its ability to capture EVs with the ZIF-8@Apt module. Once captured, numerous DNA “nano-fuel” structures are in situ assembled on the EVs’ surfaces. Subsequently, the ZIF-8@Apt@EV@nano-fuels composites are lysed to release Zn2+, the EVs’ nucleic acids, and additional nano-fuels for subsequent detection. Finally, a DNAzyme detection system is introduced, where the released nano-fuels activate the DNAzyme, leading to multiple signal amplification aided by Zn2+ for highly sensitive detection of plasma EVs. This integrated approach effectively enriches and detects target EVs, achieving a significantly enhanced detection sensitivity of 500 particles/μL. In a clinical study involving glioblastoma patients, our chip demonstrated a remarkable ability to distinguish between cancer patients and healthy individuals, achieving an area under the curve (AUC) of 0.958. Moreover, the response signals of the chip can be conveniently read using fluorescence spectroscopy or microscope, offering a rapid, highly sensitive, and high-throughput analysis of plasma EVs for various application scenarios. Overall, this study introduces a comprehensive approach for the rapid isolation and accurate analysis of plasma EVs, holding significant promise for early diagnosis and disease monitoring.

3D-MSFC: A 3D multi-scale features compression method for object detection

As machine vision tasks rapidly evolve, a new concept of compression, namely video coding for machines (VCM), has emerged. However, current VCM methods are only suitable for 2D machine vision tasks. With the popularization of autonomous driving, the demand for 3D machine vision tasks has significantly increased, leading to an explosive growth in LiDAR data that requires efficient transmission. To address this need, we propose a machine vision-based point cloud coding paradigm inspired by VCM. Specifically, we introduce a 3D multi-scale features compression (3D-MSFC) method, tailored for 3D object detection. Experimental results demonstrate that 3D-MSFC achieves less than a 3% degradation in object detection accuracy at a compression ratio of 2796×. Furthermore, its low-profile variant, 3D-MSFC-L, achieves less than a 2% degradation in accuracy at a compression ratio of 463×. The above results indicate that our proposed method can provide an ultra-high compression ratio while ensuring no significant drop in accuracy, greatly reducing the amount of data required for transmission during each detection. This can significantly lower bandwidth consumption and save substantial costs in application scenarios such as smart cities.

Unidirectional moisture-wicking PAN/BTO-PVDF/ZnO all fibrous bilayer breathable electronic skin for health sensing

All fibrous electronic skin based on excellent flexibility and piezoelectric properties could be widely applied in monitoring and healthcare sensing. The accumulative moisture during application scenarios, just as violent sweat or a damp environment, can affect the stability and sensitivity of the piezoelectric signal. Here, a bilayer piezoelectric sensor was fabricated using a layer-by-layer electrospinning technique. The inner layer is composed of hydrophobic piezoelectric polyvinylidene fluoride (PVDF)-zinc oxide (ZnO) nanofibers, while the outer layer consists of hydrophilic piezoelectric polyacrylonitrile (PAN)-barium titanate (BTO) nanofibers. The unidirectional moisture-wicking performance based on the hydrophilic-hydrophobic gradient of PVDF/ZnO-PAN/BTO nanofiber membranes (PZ-PBNF) could conduct liquid within 1 s. Incorporating inorganic ZnO and BTO nanoparticles provides a practical approach to enhancing the piezoelectric output performance (277.5 mV). These fibrous PZ-PBNF membranes also exhibit excellent stretchability properties (breaking elongation of 110 %) and air permeability (12.065 mm/s). This innovative electronic skin with directional water transport and sensing functions could ensure long-term wear comfort for practical application in emerging wearable technologies and all healthcare ranges.

