# Weiqi Ji · 季维奇 — Research publications https://jiweiqi.github.io ## Scientific machine learning - **2023** [Kinetics parameter optimization of hydrocarbon fuels via neural ordinary differential equations](https://jiweiqi.github.io/papers/kinetics-neural-ode/index.md) — Treats kinetic parameter optimization as neural ODE training to calibrate hydrocarbon-fuel models against experimental targets. - **2022** [Autonomous kinetic modeling of biomass pyrolysis using chemical reaction neural networks](https://jiweiqi.github.io/papers/biomass-crnn/index.md) — Learns biomass pyrolysis kinetics from thermogravimetric measurements with interpretable chemical reaction neural networks. - **2022** [SGD-based optimization in modeling combustion kinetics: Case studies in tuning mechanistic and hybrid kinetic models](https://jiweiqi.github.io/papers/sgd-kinetics/index.md) — Uses differentiable simulation and stochastic gradient descent to optimize mechanistic and hybrid chemical kinetic models. - **2021** [Arrhenius.jl: A Differentiable Combustion Simulation Package](https://jiweiqi.github.io/papers/arrhenius-jl/index.md) — Introduces differentiable combustion modeling in Julia for gradient-based sensitivity analysis, calibration, uncertainty quantification and model discovery. - **2021** [Autonomous Discovery of Unknown Reaction Pathways from Data by Chemical Reaction Neural Network](https://jiweiqi.github.io/papers/crnn/index.md) — Infers interpretable reaction pathways and kinetic parameters from concentration time series using a neural architecture based on mass-action and Arrhenius laws. - **2021** [Data-Driven Approaches to Learn HyChem Models](https://jiweiqi.github.io/papers/hychem/index.md) — Applies stochastic gradient descent to calibrate lumped HyChem fuel models against ignition-delay measurements across temperature regimes. - **2021** [Inference of cell dynamics on perturbation data using adjoint sensitivity](https://jiweiqi.github.io/papers/cellbox-adjoint/index.md) — Uses adjoint sensitivity and differentiable programming to infer cell-network dynamics from simulated perturbation-response data. - **2021** [KiNet: A Deep Neural Network Representation of Chemical Kinetics](https://jiweiqi.github.io/papers/kinet/index.md) — Represents time-stepping chemical kinetics with a residual neural network and multi-step training, with ignition-delay gradients for model refinement. - **2021** [Neural Differential Equations for Inverse Modeling in Model Combustors](https://jiweiqi.github.io/papers/inverse-combustors/index.md) — Infers unknown inlet composition and flow fluctuations from sparse combustor-temperature measurements using neural differential equations. - **2021** [Stiff neural ordinary differential equations](https://jiweiqi.github.io/papers/stiff-neural-ode/index.md) — Studies stiff neural ODE training using scale-aware architectures, output and loss scaling, and stabilized gradient calculations. - **2021** [Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics](https://jiweiqi.github.io/papers/stiff-pinn/index.md) — Examines PINN failure on stiff chemical kinetics and uses quasi-steady-state reduction to make the studied systems tractable. ## Uncertainty quantification - **2023** [Kinetic subspace investigation using neural network for uncertainty quantification in nonpremixed flamelets](https://jiweiqi.github.io/papers/flamelet-subspace/index.md) — Uses a neural-network surrogate to identify multidimensional kinetic subspaces for uncertainty propagation across nonpremixed flamelet profiles. - **2023** [Using shock tube species time-histories in Bayesian parameter estimation: Effective independent-data number and target selection](https://jiweiqi.github.io/papers/shock-tube-bayes/index.md) — Examines effective independent-data counts and target selection when using shock-tube species time histories for Bayesian kinetic parameter estimation. - **2021** [Uncertainty analysis in mechanism reduction via active subspace and transition state analyses](https://jiweiqi.github.io/papers/mechanism-reduction-uq/index.md) — Combines active subspaces with an intermediate reduction state to separate uncertainty changes caused by parameter truncation and reaction coupling. - **2020** [Dependence of kinetic sensitivity direction in premixed flames](https://jiweiqi.github.io/papers/premixed-sensitivity/index.md) — Investigates how kinetic sensitivity directions vary through premixed flame structures and their connection to laminar flame speed and extinction. - **2019** [Evolution of sensitivity directions during autoignition](https://jiweiqi.github.io/papers/ignition-sensitivity/index.md) — Relates the sensitivity directions of temperature, species and ignition delay, enabling efficient evaluation of ignition-delay sensitivities. - **2019** [Quantifying kinetic uncertainty in turbulent combustion simulations using active subspaces](https://jiweiqi.github.io/papers/turbulent-uq/index.md) — Uses active subspaces and response surfaces to propagate kinetic uncertainty to the liftoff height of a turbulent Cabra hydrogen jet flame. - **2019** [Uncertainty Propagation in Deep Neural Network Using Active Subspace](https://jiweiqi.github.io/papers/neural-network-uq/index.md) — Builds response surfaces in gradient-based active subspaces to propagate uncertain neural-network inputs at reduced computational cost. - **2018** [Shared low-dimensional subspaces for propagating kinetic uncertainty to multiple outputs](https://jiweiqi.github.io/papers/shared-subspaces/index.md) — Combines single-output active subspaces into a shared low-dimensional representation for propagating kinetic uncertainty to multiple quantities of interest. - **2017** [Propagation of Kinetic Uncertainty through Surrogate Subspace in Combustion Simulations](https://jiweiqi.github.io/papers/surrogate-subspace/index.md) — Explores a low-rank surrogate subspace for propagating kinetic uncertainty, using neural response surfaces and genetic optimization. ## Reviews & applications - **2022** [Machine learning for combustion](https://jiweiqi.github.io/papers/machine-learning-combustion/index.md) — Reviews machine-learning approaches to combustion modeling, experiments and computational prediction. - **2020** [Machine learning model to project the impact of COVID-19 on US motor gasoline demand](https://jiweiqi.github.io/papers/mobility-demand/index.md) — Combines pandemic scenarios, mobility data and machine learning to project US motor-gasoline demand during COVID-19. ## Combustion kinetics - **2017** [Ignition delay measurements of light naphtha: A fully blended low octane fuel](https://jiweiqi.github.io/papers/naphtha-ignition/index.md) — Measures ignition delays of a fully blended low-octane light naphtha fuel. - **2017** [Measurement of reaction rate constants using RCM: A case study of decomposition of dimethyl carbonate to dimethyl ether](https://jiweiqi.github.io/papers/rcm-rate-constants/index.md) — Studies rapid-compression-machine measurement of a reaction rate using dimethyl carbonate decomposition as a case study. - **2017** [On the crossover temperature and lower turnover state in the NTC regime](https://jiweiqi.github.io/papers/ntc-lower-turnover/index.md) — Investigates crossover temperature and the lower turnover state of negative-temperature-coefficient ignition behavior. - **2016** [First-stage ignition delay in the negative temperature coefficient behavior: Experiment and simulation](https://jiweiqi.github.io/papers/first-stage-ntc/index.md) — Combines experiments and simulations to investigate negative-temperature-coefficient behavior in first-stage ignition delay. - **2016** [On the controlling mechanism of the upper turnover states in the NTC regime](https://jiweiqi.github.io/papers/ntc-upper-turnover/index.md) — Studies the kinetic mechanisms controlling the upper turnover states in the negative-temperature-coefficient regime. - **2015** [Intermediate species measurement during iso-butanol auto-ignition](https://jiweiqi.github.io/papers/isobutanol-intermediates/index.md) — Measures intermediate species during iso-butanol autoignition to examine the underlying oxidation pathways.