Gaussian Process Research Articles

Combining spectrum, thermal, and texture features using machine learning algorithms for wheat nitrogen nutrient index estimation and model transferability analysis

The nitrogen nutrition index (NNI) has been extensively applied for the diagnosis of crop nitrogen status, providing insights into efficient nitrogen utilization and plant growth. In this study, we utilized a low-altitude unmanned aerial vehicle (UAV) platform, equipped with multispectral (MS), red–green–blue (RGB), and thermal infrared (TIR) cameras, to comprehensively capture wheat spectral information. The analysis of the relationship between NNI and relative yield revealed an initially linear relationship, which saturated for high NNI values. To enhance accuracy and minimize complexity, we employed a random forest (RF) – recursive feature elimination (RFE) method to select features as inputs for four machine learning (ML) models: back propagation neural network (BPNN), extreme learning machine (ELM), support vector regression (SVR), and Gaussian process regression (GPR). After feature selection, the prediction accuracies of single-sensor models were ranked as: MS > RGB > TIR. The R2 values for the four ML models were in the range of 0.54–0.75. Among multi-sensor combinations, the GPR with MS + RGB + TIR input features achieved the best results with R2 = 0.89 and RPD = 2.52. Further, the dataset was partitioned into six subsets based on location and cultivar variety to evaluate model transferability. The results showed that the transferability largely suffered during the bivariate conditions of different varieties at different locations; the transferability of the model was average improved by 11 % when GPR was combined with transfer component analysis (TCA). The accuracy and transferability of the NNI estimation models significantly improved, offering valuable guidance and methodological support for diagnosing the nitrogen nutrient status of wheat.

Enabling efficient regional seismic fragility assessment of multi‐component bridge portfolios through Gaussian process regression and active learning

AbstractRegional seismic fragility assessment of bridge portfolios must address the embedded uncertainties and variations stemming from both the earthquake hazard and bridge attributes (e.g., geometry, material, design detail). To achieve bridge‐specific fragility assessment, multivariate probabilistic seismic demand models (PSDM) have recently been developed that use both the ground motion intensity measure and bridge parameters as inputs. However, explicitly utilizing bridge parameters as inputs requires numerous nonlinear response history analyses (NRHAs). In this situation, the associated computational cost increases exponentially for high‐fidelity bridge models with complex component connectivity and sophisticated material constitutive laws. Moreover, it remains unclear how many analyses are sufficient for the response data and the resulting demand model to cover the entire solution space without overfitting. To deal with these issues, this study integrates Gaussian process regression (GPR) and active learning (AL) into a multistep workflow to achieve efficient regional seismic fragility assessment of bridge portfolios. The GPR relaxes the probability distribution assumptions made in typical cloud analysis‐based PSDMs to enable heteroskedastic nonparametric seismic demand modeling. The AL leverages the varying standard deviation to select the least but most representative bridge‐model‐ground‐motion sample pairs to conduct NRHA with much‐improved efficiency. Both independent and correlated multi‐output GPRs are proposed to deal with bridge portfolios with seismic demand correlations among multiple components (column, bearing, shear key, abutment, unseating, and joint seal). Considering a single benchmark highway bridge class in California as the case study, the AL‐GPR framework and the associated component‐level fragility results are investigated in terms of their efficiency, accuracy, and robustness. The fragility results show that 70 AL‐selected samples would enable the GPR to derive bridge‐specific fragility models comparable to the ones using the multiple stripes analysis approach with 1950 ground motions considered for each individual bridge. The AL‐GPR model also successfully captures the physics of how bridge span length, deck area, column slenderness, and steel reinforcement ratio would change the damage state exceedance probabilities of different bridge components. The efficiency of AL stems from the fact that, with the multi‐output independent GPR, a stable and reliable fragility model can be achieved using 50 AL‐selected samples compared to at least 270 randomly chosen samples. The proposed methodology advances the state of the art in enabling more efficient and reliable regional seismic fragility assessment of multi‐component bridge portfolios.