A transparent multifunctional integrated meta-window with excellent sound insulation and vibration reduction performance

As the speed of transportation vehicles such as high-speed train continues to increase, there has been a significant rise in both noise and vibration levels, substantially compromising passenger comfort and overall travel experience. In transportation vehicles, the necessity for transparency in windows poses a challenge in incorporating high sound-insulating or vibration-damping materials, rendering windows vulnerable in sound isolation and vibration attenuation. This study employs an integrated material-structural design concept to develop a multifunctional meta-window, which ensures optimal lighting transmission while achieving outstanding sound-insulating and vibration-damping capabilities. Two distinct structures, named ultra-lightweight thin plate-type metamaterial and high-stability thick plate-type metamaterial, are precisely designed to adapt to varied application scenarios. Utilizing a gradient parameter multi-cell parallel synergetic coupling design method broadens the working bandwidth for sound insulation. The meta-window incorporates localized resonance units, enabling acoustic and vibrational energy dissipation through low-frequency resonance, effectively enhancing the window’s sound-insulating and vibration-damping capabilities. Comprising a composite of various transparent materials, the design amalgamates sound insulation, vibration reduction, and light transmission, eliminating the need for opaque sound-insulating or damping materials. Consequently, it holds substantial potential for applications across sectors, including train, aircraft, and architectural domains.

Fully degradable, highly sensitive pressure sensor based on bipolar electret for biomechanical signal monitoring

In view of the global ecosystem crisis resulting from the ubiquitous electronic waste (e− and plastic waste), the engineering of advanced electronic devices from sustainable materials is gaining considerable attention. Nevertheless, the development of advanced, maybe even degradable electronics with comparable or even improved functionality remains a great challenge. In this article a fabrication process for a fully degradable, highly sensitive pressure sensor based on electrets is proposed enabling the creation of a universal platform for monitoring various biomechanical signals. The high sensitivity of the proposed biomechanical electret-based sensor utilizes electrostatic induction of highly deformable cellular polylactic acid (PLA) films with a serrated ripple structure and an improved bipolar charge storage capability. This biodegradable pressure sensor possesses competitive mechanical signal detection performance, obtaining a high pressure sensitivity (10 V/kPa), robust working stability (∼30,000 continuous cycles), short electromechanical response/recovery time (∼17 ms), and satisfactory heat resistance up to 60 °C. By tailoring the thickness of the encapsulation layer, the functional lifetime of the biomechanical sensor in physiological environment can be controlled effectively, facilitating adaptability to various implantable application scenarios. Altogether, the present work not only proposes an effective fabrication process for high-performance pressure sensors, but also provides new insight into the design of sustainable electronics with controllable lifetime thereby minimizing their environmental footprint. The developed sensor promises great potential in monitoring multiple biomechanical signals inside and outside the human body (e.g., body movements and physiological activities) as well as an environment-friendly realization of green electronics.

Multicolor Gold Clusterzyme-Enabled Construction of Ratiometric Fluorescent Sensor Array for Visual Biosensing.

The simultaneous detection of multiple bioanalytes with similar structures has been a long-standing challenge for biological research and disease diagnosis. Bioreceptor-inspired sensor arrays provide an attractive and competitive solution for addressing this challenge, but applying this technique to biosensing in practical application scenarios is complicated by many factors such as the lack of robust probes, interference from the biological matrix, and difficulty for on-site analysis. In this work, by taking advantage of the intrinsic fluorescence and enzyme-mimic properties of gold nanoclusters (AuNCs), we report the design of an innovative ratiometric sensor array toward enhanced fluorescent visual biosensing. With biologically important phosphates as an example, we show that the present fluorescent clusterzyme-based ratiometric sensor array could effectively discriminate and detect eight types of phosphates. In particular, AuNCs with three different emission colors (blue, green, and red) and good peroxidase-mimic properties were employed as the sensing units, and the presence of phosphates affected both the intrinsic fluorescence and the enzymatic activity of these AuNCs, yielding distinct optical responses in a ratiometric manner. Moreover, a portable sensor array was established by further integrating these fluorescent clusterzymes into a hydrogel matrix, which could visually identify different phosphates based on their distinct fluorescence color changes. Consequently, the point-of-care diagnosis of urinary tract infections at different levels was achieved by analyzing urinary microbial ATP via the present strategy. This study illustrates the great potential of clusterzyme-based fluorescent sensor arrays as a promising biosensing platform for disease diagnosis.

