Adaptive Sampling Algorithm Research Articles

Prediction of surface roughness using deep learning and data augmentation

PurposeSurface roughness has a serious impact on the fatigue strength, wear resistance and life of mechanical products. Realizing the evolution of surface quality through theoretical modeling takes a lot of effort. To predict the surface roughness of milling processing, this paper aims to construct a neural network based on deep learning and data augmentation.Design/methodology/approachThis study proposes a method consisting of three steps. Firstly, the machine tool multisource data acquisition platform is established, which combines sensor monitoring with machine tool communication to collect processing signals. Secondly, the feature parameters are extracted to reduce the interference and improve the model generalization ability. Thirdly, for different expectations, the parameters of the deep belief network (DBN) model are optimized by the tent-SSA algorithm to achieve more accurate roughness classification and regression prediction.FindingsThe adaptive synthetic sampling (ADASYN) algorithm can improve the classification prediction accuracy of DBN from 80.67% to 94.23%. After the DBN parameters were optimized by Tent-SSA, the roughness prediction accuracy was significantly improved. For the classification model, the prediction accuracy is improved by 5.77% based on ADASYN optimization. For regression models, different objective functions can be set according to production requirements, such as root-mean-square error (RMSE) or MaxAE, and the error is reduced by more than 40% compared to the original model.Originality/valueA roughness prediction model based on multiple monitoring signals is proposed, which reduces the dependence on the acquisition of environmental variables and enhances the model's applicability. Furthermore, with the ADASYN algorithm, the Tent-SSA intelligent optimization algorithm is introduced to optimize the hyperparameters of the DBN model and improve the optimization performance.

An adaptive sampling algorithm for reduced‐order models using Isomap

AbstractThe use of reduced‐order models (ROMs) in physics‐based modeling and simulation is a popular tool for drastically lowering the computational cost associated with high‐fidelity simulations. ROMs use training data from a set of computed high‐fidelity simulations with different design parameters that control physical and geometric properties of the full‐order model. The quality of the training data dictates the performance of the ROM, making the choice of training design parameters important. A widely used method for generating training parameters for ROMs is Latin hypercube sampling (LHS), a statistical method that aims to maximize the distance and minimize the correlation amongst produced samples. However, LHS fails to account for the physics of the full‐order model and can lead to an over‐representation of some physical regimes in the training data while neglecting others. In this work, we present a computationally efficient adaptive sampling method for ROMs using Isomap, a versatile algorithm for nonlinear dimensionality reduction. Using an initial number of samples, the adaptive sampling algorithm iteratively generates samples based on a low‐dimensional manifold of the training data. When applied to two external aerodynamics problems, the proposed adaptive sampling algorithm offers significantly improved performance in predicting physical fields and coefficients of lift and drag for a given computational budget for both non‐intrusive and projection‐based ROMs.

A framework to improve churn prediction performance in retail banking

Managing customer retention is critical to a company’s profitability and firm value. However, predicting customer churn is challenging. The extant research on the topic mainly focuses on the type of model developed to predict churn, devoting little or no effort to data preparation methods. These methods directly impact the identification of patterns, increasing the model’s predictive performance. We addressed this problem by (1) employing feature engineering methods to generate a set of potential predictor features suitable for the banking industry and (2) preprocessing the majority and minority classes to improve the learning of the classification model pattern. The framework encompasses state-of-the-art data preprocessing methods: (1) feature engineering with recency, frequency, and monetary value concepts to address the imbalanced dataset issue, (2) oversampling using the adaptive synthetic sampling algorithm, and (3) undersampling using NEASMISS algorithm. After data preprocessing, we use XGBoost and elastic net methods for churn prediction. We validated the proposed framework with a dataset of more than 3 million customers and about 170 million transactions. The framework outperformed alternative methods reported in the literature in terms of precision-recall area under curve, accuracy, recall, and specificity. From a practical perspective, the framework provides managers with valuable information to predict customer churn and develop strategies for customer retention in the banking industry.

A low-sample-count, high-precision Pareto front adaptive sampling algorithm based on multi-criteria and Voronoi

A low-sample-count, high-precision Pareto front adaptive sampling algorithm based on multi-criteria and Voronoi

Estimation of grain filling rate of winter wheat using leaf chlorophyll and LAI extracted from UAV images