Using spectral vegetation indices and machine learning models for predicting the yield of sugar beet (Beta vulgaris L.) under different irrigation treatments

Yield prediction is essential for production planning, resource management, and competitive advantages. The use of vegetation indices and machine learning for yield prediction is rapid, practical, and accurate and contributes to the development of digital agriculture. Although many studies have been carried out on yield estimation, the number of studies on sugar beet and irrigation applications is limited. To solve this problem, in this study yield prediction of sugar beet under different irrigation treatments was carried out using spectral reflection-based vegetation indices obtained by proximal measurements and developed machine learning models. The multilayer perceptron (MLP), random forest (RF), k-nearest (kNN), bagging (BAG), support vector regression (SVR), gaussian processes (GP), and CustomNet (CN) predictors were used in yield prediction. The irrigation treatments included I100 (application of irrigation to increase the available moisture to field capacity by around 45–50% of the water holding capacity at the root depth), I75 (75% of the water applied in the control group), I50 (50% of the water applied in the control group), and I125 (25% of the water applied in the control group). The combinations of vegetation indices were determined using Pearson correlation and principal component analysis. OSAVI, SAVI, and NDVI had the most significant influence on the yield prediction of sugar beet. Among the combinations used, the kNN1 model (including all attributes as input) showed high R2 values of 0.99 for training and 0.64 for testing. In addition, the kNN3 model (including Treatment, NDVI, NWI, and OSAVI as inputs) had R2 values of 0.97 for training and 0.65 for testing, indicating successful outcomes. However, the MLP1 and SVR1 models had lower results with test R2 values of 0.53 and 0.56, respectively. The results demonstrate the successful application of machine learning and vegetation indices for yield prediction. The proposed approaches could encourage agricultural experts and researchers in future work for yield mapping and identification.

A Physics-based Model Assisted by Machine-Learning for Sodium-ion Batteries with both Liquid and Solid Electrolytes

Abstract In the absence of experimental data of a fully developed hierarchical 3D sodium solid state batteries, we developed an improved continuum model by relying on Machine Learning-assisted parameter fitting to uncover the intrinsic material properties that can be transferred into different battery models. The electrochemical system simulated has sodium metal P2-type Na2/3[Ni1/3Fe1/12Mn7/12]O2 (NNFMO) as the cathode, paired with two types of electrolytes have been modeled viz, the organic liquid electrolyte and a solid polymer electrolyte. We implemented a 1D continuum model in COMSOL to suit both liquid and solid electrolytes, then used a Gaussian Process Regressor to fit and evaluate the electrochemical parameters in both battery systems. To enhance the generalizability of our model, the liquid cell and solid cell models share the same OCV input for the cathode materials. The resulting parameters are well aligned with their physical meaning and literature values. The continuum model is then used to understand the effect of increasing the thickness of the cathode and current density by analysing the cathode utilization, and the overpotentials arising from transport and charge transfer. This 1D model and the parameter set are ready to be used in a 3D battery architecture design.

SpAbundance: An R package for single‐species and multi‐species spatially explicit abundance models

Abstract Numerous modelling techniques exist to estimate abundance of plant and animal populations. The most accurate methods account for multiple complexities found in ecological data, such as observational biases, spatial autocorrelation, and species correlations. There is, however, a lack of user‐friendly and computationally efficient software to implement the various models, particularly for large data sets. We developed the spAbundance R package for fitting spatially explicit Bayesian single‐species and multi‐species hierarchical distance sampling models, N‐mixture models, and generalized linear mixed models. The models within the package can account for spatial autocorrelation using Nearest Neighbour Gaussian Processes and accommodate species correlations in multi‐species models using a latent factor approach, which enables model fitting for data sets with large numbers of sites and/or species. We provide three vignettes and three case studies that highlight spAbundance functionality. We used spatially explicit multi‐species distance sampling models to estimate density of 16 bird species in Florida, USA, an N‐mixture model to estimate black‐throated blue warbler (Setophaga caerulescens) abundance in New Hampshire, USA, and a spatial linear mixed model to estimate forest above‐ground biomass across the continental USA. spAbundance provides a user‐friendly, formula‐based interface to fit a variety of univariate and multivariate spatially explicit abundance models. The package serves as a useful tool for ecologists and conservation practitioners to generate improved inference and predictions on the spatial drivers of abundance in populations and communities.

Harnessing the power of ML for robust SISO and MIMO FSO communication systems in fog weather

This study examines Free Space Optical (FSO) communication’s performance in different fog conditions, focusing on Single-Input Single-Output (SISO) and Multiple-Input Multiple-Output (MIMO) setups. In low fog, SISO handles signal degradation well. MIMO improves link robustness in moderate fog. High fog challenges traditional FSO, leading to ML integration to optimize communication parameters. For weather channel classification, a preprocessing scheme reduces features from 12 to 2 given that the 12 features are Bit Error Rate (BER), Quality Factor (Q-factor) and Received Optical Power (ROP) for different 4 users. A Gaussian Process Classifier (GPC) achieves an accuracy greater than 99%, surpassing SVM, Decision Tree, and Random Forest. GPC’s fit and predict functions execute in 0.15 s, outperforming NuSVM (0.2 s). This study highlights FSO, SISO, MIMO, and Machine Learning (ML) practicality in enhancing communication resilience in adverse weather, especially in fog-prone areas.