Design and performance evaluation of a spiral bar precision weeding mechanism for corn fields

This paper focuses on addressing the limitations of existing mechanical weeding methods for corn plants by introducing a spiral tendon-type precision weeding device specifically designed for corn fields. The study encompasses mechanical design and theoretical analysis to determine the overall structure, component parts, application scenarios, operation modes, and working principles of the device. The force applied to the spiral tendon weeding cutter head, a crucial working component of the device, is analyzed, along with its motion characteristics. This analysis allows for the calculation of the force required for the spiral tendon to penetrate the soil, as well as the determination of its trajectory and speed in the soil. The desired motion pattern of the weeding cutter head is considered in determining the contour shape of the inner cylinder track and its cooperation mode with the roller follower. Furthermore, the design and optimization of the circulation groove track are conducted to derive the key parameters of the track. A prototype is then constructed based on the proposed structural design and parameter optimization scheme. Soil bin tests are performed to evaluate the device’s performance. The optimal combinations of working parameters are determined as follows: a 70-mm depth of the weeding cutter head into the soil, a movement speed of 80 mm/s, and an output thrust of the electric actuator of 180 N. Under these conditions, the device achieves a weed removal rate exceeding 95% with a 3% wounding rate, demonstrating stable operational performance.

The Feasibility of Using Electrostatic Interactions for Immobilizing Ru-bda Catalysts in Covalent Organic Framework: A Proof-of-Concept.

Heterogenization of molecular catalysts effectively resolves the separation issues of homogeneous catalysts and expands their application scenarios. In recent years, more and more studies have been using non-covalent interactions to achieve the heterogenization of molecular catalysts. Herein, electrostatic attraction was used to immobilize molecular catalysts, Ru-bda small molecular catalysts in COF materials, where the charged Ru-bda catalysts were immobilized in the oppositely charged COF with a high [Ru] loading content of ~0.2 mmol [Ru] g-1 COF. The leakage experiment verified that the immobilization of Ru-bda catalysts in COF by electrostatic interactions is stable in 0.1 M HClO4 and less than 5 % of molecular Ru-bda catalysts were leached into the solution in 2 hours. The chemical water oxidation experiment was conducted as a model catalysis reaction to verify the feasibility of using electrostatic interactions for immobilizing Ru-bda catalysts in COFs. The prepared Ru(bda)@COFs demonstrate a high catalytic activity of 268 μmol L-1 s-1 O2 for chemical water oxidation, illustrating the electrostatic attractions between COF and small molecules that can be used to immobilize homogeneous catalysts in heterogeneous materials. However, the robustness of COF material itself under catalytic conditions should be considered in practical applications.

Ontological Airspace-Situation Awareness for Decision System Support

Air Traffic Management (ATM) has become complicated mainly due to the increase and variety of input information from Communication, Navigation, and Surveillance (CNS) systems as well as the proliferation of Unmanned Aerial Vehicles (UAVs) requiring Unmanned Aerial System Traffic Management (UTM). In response to the UTM challenge, a decision support system (DSS) has been developed to help ATM personnel and aircraft pilots cope with their heavy workloads and challenging airspace situations. The DSS provides airspace situational awareness (ASA) driven by knowledge representation and reasoning from an Avionics Analytics Ontology (AAO), which is an Artificial Intelligence (AI) database that augments humans’ mental processes by means of implementing AI cognition. Ontologies for avionics have also been of interest to the Federal Aviation Administration (FAA) Next Generation Air Transportation System (NextGen) and the Single European Sky ATM Research (SESAR) project, but they have yet to be received by practitioners and industry. This paper presents a decision-making computer tool to support ATM personnel and aviators in deciding on airspace situations. It details the AAO and the analytical AI foundations that support such an ontology. An application example and experimental test results from a UAV AAO (U-AAO) framework prototype are also presented. The AAO-based DSS can provide ASA from outdoor park-testing trials based on downscaled application scenarios that replicate takeoffs where drones play the role of different aircraft, i.e., where a drone represents an airplane that takes off and other drones represent AUVs flying around during the airplane’s takeoff. The resulting ASA is the output of an AI cognitive process, the inputs of which are the aircraft localization based on Automatic Dependent Surveillance–Broadcast (ADS-B) and the classification of airplanes and UAVs (both represented by drones), the proximity between aircraft, and the knowledge of potential hazards from airspace situations involving the aircraft. The ASA outcomes are shown to augment the human ability to make decisions.

