Efficient Error Research Articles

Engineer CEOs and corporate investment efficiency

Purpose This paper aims to examine whether CEOs with an engineering background increase corporate investment efficiency (CIE). The authors further investigate the role of engineering directors on boards of the above association. Design/methodology/approach Drawing from upper-echelon theory, which suggests that corporate outcomes are a reflection of its top management characteristics, the authors hypothesise a positive association between engineer CEOs and CIE and a positive moderation role of the proportion of engineer directors on boards in the above association. The authors examine this link using a sample of Australian Securities Exchange 200 firms from 2015 to 2022. Engineer CEO data is hand-collected from corporate annual report biographies and investment efficiency is a measure that captures whether the investments are maintained at optimal levels relative to industry-year benchmarks, following the approaches of Biddle et al. (2009), Chen et al. (2011) and the average values of both models. Findings The results indicate support for the hypotheses, revealing that firms managed by engineer CEOs have higher investment efficiency than their counterpart firms. This association is exacerbated in the presence of a higher proportion of engineer directors on boards. The results are robust to year and industry-fixed effects, propensity score matching, alternative measures of investment efficiency and robust standard errors. Our results also remain valid for an industry sub-sample using certain industries in which engineering expertise maybe more desirable (e.g. metals and mining). Research limitations/implications By showing that engineer CEOs are significantly associated with CIE, the authors contribute to upper-echelon literature examining the link between CEO characteristics and corporate outcomes, particularly, investment decision efficiency. The influence of engineering background on corporate outcomes is less examined in the literature; thus, the authors contribute to this thin literature. Originality/value The findings are informative to potential investors in evaluating firms’ investment efficiency before investing in firms. For example, firms with engineer CEOs are likely to maintain efficient investment levels in future years.

Dual-Discriminator Conditional Generative Adversarial Network-based LDPC-Coded OFDM Free-Space OCS for Improving BER Analysis

This paper proposes a Dual-Discriminator Conditional Generative Adversarial Network-based LDPC-Coded OFDM Free-Space OCS for Improving BER Analysis (LDPC-OFDM-FSO-DDcGAN). The proposed LDPC-OFDM-FSO-DDcGAN method containsthe transmitter model, the channel model and the receiver model. The binary data are given to the encoder of LDPC in the transmitter model and the input data encode previously controlling the situation using QAM. To decrease the effects of fading caused by turbulence, the channel model intends a probability density function with FSO-DDcGAN. The maximal ratio combing (MRC), equal gain combining (EGC) and selection combining (SC) can be employed by the combiner to integrate the signal once it has been received from the FSO channel. The combiner is used to improve one signal by combining the several signals received. The bit of data is transformed towards a sequential stream after combiner. The proposed Probability Density Function (PDF) offers high SNR gain, BER reduction and power efficiency when combined with DDcGAN. To achieve large coding gain, the standard coding methods of LDPC are used through only a code percentage as realistic to imitation data. The proposed LDPC-OFDM-FSO-DDcGAN technique is executed in MATLAB. The LDPC-OFDM-FSO-DDcGAN method provides higher power efficiency and lower bit error rate analysed with the existing models.

A Survey on Efficient Vision Transformers: Algorithms, Techniques, and Performance Benchmarking.

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real-world applications due to many hardware and environmental restrictions, such as processing and computational capabilities. Therefore, this survey investigates the most efficient methodologies to ensure sub-optimal estimation performances. More in detail, four efficient categories will be analyzed: compact architecture, pruning, knowledge distillation, and quantization strategies. Moreover, a new metric called Efficient Error Rate has been introduced in order to normalize and compare models' features that affect hardware devices at inference time, such as the number of parameters, bits, FLOPs, and model size. Summarizing, this paper first mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios. Toward the end of this paper, we also discuss open challenges and promising research directions.