Parametric Dynamic Simulation and Bayesian Design Optimization of a Front-Loading Washing Machine

Abstract Objective This paper presents the dynamic modeling and design optimization of a fully parametrized front-loading washing machine. Methods A thorough mathematical analysis is performed to capture the effect of nine design variables (including rotation speed, spring stiffness, weight balancer mass density, damping coefficient, spring and damper angles) on vibrational characteristics of the washing machine. The parametric simulation reveals a complex relationship between the vibrational dynamics and design variables, entailing a computationally efficient optimization approach. A Bayesian Optimization (BO) framework is developed, in which a Gaussian process model and Genetic Algorithm (GA) are utilized along with carefully selected acquisition functions to enable adaptive sampling and search for optimal design values. The objective function is to minimize the maximum amplitude of the tub displacement inside the washing machine body. Two case studies are performed to consider a different number of design variables and choices of various infill methods. Results Results show that the fully parametrized front-loading washing machine model is applicable for parametric simulation and design optimization. The proposed BO is able to successfully find a set of design variable values corresponding to the lowest maximum displacement for vibration reduction. A comparison analysis is also carried out to exhibit the difference in optimization convergence and computational cost caused by the choice of acquisition functions. Conclusion It is shown that the fully parametrized washing machine model yields a lower maximum displacement than the model with fewer design variables. Of the two acquisition functions studied for optimization, the Expected Improvement function converges more rapidly than the Lower Bound criterion.

Refining the rheological characteristics of high drug loading ointment via SDS and machine learning.

This paper presents an optimized preparation process for external ointment using the Definitive Screening Design (DSD) method. The ointment is a Traditional Chinese Medicine (TCM) formula developed by Professor WYH, a renowned TCM practitioner in Jiangsu Province, China, known for its proven clinical efficacy. In this study, a stepwise regression model was employed to analyze the relationship between key process factors (such as mixing speed and time) and rheological parameters. Machine learning techniques, including Monte Carlo simulation, decision tree analysis, and Gaussian process, were used for parameter optimization. Through rigorous experimentation and verification, we have successfully identified the optimal preparation process for WYH ointment. The optimized parameters included drug ratio of 24.5%, mixing time of 8 min, mixing speed of 1175 rpm, petroleum dosage of 79 g, liquid paraffin dosage of 6.7 g. The final ointment formulation was prepared using method B. This research not only contributes to the optimization of the WYH ointment preparation process but also provides valuable insights and practical guidance for designing the preparation processes of other TCM ointments. This advanced DSD method enhances the screening approach for identifying the best preparation process, thereby improving the scientific rigor and quality of TCM ointment preparation processes.

Smoothing in linear multicompartment biological processes subject to stochastic input

Many physical and biological systems rely on the progression of material through multiple independent stages. In viral replication, for example, virions enter a cell to undergo a complex process comprising several disparate stages before the eventual accumulation and release of replicated virions. While such systems may have some control over the internal dynamics that make up this progression, a challenge for many is to regulate behavior under what are often highly variable external environments acting as system inputs. In this work, we study a simple analog of this problem through a linear multicompartment model subject to a stochastic input in the form of a mean-reverting Ornstein-Uhlenbeck process, a type of Gaussian process. By expressing the system as a multidimensional Gaussian process, we derive several closed-form analytical results relating to the covariances and autocorrelations of the system, quantifying the smoothing effect discrete compartments afford multicompartment systems. Semianalytical results demonstrate that feedback and feedforward loops can enhance system robustness, and simulation results probe the intractable problem of the first passage time distribution, which has specific relevance to eventual cell lysis in the viral replication cycle. Finally, we demonstrate that the smoothing seen in the process is a consequence of the discreteness of the system, and does not manifest in systems with continuous transport. While we make progress through analysis of a simple linear problem, many of our insights are applicable more generally, and our work enables future analysis into multicompartment processes subject to stochastic inputs. Published by the American Physical Society 2024