Virtual X-ray critical dimension metrology via Monte Carlo simulation.

X-ray critical dimension (XCD) metrology is a highly promising technique for achieving sub-nanometer precision in critical dimension measurements at advanced nodes of integrated circuit manufacturing. Compared to XCD experiments utilizing synchrotron radiation sources, those employing compact X-ray sources encounter challenges like extended testing time and increased uncertainty. To evaluate the influence of experimental conditions on measurement results, we developed an ab initio virtual X-ray critical dimension metrology via a Monte Carlo simulation (MC-VXCD). Through calibrating the system parameters of the MC-VXCD to a home-built compact XCD instrument, we achieved excellent consistency between virtual and actual measurement results. The virtual instrument effectively estimated measurement errors stemming from the reduced exposure time, which significantly influences the measurement accuracy and throughput. Furthermore, through the MC-VXCD, we establish the connection between the application scenarios of the XCD metrology and the geometry of XCD instruments, offering a versatile platform for the system design, experimental configuration optimization, data analysis, etc., in XCD metrology.

Topological Metasurface for Spin‐Decoupled Wavefront Manipulation of Terahertz Surface Plasmons

AbstractOn‐chip wavefront manipulation of terahertz surface plasmons is crucial for the miniaturization and practical application of terahertz technology. Recently, topological metasurfaces have emerged as a promising avenue for spin‐decoupled wavefront manipulation, leveraging the unique topological properties of non‐Hermitian matrices near their singular points. Despite their innovative phase control mechanisms, topological metasurfaces have not yet been explored for surface plasmon devices. Here, spin‐decoupled wavefront manipulation of terahertz surface plasmons is experimentally achieved using freestanding topological metasurfaces. This approach promises to expand the control methods of surface plasmons and broaden the application scenarios of topological metasurfaces, providing a new paradigm for the design of integrated on‐chip terahertz devices.

Extension of a 3D Geological Entity Modeling Method for Discontinuous Deformation Analysis

AbstractWith the development of 3D discontinuous deformation analysis (DDA) in precise stress fields and crack propagation problems, it has also demonstrated outstanding capabilities in solving continuous–discontinuous problems. However, currently, 3D DDA modeling primarily focuses on generating rock joint networks and developing 3D cutting algorithms. Correspondingly, 3D geological modeling methods are not yet mature, and establishing 3D models often demands substantial time. The lack of supporting preprocessing modeling methods and corresponding visual operation interfaces significantly hampers the development of 3D DDA. This method builds upon advanced research achievements in unmanned aerial vehicle oblique photography, 3D reconstruction, 3D cutting, computer graphics, and visualization program design. This research establishes a 3D geological entity modeling method for 3D DDA and constructs a comprehensive program using relevant C++ libraries and C language interfaces. In this method, a 3D geological model that incorporates geological elements such as strata and faults is initially established using non‐uniform rational B‐splines (NURBSs) surfaces as the boundary of the solid model. Subsequently, finite element meshing is applied, followed by corresponding topology transformation, resulting in a 3D block system model suitable for 3D DDA calculation. To cater for diverse application scenarios, continuous–discontinuous models integrated with subblocks and models of arbitrary polyhedra can be established. The proposed method has been validated through several typical modeling examples, showing its ability to rapidly and generate 3D high‐precision geological reality models suitable for 3D DDA calculations. Additionally, some techniques used in this method can be extended for modeling other numerical simulation methods, warranting further research.