Study on the particle dynamic characteristics in a centrifugal pump based on an improved computational fluid dynamics-discrete element model

To accurately investigate the solid–liquid flow mechanisms within the pump, this study employs an improved Computational Fluid Dynamics-Discrete Element Method (CFD-DEM) approach to examine the solid–liquid interactions in a centrifugal pump. First, the improved CFD-DEM is introduced, focusing on turbulence dissipation near the wall and velocity reconstruction. Then, a comparison is made between the CFD-DEM's performance before and after the enhancements. Finally, an analysis is conducted on how the dynamic characteristics of particles within the pump vary under different solid phase concentration conditions. The study revealed that the particle distribution from the corrected CFD-DEM aligns more closely with the experimental results. At a 2% concentration under the design conditions, the head error was reduced by 0.476%, while the efficiency error decreased by 0.076%. Additionally, as the solid phase concentration increased, there was a corresponding rise in the impact power loss of the particles, dissipative power loss, collision frequency, peak values of particle collisions, and the degree of overlap during these collisions. The comparison revealed that the pressure gradient force has the most significant impact on particle motion. As the pressure gradient force increases, the shear power dissipation of the particles also rises. For solid phase concentrations ranging from 1% to 4%, the average shear power variation during the computation period is between 4.28 × 10−6 W and 5.68 × 10−6 W. As the solid phase concentration increases, the volume fraction of the solid phase distribution on the component wall also gradually rises. These findings provide valuable insights for enhancing the accuracy of research on solid–liquid flow in centrifugal pumps.

Time series prediction of aerosol optical depth across the northern Indian region: integrating PSO-optimized SARIMA-SVR based on MODIS data

AbstractAccurately predicting aerosol optical depth (AOD), a key parameter for characterizing atmospheric aerosols, is essential due to the increasing prevalence of air pollution and its detrimental effects. From existing literature on AOD time-series prediction, linear models like seasonal autoregressive integrated moving average (SARIMA) are commonly used, while nonlinear models such as machine learning (ML) and deep learning (DL) have gained popularity recently for their ability to handle nonlinear patterns. This study introduces a hybrid model, particle swarm optimization-seasonal autoregressive integrated moving average-support vector regression (PSOSARIMA-PSOSVR), which integrates linear and nonlinear modeling through residual modeling to significantly enhance AOD prediction accuracy. By combining these approaches, we aim to better handle the nonlinearities and overall variability in AOD data, leading to more accurate predictions. To address hyperparameter tuning challenges, including the risks of model misspecification and overfitting or underfitting, PSO is utilized for optimization. PSO’s evolutionary optimization ensures efficient tuning for optimal model performance. Monthly AOD data sourced from the moderate resolution imaging spectroradiometer (MODIS) satellite covering the northern Indian region from 2001 to 2019 is used for experiments. Performance metrics such as root mean square error (RMSE), mean absolute percentage error (MAPE), coefficient of determination ($$R^2$$ R 2 ), Nash-Sutcliffe efficiency (NSE), and root mean square error ratio (RSR) are employed to evaluate model accuracy and dependability. The results of this study illustrate that the proposed PSOSARIMA-PSOSVR model outperforms both standalone PSOSARIMA and PSOSVR models. Moreover, it consistently surpasses SARIMA, SVR, and long short-term memory (LSTM) in AOD prediction, effectively addressing non-stationarity and variability challenges in AOD data. This study suggests the hybrid model as a promising approach for improving the accuracy of AOD prediction.

Strong error bounds for Trotter and strang-splittings and their implications for quantum chemistry

Efficient error estimates for the Trotter product formula are central in quantum computing, mathematical physics, and numerical simulations. However, the Trotter error's dependency on the input state and its application to unbounded operators remains unclear. Here, we present a general theory for error estimation, including higher-order product formulas, with explicit input state dependency. Our approach overcomes two limitations of the existing operator-norm estimates in the literature. First, previous bounds are too pessimistic as they quantify the worst-case scenario. Second, previous bounds become trivial for unbounded operators and cannot be applied to a wide class of Trotter scenarios, including atomic and molecular Hamiltonians. Our method enables analytical treatment of Trotter errors in chemistry simulations, illustrated through a case study on the hydrogen atom. Our findings reveal the following: (i) for states with fat-tailed energy distribution, such as low-angular-momentum states of the hydrogen atom, the Trotter error scales worse than expected (sublinearly) in the number of Trotter steps; (ii) certain states do not admit an advantage in the scaling from higher-order Trotterization and, thus, the higher-order Trotter hierarchy breaks down for these states, including the hydrogen atom's ground state; (iii) the scaling of higher-order Trotter bounds might depend on the order of the Hamiltonians in the Trotter product for states with fat-tailed energy distribution. Physically, the enlarged Trotter error is caused by the atom's ionization due to the Trotter dynamics. Mathematically, we find that certain domain conditions are not satisfied by some states so higher moments of the potential and kinetic energies diverge. Our analytical error analysis agrees with numerical simulations, indicating that we can estimate the state-dependent Trotter error scaling genuinely. Published by the American Physical Society 2024