Data-driven real-time fuel cetane estimation and control design for multifuel UAVs

Multifuel compression ignition (CI) engines have been proven to be useful for the aviation industry, especially for powering unmanned aerial vehicles (UAVs). To operate multifuel UAVs at desired operating conditions, an appropriate control strategy is needed that can adapt based on changing fuel properties. Therefore, having knowledge of fuel properties at all times is critical. However, the challenge comes in identifying fuel property in real-time when fuel switching happens during engine operation. The current work proposes a novel data-driven control algorithm for estimating fuel property (cetane number) and adapting the control strategy in real-time. Gaussian process regression (GPR) is used for modeling the multifuel CI engine, and feedforward control is developed to correct the control inputs based on the estimated fuel cetane property. For feedforward control development, model inversion of data-driven GPR is performed. Based on the estimated fuel property and using the feedforward table, the control strategy gets adjusted in real-time within one combustion cycle to avoid the system performance from drifting away beyond specified bounds. The entire approach was implemented and validated on an engine test bed. Fuel switching is performed in real time, and the results demonstrated the capability of the algorithm to maintain the desired performance.

Multiresolution kernel matrix algebra

AbstractWe propose a sparse algebra for samplet compressed kernel matrices to enable efficient scattered data analysis. We show that the compression of kernel matrices by means of samplets produces optimally sparse matrices in a certain S-format. The compression can be performed in cost and memory that scale essentially linearly with the number of data points for kernels of finite differentiability. The same holds true for the addition and multiplication of S-formatted matrices. We prove that the inverse of a kernel matrix, given that it exists, is compressible in the S-format as well. The use of selected inversion allows to directly compute the entries in the corresponding sparsity pattern. Moreover, S-formatted matrix operations enable the efficient, approximate computation of more complicated matrix functions such as $${\varvec{A}}^\alpha $$ A α or $$\exp ({\varvec{A}})$$ exp ( A ) of a matrix $${\varvec{A}}$$ A . The matrix algebra is justified mathematically by pseudo differential calculus. As an application, we consider Gaussian process learning algorithms for implicit surfaces. Numerical results are presented to illustrate and quantify our findings.

A probabilistic fatigue life assessment method for wind turbine blade based on Bayesian GPR with the effects of pitch angle

AbstractThe fatigue behavior of large wind turbine blades is complex and stochastic due to their complex structure and operating environment. This paper focuses on developing a probabilistic fatigue life assessment method for wind turbine blades considering the uncertainties from wind velocity, material mechanical properties, pitch angle, and layer thickness. To improve the efficiency of stochastic fatigue behavior analysis of wind turbine blade, unidirectional fluid‐structure coupling (UFSC) and bidirectional fluid‐structure coupling (BFSC) analysis are employed to analyze the stochastic response. Then, Gaussian process regression (GPR) and Bayesian updating are combined to establish the stochastic fatigue behavior prediction model for wind turbine blade. On this basis, a modified S‐N curve formulation is proposed, and the fatigue life of wind turbine blade is analyzed by the modified S‐N curve and compared with the three‐parameter Weibull model. The results indicate that the proposed method for fatigue life assessment has better accuracy. The proposed probabilistic fatigue life assessment method with high accuracy and high efficiency, which is beneficial for the fatigue reliability design of wind turbine blades.

Physical Prior Mean Function-Driven Gaussian Processes Search for Minimum-Energy Reaction Paths with a Climbing-Image Nudged Elastic Band: A General Method for Gas-Phase, Interfacial, and Bulk-Phase Reactions.

The climbing-image nudged elastic band (CI-NEB) method serves as an indispensable tool for computational chemists, offering insight into minimum-energy reaction paths (MEPs) by delineating both transition states (TSs) and intermediate nonstationary structures along reaction coordinates. However, executing CI-NEB calculations for reactions with extensive reaction coordinate spans necessitates a large number of images to ensure a reliable convergence of the MEPs and TS structures, presenting a computationally demanding optimization challenge, even with mildly costly electronic-structure methods. In this study, we advocate for the utilization of physically inspired prior mean function-based Gaussian processes (GPs) to expedite MEP exploration and TS optimization via the CI-NEB method. By incorporating reliable prior physical approximations into potential energy surface (PES) modeling, we demonstrate enhanced efficiency in multidimensional CI-NEB optimization with surrogate-based optimizers. Our physically informed GP approach not only outperforms traditional nonsurrogate-based optimizers in optimization efficiency but also on-the-fly learns the reaction path valley during optimization, culminating in significant advancements. The surrogate PES derived from our optimization exhibits high accuracy compared to true PES references, aligning with our emphasis on leveraging reliable physical priors for robust and efficient posterior mean learning in GPs. Through a systematic benchmark study encompassing various reaction pathways, including gas-phase, bulk-phase, and interfacial/surface reactions, our physical GPs consistently demonstrate superior efficiency and reliability. For instance, they outperform the popular fast inertial relaxation engine optimizer by approximately a factor of 10, showcasing their versatility and efficacy in exploring reaction mechanisms and surface reaction PESs.