The grain filling rate (GFR) plays a pivotal role in assessing winter wheat grain development and guiding crop variety selection and cultivation strategies. Presently, GFR monitoring primarily relies on destructive sampling methods, which are impractical for swift assessments in extensive agricultural fields. Our study introduces a novel approach for estimating winter wheat grain filling rate (GFR) using leaf chlorophyll content (LCC) and Leaf Area Index (LAI) extracted from UAV imagery. Initially, we established a quantitative relationship between GFR and LAI as well as LCC in winter wheat. Subsequently, UAV multispectral imagery was employed to track the time-series dynamics of LAI and LCC during the grain-filling stage. Ultimately, we constructed an estimation model for winter wheat GFR and achieved plot-scale GFR mapping through UAV-based imaging technology. To identify sensitive vegetation index combinations for LAI and chlorophyll content (SPAD), we employed adaptive re-weighted sampling and continuous projection algorithms, respectively. Following this, we employed partial least squares and random forest algorithms to develop LAI and SPAD estimation models, which were then compared to full-band regression. Finally, GFR estimation was based on the conversion models of LAI and SPAD to GFR. Our findings revealed that, despite variations in water supply, there were no significant differences in GFR trends among the irrigated treatments. However, in the nitrogenous fertilizer application treatments, GFR initially declined with increased nitrogenous fertilizer supply, reaching its peak between 21 and 25 days post-flowering, during which period the differences in GFR among the various nitrogenous fertilizer application treatments were not significant. As the reproductive period advanced, higher nitrogenous fertilizer treatments maintained a higher GFR for a more extended period and experienced a slower decline compared to the lower nitrogenous fertilizer treatments. LAI validation yielded an R2 of 0.84, a root mean square error (RMSE) of 0.39, and a normalized root mean square error (NRMSE) of 10.9%. SPAD validation resulted in R2, RMSE, and NRMSE values of 0.79%, 1.30%, and 12.5%, respectively. The GFR estimation achieved an R2 of 0.77, an RMSE of 0.32 mg/d, and an NRMSE of 11.3%. Mapping the GFR distribution in the field, coupled with water and fertilizer management, supports UAVs in monitoring crop growth and refining field-level water and fertilizer decisions.

Adaptive Sampling Methods for Molecular Dynamics in the Era of Machine Learning.

Molecular dynamics (MD) simulations are fundamental computational tools for the study of proteins and their free energy landscapes. However, sampling protein conformational changes through MD simulations is challenging due to the relatively long time scales of these processes. Many enhanced sampling approaches have emerged to tackle this problem, including biased sampling and path-sampling methods. In this Perspective, we focus on adaptive sampling algorithms. These techniques differ from other approaches because the thermodynamic ensemble is preserved and the sampling is enhanced solely by restarting MD trajectories at particularly chosen seeds rather than introducing biasing forces. We begin our treatment with an overview of theoretically transparent methods, where we discuss principles and guidelines for adaptive sampling. Then, we present a brief summary of select methods that have been applied to realistic systems in the past. Finally, we discuss recent advances in adaptive sampling methodology powered by deep learning techniques, as well as their shortcomings.

An Adaptive Meta-Modelling Approach for Multi-Dimensional Correlated Flow Field Responses

ABSTRACT It has become common practice to build inexpensive surrogate models to supplant time-consuming numerical simulations. By gradually increasing the number of training samples, the efficiency of model construction can be significantly improved. This study proposes an adaptive meta-modelling approach for multi-dimensional correlated responses within the framework of proper orthogonal decomposition (POD) and the Kriging model. The algorithm begins with the adaptive sampling algorithm for each reduced-dimension response, which integrates the prediction variance, distances between samples, and sensitivity indicator of each parameter. The adaptive sampling criterion for each reduced-dimension response is weighted by the energy of the modal, forming the adaptive sampling algorithm for multi-dimensional correlated responses. Tests on an analytical function and M6 wing simulation show that, under the same number of training samples, the proposed adaptive algorithm results in a model with lower prediction error than the random sampling algorithm, offering a more efficient model for flow field prediction.

Glare analysis of an integral daylighting and lighting control strategy for offices

Complex Fenestration Systems (CFSs) can significantly impact both the visual and non-visual daylight effects on the occupants as well as the energy performance of buildings. To ensure that those impacts improve the overall situation, proper control algorithms are required if the CFS can be operated. The state of the CFS directly and immediately effects the indoor lighting situation. The thermal condition of the building is usually strongly but not directly influenced by the condition of the façade system due to thermal capacities.In this study an experimental integral control strategy, called Integrated Lighting Module (ILM) is investigated in terms of it’s glare prevention capabilities and compared to a cut-off- and a simple rule based control logic. The ILM is an autonomous software package capable to run on building management hardware to control façade systems and artificial lighting in real buildings in an energetically optimised way. The adaptive sampling algorithm raytraverse is employed to calculate Daylight Glare Probability (DGP) values, which are used as a benchmark for the control strategy comparison. The other aspect of this comparison is the opening of the façade, which is evaluated as statistics how often each possible façade state is selected by each control strategy.

Hyperspectral Prediction Model of Nitrogen Content in Citrus Leaves Based on the CEEMDAN–SR Algorithm

