🔬 New from Thermopedia: This article revisits the square cavity benchmark, showing how physics-informed neural networks can predict buoyancy-driven flows with high accuracy using limited CFD data.
🔗 thermopedia.com/content/1047...
#CFD #MachineLearning #HeatTransfer
Fractional-Order Prey−Predator Models with Parameter Estimation via Fractional Physics-Informed Neural Networks (fPINNS)
www.dl.begellhouse.com/journals/558...
#FractionalCalculus #MachineLearning #MathBiology
Quantum Computing CFD Simulations: Review and State of the Art
dl.astfe.org/conferences/...
#QuantumComputing #CFD #AerospaceEngineering
🔬 New from Thermopedia: Changing Paradigm for Space Exploration proposes docking reusable upper stages in LEO to reach the Moon, Mars, and beyond using proven rockets.
🔗 thermopedia.com/content/1046...
#SpaceExploration #PropulsionEngineering
New from Thermopedia: "Anomalies in Fluid's Behavior Around the Critical Point" by Almara, Wang & Prasad presents a unified thermodynamic model redefining the critical point: thermopedia.com/content/1045...
#SupercriticalFluids #HeatTransfer
Hybrid Chance-Constrained Optimal Power Flow under Load and Renewable Generation Uncertainty using Enhanced Multi-Fidelity Graph Neural Networks
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
Vol. 7, Iss. 1 of Journal of Machine Learning for Modeling and Computing out now!
From predator-prey neural networks to faster battery simulations, this issue is at the cutting edge of ML and scientific computing.
📖 www.dl.begellhouse.com/journals/558...
#MachineLearning
Flow Map Learning for Unknown Dynamical Systems: Overview, Implementation, and Benchmarks
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
Physics-Informed Neural Networks for Modeling of 3D Flow Thermal Problems with Sparse Domain Data
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
Transfer Learning on Multi-Dimensional Data: A Novel Approach to Neural Network-Based Surrogate Modeling
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
ChatGPT for Programming Numerical Methods
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
AI-Enabled Cardiovascular Models Trained on Multifidelity Simulations Data
dl.begellhouse.com/journals/558...
#MachineLearningMaterials #AIinMaterials #ComputationalMaterialsScience
Why invest in mathematically guided ML for biology now? New special issue explores how math, biology & ML convergence enables deeper insights from complex datasets.
Read now: dl.begellhouse.com/journals/558...
#BioML #MathematicalModeling
📊 Vol. 16, Issue 1 of International Journal for Uncertainty Quantification is out now!
Accelerating optimization under uncertainty. Revolutionary ensemble filtering. Novel Bayesian frameworks.
Read: www.dl.begellhouse.com/journals/520...
#UncertaintyQuantification
How can AI improve vaccine distribution? New research uses physics-informed neural networks to estimate disease parameters & calculate optimal distribution for diverse populations—even with noisy data.
dl.begellhouse.com/journals/558...
#PhysicsInformedML #VaccineDistribution
Can ML fill gaps in groundwater monitoring? Random forest methods achieve 90% accuracy for random gaps, 50% for contiguous gaps. Novel sequential approach tackles missing extremes—the toughest challenge.
dl.begellhouse.com/journals/558...
#EnvironmentalDataScience #GroundwaterMonitoring
How to predict population dynamics with incomplete data? fPINNs provide a robust framework for fractional prey-predator models, accurately inferring predator populations from prey data alone under real-world constraints.
dl.begellhouse.com/journals/558...
#PhysicsInformedML #PopulationDynamics
Brittle materials fail without warning—until now. New data-driven framework combines phase field modeling & ML to predict failure via virtual sensors and pattern recognition, maintaining accuracy despite data noise.
dl.begellhouse.com/journals/558...
#DataDrivenEngineering #MLForStructures
How can AI accelerate nuclear waste safety? New ML emulators rapidly simulate complex repository processes, comparing random forests vs neural networks for uranium prediction in clay buffers.
dl.begellhouse.com/journals/558...
#MLforEngineering #NuclearSafety
26 citations: Reimagining generative modeling—diffusion models create labeled data via training-free score estimation, enabling supervised learning of simple architectures that outperform traditional approaches.
📖 www.dl.begellhouse.com/journals/558...
#GenerativeModeling #MLInnovation
31 citations: Neural ODE framework infers internal material states from observable quantities using Coleman-Gurtin theory. Dual networks respect thermodynamic laws through constrained weights.
📖 www.dl.begellhouse.com/journals/558...
#PhysicsGuidedML #MaterialsInformatics
Happy New Year! 🎊
As 2026 begins, we celebrate the Year of the Horse, a symbol of energy, progress, and optimism in Chinese tradition. To our scholarly community: may this year bring success, groundbreaking discoveries, and new opportunities!
#HappyNewYear #YearOfTheHorse
45 citations: Deep neural networks with memory learn reduced governing equations from partial observations using Mori-Zwanzig formulation—capturing hidden dynamics when full measurements aren't feasible.
📖 www.dl.begellhouse.com/journals/558...
#DataDrivenModeling #DeepLearning
64 citations: Multifidelity transfer learning trains deep CNNs using mostly cheap low-resolution simulations supplemented with select high-res runs—delivering expensive method accuracy at a fraction of the cost.
📖 www.dl.begellhouse.com/journals/558...
#PhysicsInformedML #DataScience
66 citations: Tensor basis GP models for hyperelastic materials build physical invariances into model structure, achieving better predictions with less data than black-box ML approaches.
📖 www.dl.begellhouse.com/journals/558...
#PhysicsInformedML #Materials
71 citations: MyCrunchGPT makes SciML accessible through an LLM-powered framework. Users provide simple prompts; the system handles problem formulation, code generation & analysis with a web interface.
📖 www.dl.begellhouse.com/journals/558...
#GenerativeAI #SciML
125 citations: Can you trust your PINN solutions? This work develops rigorous error estimates for residual minimization in neural networks, providing convergence guarantees for quantifying solution accuracy.
📖 www.dl.begellhouse.com/journals/558...
#ScientificML #PINNs
165 citations: ReLU performs poorly in physics-informed ML due to derivative requirements. Hyperbolic tangent, swish & sine (especially adaptive variants) deliver superior results for multiscale scientific problems.
📖 www.dl.begellhouse.com/journals/558...
#NeuralNetworks #ScientificML
220 citations: Essential roadmap for constrained GP regression. Learn to incorporate physical constraints (positivity, monotonicity, PDEs, boundary conditions) with practical implementation strategies.
📖 www.dl.begellhouse.com/journals/558...
#UncertaintyQuantification #DataEfficientML
359 citations: Standard PIML fails for nonlinear hyperbolic PDEs with shock discontinuities in two-phase porous media transport. The breakthrough? Adding minimal diffusion enables accurate neural network learning.
📖 www.dl.begellhouse.com/journals/558...
#PIML #ScientificML