Uncertainty quantification in multivariable regression for material property prediction with Bayesian neural networks

With the increased use of data-driven approaches and machine learning-based methods in material science, the importance of reliable uncertainty quantification (UQ) of the predicted variables for informed decision-making cannot be overstated. UQ in material property prediction poses unique challenges, including multi-scale and multi-physics nature of materials, intricate interactions between numerous factors, limited availability of large curated datasets, etc. In this work, we introduce a physics-informed Bayesian Neural Networks (BNNs) approach for UQ, which integrates knowledge from governing laws in materials to guide the models toward physically consistent predictions. To evaluate the approach, we present case studies for predicting the creep rupture life of steel alloys. Experimental validation with three datasets of creep tests demonstrates that this method produces point predictions and uncertainty estimations that are competitive or exceed the performance of conventional UQ methods such as Gaussian Process Regression. Additionally, we evaluate the suitability of employing UQ in an active learning scenario and report competitive performance. The most promising framework for creep life prediction is BNNs based on Markov Chain Monte Carlo approximation of the posterior distribution of network parameters, as it provided more reliable results in comparison to BNNs based on variational inference approximation or related NNs with probabilistic outputs.

A physical simulation-machine learning model for optimal process schemes in laser-based directed energy deposition process

The major challenge faced is the definition of optimal process variables for rich quality of fabricated parts in laser-based directed energy deposition (DED-LB) processes. However, predicting the optimal process scheme using machine learning models is still challenging owing to the need for a large amount of training experimental data with high costs in DED-LB. In view of this, a physical simulation (PS)-machine learning (ML) model using a relatively small accurate data set of 31 simulation data for optimal process schemes is proposed in DED-LB process in this study. Firstly, a powder-scale high precision phenomenon model incorporating the mass transfer, phase transformations and heat transfer and using Lagrangian particle model to add mass is developed to depict the DED-LB process. Then, a Gaussian process regression (GPR) agent model is established to rapidly and accurately predict the geometry and dilution rate of deposition tracks under different manufacturing parameters based on the high precision simulation results. Finally, a PS-ML model for process parameter optimization is developed using the particle swarm algorithm (PSO), and the optimized parameters are experimentally validated. The results show that the developed powder-scale model and GPR model results are consistent with the Inconel 718 alloy experimental results. The proposed PS-ML model can increase the accuracy of the ML models even with a small simulation data set. None of PS-ML model optimization results has a relative error of more than 3% to the experimental results, and the dilution rate is reduced by up to 61.66% compared to the experimental design parameters without optimization. The proposed physical simulation-machine learning model in this study enables inexpensive and accurate optimization of DED-LB process parameters.

Machine-Learning-Based Kinetic-Free Hybrid Gray-Box Model to Predict Sulfuric-Acid-Catalyzed Esterification Reaction.

The sulfuric-acid-catalyzed esterification reaction of 2-butanol and propionic anhydride is a vital industrial process. In this paper, several experiments are conducted via reaction calorimetry to validate that both sulfuric and propionic acids have discernible catalytic effects on the reaction. This finding complicates the accurate description of the reaction kinetics through traditional methods. So this paper turns to a kinetic-free black-box model, Gaussian process regression (GPR) model via 24 experiments, as a more adaptable approach. Besides, the best GPR model is combined with traditional heat balance model to generate a hybrid gray-box model, which can give complete knowledge of reaction process. The hybrid gray-box model finally achieves maximum root-mean-square error (RMSE) of 0.0069 for conversion, 0.6535 for temperature, and 10.6087 for heat flow rate, underscoring its pretty good predictive ability.

