Results 61 to 70 of about 1,209 (211)

Forecast‐Error Diagnostics in Neural Weather Models

Quarterly Journal of the Royal Meteorological Society, EarlyView.
Deep learning weather prediction models enable efficient forecast‐error diagnostics through auto‐differentiation and low computational cost. We apply grid‐point relaxation and gradient‐based error sensitivity to identify key forecast‐error sources. Results show that medium‐range forecasts in the midlatitudes benefit most from relaxing the stratosphere ...
Uroš Perkan, Gregor Skok, Žiga Zaplotnik   +2 more
wiley   +1 more source

Not All Missing Data are Equal: Choosing the Right Imputation Method for Binary Datasets

Quality and Reliability Engineering International, EarlyView.
ABSTRACT Missing binary predictors are common in reliability, quality control, and industrial decision systems, yet imputation methods are often chosen by convenience rather than evidence. We conduct a Monte Carlo study comparing mode substitution, sequential hot‐deck, missForest, MICE, and KNN with three neighbourhood sizes under MCAR, MAR, and MNAR ...
Manuel Delfino, Fabio Rapallo
wiley   +1 more source

Adaptive Sliding‐Mode Control of a Perturbed Diffusion Process With Pointwise In‐Domain Actuation

International Journal of Robust and Nonlinear Control, EarlyView.
ABSTRACT A sliding mode–based adaptive control law is proposed for a class of diffusion processes featuring a spatially‐varying uncertain diffusivity and equipped with several point‐wise actuators located at the two boundaries of the spatial domain as well as in its interior.
Paul Mayr, Alessandro Pisano, Stefan Koch, Markus Reichhartinger   +3 more
wiley   +1 more source

Deep learning‐based super‐resolution reconstruction and improved YOLOv9 for efficient benthos detection: a case study at Lake Hamana, Japan

Remote Sensing in Ecology and Conservation, EarlyView.
This study presents a UAV‐based framework that integrates deep learning‐based super‐resolution reconstruction and an enhanced YOLO detector to improve centimetre‐scale benthic organism monitoring. Using hermit crabs in Lake Hamana, a coastal lagoon in Japan, as a case study, the method substantially enhanced small‐object detection performance ...
Fan Zhao, Bangzhang Ma, Dianhan Xi, Jiaqi Wang, Yijia Chen, Yongying Liu, Xinlei Shao, Mowen Zhang, Guocheng Zhang, Jundong Chen, Katsunori Mizuno   +10 more
wiley   +1 more source

Synergies of Geospatial and Digital Technologies for Sustainable Rural Development: A Data‐Driven Analysis of Topics and Novelty Assessment

Sustainable Development, EarlyView.
ABSTRACT The adoption of geospatial and digital technologies, including Geographic Information Systems (GIS), Building Information Modelling (BIM), Digital Twins, the Internet of Things (IoT) and Artificial Intelligence (AI), is increasingly recognised as key enablers of sustainable development.
Monica C. M. Parlato, Andrea Pezzuolo
wiley   +1 more source

Development and Validation of a Next‐Generation Mechanistic Model of the Electric Arc Furnace

steel research international, EarlyView.
This study presents a next‐generation mechanistic model of the electric arc furnace (EAF). It describes equations for all crucial processes appearing during the steel‐recycling process in an EAF, i.e., thermal, mass, and chemical. The model was parameterized and validated using industrial EAF data.
Vito Logar, Igor Škrjanc
wiley   +1 more source

A Detailed and Comprehensive Account of Fractional Physics‐Informed Neural Networks: From Implementation to Efficiency

Artificial Intelligence for Engineering, EarlyView.
Caputo‐based fPINNs accurately solve fractional ODEs and PDEs while exposing an accuracy–cost trade‐off driven by the history‐dependent fractional derivative. Temporal collocation and shorter time windows are the most effective strategies for improving early‐time accuracy without unnecessary spatial refinement.
Donya Dabiri, Joshua DaRosa, Milad Saadat, Deepak Mangal, Safa Jamali   +4 more
wiley   +1 more source

APTNet: A Condition‐Sensitive Modulation Framework for Surface Pressure Prediction on Supersonic Aircraft

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Accurate surface‐pressure prediction over broad operating envelopes is critical for supersonic aerodynamic analysis and design. To overcome the bottlenecks of traditional computational fluid dynamics (CFD) in real‐time performance and computational efficiency, data‐driven deep learning methods have emerged. However, existing data‐driven models
Hongbin Xu, Yin Long, Junlin Wu
wiley   +1 more source

Dissecting Glioma Heterogeneity: A Deep Hybrid Graph Convolutional Network With Hinge Attention for Causal‐Effect Explainability

CAAI Transactions on Intelligence Technology, EarlyView.
ABSTRACT Brain tumour classification is a critical task in medical imaging that requires accurate and interpretable solutions to assist in clinical decision‐making. In this paper, we present GraphConvNet‐X, a novel hybrid model that integrates convolutional neural networks (CNNs) for spatial feature extraction with graph neural networks (GNNs) that ...
Sultanul Arifeen Hamim, Mubasshar U. I. Tamim, S. M. Hasan Mahmud, M. F. Mridha, Zeyar Aung   +4 more
wiley   +1 more source

YOLO‐GDCNN: Real‐Time Operating Point Detection for Live Working Robots in the Power Industry

High Voltage, EarlyView.
ABSTRACT In the power industry maintenance, the capability of live working robots to detect and operate with power components in real time is paramount. This paper proposes a cascaded detection framework for real‐time detection of live working operation points, named YOLO‐GDCNN. The framework consists of two parts.
Haoning Zhao, Jiamin Guo, Erbao Dong, Rui Guo, Linkun Zhao, Chaoqun Wang, Xuewen Rong, Yibin Li   +7 more
wiley   +1 more source