Density adaptive path based on stacked rotation convolution model in ultra-precision robotic optical polishing

Deterministic optics fabrication using sub-aperture tools has been vital for manufacturing precision optical surfaces, industrial robotic polishing, which is a more economical and intelligent method is required in modern fabrication process. However, the challenge of robotic polishing lies in the widely used spiral and raster paths, which may leave excess waviness from the tool path, and the unavoidable constant removal layer is added to obtain positive dwell time which cause low polishing accuracy. The waviness can be removed by either using smoothing tools sequentially or randomizing the tool path. However, process efficiency and accuracy are not well considered in the existing tool-path planning. A density adaptive path based on a stacked rotation convolution model to ensure polishing accuracy and efficiency while avoiding waviness generation is proposed in this study, and then the dwell time is calculated by anti-aliasing space-variant deconvolution. The robotic polisher experimental results confirm that the root mean square (RMS) of the final surface figure has been successfully reduced and stabilized at 7.355 nm, and the convergence effect at unit wavelength has been significantly augmented with an improvement of 367%, reducing the measurement from 28% to 131%; in addition, no obvious mid-spatial frequency (MSF) peak was generated in the PSD analysis of density adaptive path polishing results. Henceforth, the polishing accuracy, efficiency, and MSF error of robotic polishing can be greatly enhanced.

A novel carrier index M‐ary differential chaos shift keying modulation scheme

AbstractTo obtain better spectral efficiency and higher bit rate, a novel carrier index M‐ary differential chaos shift keying modulation scheme is proposed. In this system, part of subcarriers is assigned to the chaotic reference so that it can carry extra data bits through carrier index modulation, while one of the remaining subcarriers is activated to transmit the data‐bearing signal. In addition, M‐ary DCSK modulation is also applied to data‐bearing signals based on the constellation theory and Walsh codes. Theoretical bit error rate expressions are derived over the multipath Rayleigh fading and additive white Gaussian noise channels. Simulations and comparisons are performed with various combinations of chaotic sequence lengths, subcarrier numbers and constellation sizes. Results show that the proposed scheme can outperform other counterparts in both spectral efficiency and bit error rate performances.

Perceptual Pigeon Galvanized Optimization of Multi-objective CNN on the Identification and Classification of Mango Leaves Disease

Aims The aim of this study is to develop a strong Multi-objective Convolutional Neural Network (MOCNN) optimized using Perceptual Pigeon Galvanized Optimization (PPGO) for accurate identification and classification of mango leaf diseases. This approach aims to increase classification accuracy, computational efficiency, and generalization ability. The ultimate goal is to improve disease management in mango crops through advanced image-based diagnostic techniques. Background Demands for the consumption of mango (Mangifera indica) fruit and its leaves were growing exponentially in all parts of the world due to its large health benefits for various organs in the human body. However, these plants were largely exposed to various kinds of microbial diseases during cultivation despite the application of pesticides. Hence, it is becoming a significant threat to the farmers and to the food industry. Objective The objectives of this study are to develop reliable methods for the early identification of mango leaf diseases, enabling prompt intervention and reducing crop damage. Additionally, the study aims to provide effective disease management applications that will help farmers minimize crop losses and maintain their economic stability. Methods PPGO is an advanced optimization algorithm inspired by the natural foraging behavior of pigeons. It integrates perceptual hashing and galvanic responses to adaptively adjust the search process, allowing for efficient exploration and exploitation of the solution space. The multi-objective convolutional neural network is trained to minimize a composite loss function that considers classification accuracy, computational efficiency, and generalization error. Results The Perceptual Pigeon Galvanized Optimization (PPGO) with a Multi-objective Convolutional Neural Network (MOCNN) demonstrates superior performance compared to traditional CNN optimization techniques. The results show an accuracy of 96%, recall of 94%, precision of 92%, and an F1 score of 92%. These metrics surpass those of existing methods such as Efficient Supervised Learning based on Deep Neural Network (ESDNN), Hierarchical Deep Learning Support Vector Machine (HDLSVM), Ordinal Regression Neural Network (ORNN), Deep Convolutional Generative Adversarial Network (DCGAN), Convolutional Neural Network (CNN), Local Contrast Normalization Convolutional Neural Network (LCNN), and Visual Geometry Group Network (VGGNET 19). Conclusion The integration of Perceptual Pigeon Galvanized Optimization with a Multi-objective Convolutional Neural Network offers a powerful approach for identifying and classifying mango leaf diseases. The proposed method effectively balances multiple performance metrics, leading to a robust and efficient model suitable for real-world agricultural applications.