Model predictive control of blood glucose in critically ill patients using Gaussian processes

Abstract Stress-induced hyperglycemia and high glycemic variability are common in intensive care patients. Several clinical studies show the benefits of tight blood glucose control, including lower mortality. This article presents an algorithm for blood glucose control in the intensive care unit. An Unscented Kalman Filter is developed to estimate the glucose metabolism state and time-varying insulin sensitivity from blood glucose measurements. Gaussian Processes are used to predict future insulin sensitivity changes based on previous measurements. A model predictive controller is designed to estimate optimal insulin infusion based on current state, predicted insulin sensitivity and planned nutrition. The developed control algorithm allows individualized blood glucose control with reduced glycemic variability and reduced risk of hypoglycemia in the intensive care unit.

Multiple measurements on the cosmic curvature using Gaussian process regression without calibration and a cosmological model

In this letter, we propose a novel cosmological model-independent method to determine cosmic curvature, combining the recent measurements of transverse and line-of-sight directions in the baryon acoustic oscillations (BAO) with cosmic chronometers (CC) datasets. Considering that the CC dataset is discrete and includes only 32 H(z) measurements, we apply Gaussian process (GP) regression to fit the CC dataset and reconstruct them. Our methodology, which does not need the calibration or selection of any cosmological model, provide multiple measurements of spatial curvature (ΩK) at different redshifts (depending on the redshift coverage of BAO dataset). For combination of all BAO data, we find that the constraint result on cosmic curvature is ΩK=−0.096−0.195+0.190 with 1σ observational uncertainty. Although the measured ΩK is in good agreement with zero cosmic curvature within 1σ confidence level, our result revels the fact of a closed universe. More importantly, our results show that the obtained ΩK measurements are almost unaffected by different priors of the Hubble constant. This could help solve the issue of the Hubble tension that may be caused by inconsistencies in the spatial curvature between the early and late universes.

Complexity of many-body interactions in transition metals via machine-learned force fields from the TM23 data set

This work examines challenges associated with the accuracy of machine-learned force fields (MLFFs) for bulk solid and liquid phases of d-block elements. In exhaustive detail, we contrast the performance of force, energy, and stress predictions across the transition metals for two leading MLFF models: a kernel-based atomic cluster expansion method implemented using sparse Gaussian processes (FLARE), and an equivariant message-passing neural network (NequIP). Early transition metals present higher relative errors and are more difficult to learn relative to late platinum- and coinage-group elements, and this trend persists across model architectures. Trends in complexity of interatomic interactions for different metals are revealed via comparison of the performance of representations with different many-body order and angular resolution. Using arguments based on perturbation theory on the occupied and unoccupied d states near the Fermi level, we determine that the large, sharp d density of states both above and below the Fermi level in early transition metals leads to a more complex, harder-to-learn potential energy surface for these metals. Increasing the fictitious electronic temperature (smearing) modifies the angular sensitivity of forces and makes the early transition metal forces easier to learn. This work illustrates challenges in capturing intricate properties of metallic bonding with current leading MLFFs and provides a reference data set for transition metals, aimed at benchmarking the accuracy and improving the development of emerging machine-learned approximations.

Reverse engineering morphogenesis through Bayesian optimization of physics-based models

Morphogenetic programs coordinate cell signaling and mechanical interactions to shape organs. In systems and synthetic biology, a key challenge is determining optimal cellular interactions for predicting organ shape, size, and function. Physics-based models defining the subcellular force distribution facilitate this, but it is challenging to calibrate parameters in these models from data. To solve this inverse problem, we created a Bayesian optimization framework to determine the optimal cellular force distribution such that the predicted organ shapes match the experimentally observed organ shapes. This integrative framework employs Gaussian Process Regression, a non-parametric kernel-based probabilistic machine learning modeling paradigm, to learn the mapping functions relating to the morphogenetic programs that maintain the final organ shape. We calibrated and tested the method on Drosophila wing imaginal discs to study mechanisms that regulate epithelial processes ranging from development to cancer. The parameter estimation framework successfully infers the underlying changes in core parameters needed to match simulation data with imaging data of wing discs perturbed with collagenase. The computational pipeline identifies distinct parameter sets mimicking wild-type shapes. It enables a global sensitivity analysis to support the regulation of actomyosin contractility and basal ECM stiffness to generate and maintain the curved shape of the wing imaginal disc. The optimization framework, combined with experimental imaging, identified that Piezo, a mechanosensitive ion channel, impacts fold formation by regulating the apical-basal balance of actomyosin contractility and elasticity of ECM. This workflow is extensible toward reverse-engineering morphogenesis across organ systems and for real-time control of complex multicellular systems.