Results 71 to 80 of about 5,170 (214)

Machine Learning‐Based Correction of Reanalysis Surface Radiation Fluxes Using Ground‐Measured Data in the Southern Brazilian Pampa Biome

International Journal of Climatology, EarlyView.
This study demonstrates that ERA5 provides more accurate surface radiation flux estimates than MERRA2 across the Southern Brazilian Pampa. Machine learning models, particularly Random Forest, further improved the precision of reanalysis data for climate applications.
Olusola Samuel Ojo, Michel Baptistella Stefanello, Alecsander Mergen, Maria Eduarda Oliveira Pinheiro, Vanessa de Arruda Souza, Débora Regina Roberti   +5 more
wiley   +1 more source

PVkNN: A Publicly Verifiable and Privacy-Preserving Exact kNN Query Scheme for Cloud-Based Location Services

Modelling
The k-nearest- neighbor (kNN) algorithm is crucial in data mining and machine learning, yet its deployment on large-scale datasets within cloud environments presents significant security and efficiency challenges. This paper is dedicated to advancing the
Jingyi Li, Yuqi Song, Chengliang Tian, Weizhong Tian   +3 more
doaj   +1 more source

Image‐based and biochemical multimodal phenotyping for explainable classification of chia (Salvia hispanica L.) genotypes

Journal of the Science of Food and Agriculture, EarlyView.
Abstract BACKGROUND This study developed an explainable machine learning framework integrating morphological, color, and biochemical characteristics for classifying chia (Salvia hispanica L.) genotypes. A dataset was assembled from 1200 seed images spanning four genotypes, from which 17 morphological and color features were extracted.
Sevim Akcura, Irem Poyraz, Beyza Ciftci, Mahmut Kaplan   +3 more
wiley   +1 more source

Cross‐regional and temporal generalizability of portable visible spectroscopy for olive maturity classification

Journal of the Science of Food and Agriculture, EarlyView.
Abstract BACKGROUND Olive maturity governs lot destination and the yield–quality trade‐off in olive oil production, yet it is still monitored by subjective visual scoring of the Jaén index. Spectroscopic alternatives have relied mainly on near‐infrared instruments, with scarce evidence from Brazilian orchards and almost no evaluation of spatial or ...
David Mojaravscki, Paulo S Graziano Magalhães   +1 more
wiley   +1 more source

Mass Spectrometry in Authentication and Forensic Approaches for Determining the Origin of Hazardous Chemicals

Mass Spectrometry Reviews, EarlyView.
ABSTRACT Identification of a chemical agent yields insights into its physicochemical properties. By examining the intrinsic characteristics and environment of a compound, information about its history can be gathered. The main objective of authentication/forensic approaches to chemicals is to trace the history of the compound's origin, regardless of ...
Carla Orlandi, Grégoire Delaporte, Christine Albaret, Emmanuel Joubert, Anne Bossée, Emilien L. Jamin, Laurent Debrauwer   +6 more
wiley   +1 more source

ChatXRD: A LLM‐Driven Framework for Crystal System Classification and Lattice Parameters Prediction Based on XRD

Materials Genome Engineering Advances, EarlyView.
ChatXRD is an LLM‐driven framework that autonomously performs crystal system classification and lattice parameter prediction from XRD data. By integrating a GPT‐5‐based agent with specialized tools and decision tree reasoning, it achieves state‐of‐the‐art accuracy, enabling scalable and reliable high‐throughput materials characterization. ABSTRACT High‐
Xiaoyue He, Qian Cao, Bo Chen, Kun Hu, Yin Xu, Mingjun Xiao, Xin Chen   +6 more
wiley   +1 more source

Creep Mechanism Mapping of Lamellar Ti–Al Alloys With Crystal‐Plasticity Phase‐Field and Interpretable Machine Learning Framework

Materials Genome Engineering Advances, EarlyView.
Crystal‐plasticity phase‐field simulations combined with stacked machine learning map the creep microstructure relationship in lamellar Ti‐Al alloys. Interpretable learning identifies lamellar thickness, elastic strain energy, and interfacial energy as dominant factors governing the diffusion‐to‐dislocation creep transition and overall creep resistance.
Zan Zhang, Kunning Niu, Shenglong Wang, Xianshun Wu, Yongsheng Li   +4 more
wiley   +1 more source

A Supervised Learning Framework for Accelerating Solvers and Metaheuristics in Routing Problems

Networks, EarlyView.
ABSTRACT Routing problems such as the traveling salesman problem (TSP) and the capacitated vehicle routing problem (CVRP) are computationally challenging due to the exponential growth of their feasible solution spaces with increasing instance size.
Johannes Gückel, Stefan Voigt, Pirmin Fontaine   +2 more
wiley   +1 more source

AI‐Based PV Fault Detection: Benchmarking Indicators and Feature Selection Methods

Progress in Photovoltaics: Research and Applications, EarlyView.
This article benchmarks indicators for automated defect detection in photovoltaic modules. The methodology has three phases: generating a simulated ideal defect‐free I‐V curve, comparing it with experimental measurements under standard test conditions, calculating indicators, and applying a feature‐selection strategy to identify the most relevant ...
Cristian Terrados‐López, Diego Granados‐López, Jesús‐Marcos García‐Alonso, David Gonzalez‐Peña, Cristina Alonso‐Tristán   +4 more
wiley   +1 more source

Automatic insect identification, counting, and monitoring techniques: a review

Pest Management Science, EarlyView.
Automated insect monitoring increasingly integrates optical, acoustic, infrared, radar, electrostatic, and biosensing technologies with artificial intelligence. No single approach is universally optimal; reliable deployment depends on task‐specific validation, representative datasets, robustness under field conditions, energy autonomy, connectivity ...
Mariano González García, Juan Carlos Noguera Polania, Rosana González Combarros, José Ignacio López Sánchez   +3 more
wiley   +1 more source