A gas-surface interaction algorithm for discrete velocity methods in predicting rarefied and multi-scale flows: For Maxwell boundary model

The discrete velocity method (DVM) for rarefied flows and the unified methods (based on the DVM framework) for flows in all regimes, from continuum one to free molecular one, have worked well as precise flow solvers over the past decades and have been successfully extended to other important physical fields. Both DVM and unified methods endeavor to model the gas-gas interaction physically. However, for the gas-surface interaction (GSI) at the wall boundary, they have only use the full accommodation boundary up to now, which can be viewed as a rough Maxwell boundary with a fixed accommodation coefficient (AC) at unity, deviating from the real value. For example, the AC for metal materials typically falls in the range of 0.8 to 0.9. To overcome this bottleneck and extend the DVM and unified methods to more physical boundary conditions, an algorithm for Maxwell boundary with an adjustable AC is established into the DVM framework. The Maxwell boundary model splits the distribution of the bounce-back molecules into specular ones and Maxwellian (normal) ones. Since the bounce-back molecules after the spectral reflection does not math with the discrete velocity space (DVS), both macroscopic conservation (from numerical quadrature) and microscopic consistency in the DVS are hard to achieve in the DVM framework. In this work, this problem is addressed by employing a combination of interpolation methods for mismatch points in DVS and an efficient numerical error correction method for micro-macro consistency. On the other hand, the current Maxwell boundary for DVM takes the generality into consideration, accommodating both the recently developed efficient unstructured velocity space and the traditional Cartesian velocity space. Moreover, the proposed algorithm allows for calculations of both monatomic gases and diatomic gases with internal degrees in DVS. Finally, by being integrated with the unified gas-kinetic scheme within the DVM framework, the performance of the present GSI algorithm is validated through a series of benchmark numerical tests across a wide range of Knudsen numbers.

Effects of Tropospheric Turbulence on Radio Signal Data Passing Atmospheric Communication Links

AbstractThis paper analyzes the effects of turbulent structures of different sizes on the structural parameter of the refractive index and, consequently, on the scintillation index of radio waves passing through atmospheric channels with fading. The relationships between these parameters are analyzed and discussed not only for weak turbulence, but also for moderate and strong turbulences occurring in the mid‐latitude troposphere. By using the relationship between the scintillation index of signal intensity and the well‐known Rician parameter of fast fading, and by obtaining the relationships between the signal data stream parameters, capacity, spectral efficiency, and bit error rate, and factor of fast fading, we have numerically analyzed various cases of data transmission over tropospheric communication links with fading. This analysis considers the effects of weak, moderate, and strong turbulence on the quality of data transmission over such communication links. The results of this study can be used to improve the design and performance of tropospheric communication links in the presence of turbulence.

Efficient Error Detection Cryptographic Architectures Benchmarked on FPGAs for Montgomery Ladder

Efficient Error Detection Cryptographic Architectures Benchmarked on FPGAs for Montgomery Ladder

Data-driven optimization of coastal sea level monitoring: Leveraging known patterns for enhanced reconstruction

Efficiently configuring sea level monitoring stations is crucial for obtaining accurate spatiotemporal data while managing operational and maintenance costs and addressing the challenges posed by missing data. This study focuses on optimizing the selection of stations within Turkey's coastal sea level monitoring network by leveraging the inherent lower dimensionality in data. The network consists of 18 stations distributed along Turkey's coastline. To identify dominant patterns in historical sea level data, Empirical Orthogonal Function (EOF) analysis was employed, followed by the application of the QR decomposition with column pivoting algorithm. Model performance is assessed using the Nash-Sutcliffe coefficient of efficiency (CE) and root mean square error (RMSE). Remarkably, the results demonstrated that reconstructing the entire dataset, encompassing all 18 stations was possible with a CE of 0.94 and an RMSE of 0.06. Even utilizing data from two or three stations alone achieves acceptable reconstruction accuracy. The effectiveness of EOF analysis combined with QR with column pivoting algorithm suggests promising applications in various scientific fields.