Secure Search of Smart Home Data Based on Access Control Encryption

Abstract: In recent years, the increasing variety of smart home devices, such as smart locks, surveillance cameras, and various sensors, has led to a significant rise in related data. To facilitate the sharing of smart home data, manufacturers store these data on the Internet of Things (IoT). However, since IoT servers are not fully trustworthy and the data often contain sensitive commercial information, any leakage could result in a commercial crisis for manufacturers. To address security concerns, manufacturers encrypt the data before storing them on the IoT. A challenge arises: how can users search for target data in encrypted form? This paper proposes a new search encryption scheme for smart home data, addressing the limitations of existing attribute-based encryption (ABE) searchable encryption schemes. The proposed scheme integrates access control trees and bilinear mapping technology, supporting multiple access policies including AND gates, OR gates, and threshold gates. Experimental results demonstrate a comprehensive analysis of the attribute-based searchable encryption protocol under a multi-authority architecture, covering four dimensions: correctness, security, complexity, and real-world application scenarios. In specific scenarios, when a data user, out of privacy concerns, is unwilling to reveal all attribute information to a single authority during a query for shared datathus avoiding identity disclosureor when the users identity information is managed by multiple independent authorities, this protocol proves highly effective. It ensures smooth data sharing while maintaining data security for both data owners and users, fully safeguarding data privacy and shareability.

Fixed frequency range empirical wavelet transform based acoustic and entropy features for speech emotion recognition

The primary goal of automated speech emotion recognition (SER) is to accurately and effectively identify each specific emotion conveyed in a speech signal utilizing machines such as computers and mobile devices. The widespread recognition of the popularity of SER among academics for three decades is mainly attributed to its broad application in practical scenarios. The utilization of SER has proven to be beneficial in various fields, such as medical intervention, bolstering safety strategies, conducting vigil functions, enhancing online search engines, enhancing road safety, managing customer relationships, strengthening the connection between machines and humans, and numerous other domains. Many researchers have used diverse methodologies, such as the integration of different attributes, the use of different feature selection techniques, and designed a hybrid or complex model using more than one classifier, to augment the effectiveness of emotion classification. In our study, we used a novel technique called the fixed frequency range empirical wavelet transform (FFREWT) filter bank decomposition method to extract the features, and then used those features to accurately identify each and every emotion in the speech signal. The FFREWT filter bank method segments the speech signal frame (SSF) into many sub-signals or modes. We used each FFREWT-based decomposed mode to get features like the mel frequency cepstral coefficient (MFCC), approximate entropy (ApEn), permutation entropy (PrEn), and increment entropy (IrEn). We then used the different combinations of the proposed FFREWT-based feature sets and the deep neural network (DNN) classifier to classify the speech emotion. Our proposed method helps to achieve an emotion classification accuracy of 89.35%, 84.69%, and 100% using the combinations of the proposed FFREWT-based feature (MFCC + ApEn + PrEn + IrEn) for the EMO-DB, EMOVO, and TESS datasets, respectively. Our experimental results were compared with the other methods, and we found that the proposed FFREWT-based feature combinations with a DNN classifier performed better than the state-of-the-art methods in SER.

A dynamic semi-quantum private comparison protocol for size relations

Abstract Semi-quantum private comparison allows multiple ``classical'' users who have restricted quantum capabilities to compare their private data with the assistance of a quantum third party. In this work, we propose a novel dynamic semi-quantum private comparison protocol using a circular transmission mode along with $d$-dimensional single-particle states. The protocol enables the comparison of data size relations among several ``classical'' users, while the third party can only determine the relative sizes without accessing the users' secret information. Security evaluations demonstrate that the designed protocol withstands typical external and internal attacks. Compared to previous works, this protocol offers several improvements: first, it supports dynamic addition or removal of users, enhancing applicability in practical scenarios; second, it eliminates the need for pre-shared keys, reducing quantum resource consumption; third, it avoids the use of high-dimensional multi-particle entangled states, thereby enhancing the feasibility of implementation. Therefore, the proposed protocol may have more practical potential compared to previous protocols.