A robust multi-model framework for groundwater level prediction: The BFSA-MVMD-GRU-RVM model

Groundwater level prediction is critical for environmental protection and agricultural planning. Accurate predictions help manage risks associated with excessive groundwater extraction and land subsidence. This study introduces a novel model combining multivariate variational mode decomposition (MVMD), gated recurrent unit (GRU), and relevance vector machine (RVM), along with the Boruta feature selection algorithm (BFSA), for precise groundwater level forecasting. The model operates in several stages. First, BFSA selects the most informative features as input data. Next, the MVMD method decomposes the time series of these features. The GRU model then extracts crucial information from these decompositions. Finally, the extracted data is fed into the RVM model to predict groundwater levels one month ahead in Iran's Bastam Plain. To assess the model's accuracy, multiple error indices were employed. The MVMD-GRU-RVM model outperformed other models, improving the testing Nash–Sutcliffe Efficiency and mean absolute error by 24–31 % and 6–61 %, respectively. Additionally, it enhanced R2 values of the MVMD-CNN, MVMD-RNN, MVMD-MLP, and MVMD-RBFNN models by 1.0–3.33 %. These results demonstrate that the MVMD-GRU-RVM model significantly improves groundwater level prediction accuracy. The key points of the paper are the successful effectiveness of MVMD in processing non-stationary time series and improving the predictive performance of the models, as well as the high ability of the GRU model in data feature extraction. The study also shows that the novel model can provide outputs with lower uncertainty.

Coupler-Assisted Leakage Reduction for Scalable Quantum Error Correction with Superconducting Qubits.

Superconducting qubits are a promising platform for building fault-tolerant quantum computers, with recent achievement showing the suppression of logical error with increasing code size. However, leakage into noncomputational states, a common issue in practical quantum systems including superconducting circuits, introduces correlated errors that undermine quantum error correction (QEC) scalability. Here, we propose and demonstrate a leakage reduction scheme utilizing tunable couplers, a widely adopted ingredient in large-scale superconducting quantum processors. Leveraging the strong frequency tunability of the couplers and stray interaction between the couplers and readout resonators, we eliminate state leakage on the couplers, thus suppressing space-correlated errors caused by population propagation among the couplers. Assisted by the couplers, we further reduce leakage to higher qubit levels with high efficiency (98.1%) and low error rate on the computational subspace (0.58%), suppressing time-correlated errors during QEC cycles. The performance of our scheme demonstrates its potential as an indispensable building block for scalable QEC with superconducting qubits.

Generating Payloads of Power Monitoring Systems Compliant with Power Network Protocols Using Generative Adversarial Networks

In the network environment of power systems, payload generation is used to construct data packets, which are used to obtain data for the security management of network assets. Payloads generated by existing methods cannot satisfy the specifications of the protocols in power systems, resulting in low efficiency and information errors. In this paper, a payload generation model, LoadGAN, is proposed by using generative adversarial networks (GANs). Firstly, we find segmentation points to cut payloads into different segment sequences using sliding window schema based on Bayesian optimization. Then, we use different payload segments to train several child generators to generate corresponding parts of a whole payload. Segment sequences generated by these generators are assembled to form a whole new payload that is compliant with the specifications of the original network protocol. Experiments on the Mozi botnet dataset show that LoadGAN achieves precise payload segmentation while maintaining a high payload effectiveness of 85.5%, which is a 40% improvement compared to existing methods.

Aerodynamic design of two-stage centrifugal compressor for vehicle hydrogen fuel cell