Multi-scale analysis of voltage curves for accurate and adaptable lifecycle prediction of lithium-ion batteries

Health status prediction of lithium-ion batteries is critical for the stable operation of electrical equipment. The data-driven approach can fit the degradation laws based on the historical cyclic data and identify potential problems in time. However, existing prediction methods mainly focus on acquiring various cyclic degradation features, and excessive battery-related data types increase the complexity and indeterminacy, posing a challenge for efficient and accurate prediction during practical application scenarios. Herein, this study only uses cyclic voltages and proposes a novel multi-scale cyclic voltage data preprocessing technique, involving the selection of highly correlated feature parameters with battery life in both the time and frequency domains, and constructing graphical samples with dynamic node connectivity properties. The proposed multi-scale graph convolutional network model adeptly captures and amalgamates the evolving features among graphical samples with efficacy. The one-step prediction experiments demonstrate the capability to predict subsequent capacity degradation solely based on the voltages of any consecutive 20 cycles, with a root mean square error of 0.173 %, exhibiting adaptable capability across different battery datasets. Compared to existing methods that transform data into images for health status prediction, this study highlights the significance of a multi-scale approach to voltage analysis in cyclic data, leveraging advanced feature engineering and modeling techniques, not only to enhance the accuracy and adaptability of battery lifecycle predictions but also to offer a robust framework for overcoming prevailing challenges in monitoring accuracy and cost-effectiveness.

Fundamentals and Challenges of Ligand Modification in Heterogeneous Electrocatalysis

AbstractThe development of efficient catalytic materials in the energy field could promote the structural transformation from traditional fossil fuels to sustainable energy. In heterogeneous catalytic reactions, ligand modification is an effective way to regulate both electronic and steric structures of catalytic sites, thus paving a prospective avenue to design the interfacial structures of heterogeneous catalysts for energy conversion. Although great achievements have been obtained for the study and applications of heterogeneous ligand‐modified catalysts, the systematical refinements of ligand modification strategies are still lacking. Here, we reviewed the ligand modification strategy from both the mechanistic and applicable scenarios by focusing on heterogeneous electrocatalysis. We elucidated the ligand‐modified catalysts in detail from the perspectives of basic concepts, preparation, regulation of physicochemical properties of catalytic sites, and applications in different electrocatalysis. Notably, we bridged the electrocatalytic performance with the electronic/steric effects induced by ligand modification to gain intrinsic structure‐performance relations. We also discussed the challenges and future perspectives of ligand modification strategies in heterogeneous catalysis.

UNIQUE: A Framework for Uncertainty Quantification Benchmarking.

Machine learning (ML) models have become key in decision-making for many disciplines, including drug discovery and medicinal chemistry. ML models are generally evaluated prior to their usage in high-stakes decisions, such as compound synthesis or experimental testing. However, no ML model is robust or predictive in all real-world scenarios. Therefore, uncertainty quantification (UQ) in ML predictions has gained importance in recent years. Many investigations have focused on developing methodologies that provide accurate uncertainty estimates for ML-based predictions. Unfortunately, there is no UQ strategy that consistently provides robust estimates about model's applicability on new samples. Depending on the dataset, prediction task, and algorithm, accurate uncertainty estimations might be unfeasible to obtain. Moreover, the optimum UQ metric also varies across applications, and previous investigations have shown a lack of consistency across benchmarks. Herein, the UNIQUE (UNcertaInty QUantification bEnchmarking) framework is introduced to facilitate a comparison of UQ strategies in ML-based predictions. This Python library unifies the benchmarking of multiple UQ metrics, including the calculation of nonstandard UQ metrics (combining information from the dataset and model), and provides a comprehensive evaluation. In this framework, UQ metrics are evaluated for different application scenarios, e.g., eliminating the predictions with the lowest confidence or obtaining a reliable uncertainty estimate for an acquisition function. Taken together, this library will help to standardize UQ investigations and evaluate new methodologies.