Abstract The on-board hydrogen fuel cell is a power generation device that converts the chemical energy of hydrogen and oxygen directly into electrical energy. The centrifugal compressor mainly provides oxygen for the cathode of the fuel cell system. With the rapid development of the hydrogen fuel cell industry, the key components of the air compressor field are also developing rapidly. In the technical route, most companies launched two-stage compression centrifugal air compressors in response to the increasing power of the product development trend. The newly developed hydrogen fuel cell system power has reached above 120kW to meet the needs of heavy trucks and other applications. Both the flow rate and pressure ratio of the air compressor are required to increase accordingly. Based on the reduction of parasitic power, the optimal efficiency at the working point of the two-stage centrifugal air compressor is taken as the design goal, from one-dimensional aerodynamic calculation to two-dimensional flow channel design. Finally, the feasibility and accuracy of the aerodynamic design are verified based on key parameters such as pressure ratio, flow rate, and efficiency of the final stage through CFD flow field simulation and test data comparison. The results show that the flow rate is consistent with the calculated flow field, and the maximum error of pressure ratio and efficiency is less than 2%, which meets the target requirements. The research results can provide a research and development basis for designing high-performance centrifugal air compressors for fuel cell vehicles.

Identification of Concrete Crack Using Deep Learning Based Approach

Cracks reflect the safety and durability of concrete structures, and the existing artificial crack detection has the disadvantages of low efficiency and large error. However, the use of deep learning of images to identify cracks has the advantages of high efficiency, small error and low cost. This paper systematically discusses the deep learning in the identification of concrete structure cracks, expounds the deep learning technology, studies the SqueezeNet network model and YOLO (You Only Look Once) network model in the field of concrete structure crack identification, and improves the model according to the test results. In this paper, the classification accuracy based on crack trend is improved by increasing the width and depth of the Fire module of the SqueezeNet network. Secondly, the target detection accuracy is improved by the transfer learning of the YOLO model. The results show that the classification accuracy of the improved SqueezeNet model is more than 82% and the recognition accuracy of YOLO model is more than 92%.

Evaluating Performance of ChatGPT on MKSAP Cardiology Board Review Questions

Chat Generative Pretrained Transformer (ChatGPT) is a natural language processing tool created by OpenAI. Much of the discussion regarding artificial intelligence (AI) in medicine is the ability of the language to enhance medical practice, improve efficiency and decrease errors. The objective of this study was to analyze the ability of ChatGPT to answer board-style cardiovascular medicine questions by using the Medical Knowledge Self-Assessment Program (MKSAP).The study evaluated the performance of ChatGPT (versions 3.5 and 4), alongside internal medicine residents and internal medicine and cardiology attendings, in answering 98 multiple-choice questions (MCQs) from the Cardiovascular Medicine Chapter of MKSAP. ChatGPT-4 demonstrated an accuracy of 74.5 %, comparable to internal medicine (IM) intern (63.3 %), senior resident (63.3 %), internal medicine attending physician (62.2 %), and ChatGPT-3.5 (64.3 %) but significantly lower than cardiology attending physician (85.7 %). Subcategory analysis revealed no statistical difference between ChatGPT and physicians, except in valvular heart disease where cardiology attending outperformed ChatGPT (p = 0.031) for version 3.5, and for heart failure (p = 0.046) where ChatGPT-4 outperformed senior resident. While ChatGPT shows promise in certain subcategories, in order to establish AI as a reliable educational tool for medical professionals, performance of ChatGPT will likely need to surpass the accuracy of instructors, ideally achieving the near-perfect score on posed questions.

Superiority of artificial neural networks over conventional hydrological models in simulating urban catchment runoff

ABSTRACT The synergistic impacts of climate change and urbanisation have amplified the recurrence and austerity of intense rainfall events, exacerbating persistent flooding risk in urban environments. The intricate topography and inherent non-linearity of urban hydrological processes limit the predictive accuracy of conventional models, leading to significant discrepancies in flow estimation. Recent advancements in artificial neural network (ANNs) have demonstrated remarkable progress in mitigating most limitations, specifically in simulating complex, non-linear relationships, without an intricate comprehension of the underlying physical processes. This paper proposes a deep learning ANN-based flow estimation model for enhanced precision simulation of streamflow in urban catchments, with the research's distinctive contribution involving rigorous comparative evaluation of the developed model against the established Australian hydrological model, RORB. Gardiners Creek catchment, an urban catchment situated in East Melbourne was designated as the study area, with the model being calibrated upon historical storm incidences. The findings reveal that the ANN model substantially outperforms RORB, as evidenced by superior correlation, prediction efficiency, and lower generalisation error. This underscores the ANN's adeptness in accurately replicating non-linear-catchment responses to storm events, marking a substantial advancement over conventional modelling practices and indicating its transformative potential for enhancing flood prediction precision and revolutionising current estimation practices.