Nitrogen content is one of the essential elements in citrus leaves (CL), and many studies have been conducted to determine the nutrient content in CL using hyperspectral technology. To address the key problem that the conventional spectral data-denoising algorithms directly discard high-frequency signals, resulting in missing effective signals, this study proposes a denoising preprocessing algorithm, complete ensemble empirical mode decomposition with adaptive noise joint sparse representation (CEEMDAN–SR), for CL hyperspectral data. For this purpose, 225 sets of fresh CL were collected at the Institute of Fruit Tree Research of the Guangdong Academy of Agricultural Sciences, to measure their elemental nitrogen content and the corresponding hyperspectral data. First, the spectral data were preprocessed using CEEMDAN–SR, Stein’s unbiased risk estimate and the linear expansion of thresholds (SURE–LET), sparse representation (SR), Savitzky–Golay (SG), and the first derivative (FD). Second, feature extraction was carried out using principal component analysis (PCA), uninformative variables elimination (UVE), and the competitive adaptive re-weighted sampling (CARS) algorithm. Finally, partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and Gaussian process regression (GPR) were used to construct a CL nitrogen prediction model. The results showed that most of the prediction models preprocessed using the CEEMDAN–SR algorithm had better accuracy and robustness. The prediction models based on CEEMDAN–SR preprocessing, PCA feature extraction, and GPR modeling had an R2 of 0.944, NRMSE of 0.057, and RPD of 4.219. The study showed that the CEEMDAN–SR algorithm can be effectively used to denoise CL hyperspectral data and reduce the loss of effective information. The prediction model using the CEEMDAN–SR+PCA+GPR algorithm could accurately obtain the nitrogen content of CL and provide a reference for the accurate fertilization of citrus trees.

Adaptive Sampling and Quick Anomaly Detection in Large Networks

The monitoring of data streams with a network structure have drawn increasing attention due to its wide applications in modern process control. In these applications, high-dimensional sensor nodes are interconnected with an underlying network topology. In such a case, abnormalities occurring to any node may propagate dynamically across the network and cause changes of other nodes over time. Furthermore, high dimensionality of such data significantly increased the cost of resources for data transmission and computation, such that only partial observations can be transmitted or processed in practice. Overall, how to quickly detect abnormalities in such large networks with resource constraints remains a challenge, especially due to the sampling uncertainty under the dynamic anomaly occurrences and network-based patterns. In this paper, we incorporate network structure information into the monitoring and adaptive sampling methodologies for quick anomaly detection in large networks where only partial observations are available. We develop a general monitoring and adaptive sampling method and further extend it to the case with memory constraints, both of which exploit network distance and centrality information for better process monitoring and identification of abnormalities. Theoretical investigations of the proposed methods demonstrate their sampling efficiency on balancing between exploration and exploitation, as well as the detection performance guarantee. Numerical simulations and a case study on power network have demonstrated the superiority of the proposed methods in detecting various types of shifts. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Continuous monitoring of networks for anomalous events is critical for a large number of applications involving power networks, computer networks, epidemiological surveillance, social networks, etc. This paper aims at addressing the challenges in monitoring large networks in cases where monitoring resources are limited such that only a subset of nodes in the network is observable. Specifically, we integrate network structure information of nodes for constructing sequential detection methods via effective data augmentation, and for designing adaptive sampling algorithms to observe suspicious nodes that are likely to be abnormal. Then, the method is further generalized to the case that the memory of the computation is also constrained due to the network size. The developed method is greatly beneficial and effective for various anomaly patterns, especially when the initial anomaly randomly occurs to nodes in the network. The proposed methods are demonstrated to be capable of quickly detecting changes in the network and dynamically changes the sampling priority based on online observations in various cases, as shown in the theoretical investigation, simulations and case studies.

Multi-objective optimization of additive manufactured functionally graded lattice structures under impact

A multi-objective optimization procedure to effectively design gradient lattice structures under dynamic loading is presented. It aims both at maximized energy absorption characteristics and a lightweight design. The reduction of the peak crushing force and a maximized specific energy absorption are simultaneously optimized. Design variables like the relative density and density gradient of the lattice structure are investigated, considering different topologies of the lattice unit cells. To model and simulate the lattice structures efficiently, a simplified beam-based simulation finite element model is introduced and validated against experimental tests. They cover the range from dynamic equilibrium up to compaction wave propagation as impact deformation phenomena. Based on large numbers of simulations, an artificial neural network is used to predict the energy absorbing characteristics for the given design parameters and to find the optimal configuration of the lattice structures. The neural network is trained using a multi response adaptive sampling algorithm allowing parallel simulation with automatically generated finite element models during each iteration step. Subsequently, a multi-objective genetic algorithm is used to find optimal combinations of the design parameters of lattice structures under different impact velocities and cell topologies.

Rapid Estimation of Soil Pb Concentration Based on Spectral Feature Screening and Multi-Strategy Spectral Fusion.

Traditional methods for obtaining soil heavy metal content are expensive, inefficient, and limited in monitoring range. In order to meet the needs of soil environmental quality evaluation and health status assessment, visible near-infrared spectroscopy and XRF spectroscopy for monitoring heavy metal content in soil have attracted much attention, because of their rapid, nondestructive, economical, and environmentally friendly features. The use of either of these spectra alone cannot meet the accuracy requirements of traditional measurements, while the synergistic use of the two spectra can further improve the accuracy of monitoring heavy metal lead content in soil. Therefore, this study applied various spectral transformations and preprocessing to vis-NIR and XRF spectra; used the whale optimization algorithm (WOA) and competitive adaptive re-weighted sampling (CARS) algorithms to identify feature spectra; designed a combination variable model (CVM) based on multi-layer spectral data fusion, which improved the spectral preprocessing and spectral feature screening process to increase the efficiency of spectral fusion; and established a quantitative model for soil Pb concentration using partial least squares regression (PLSR). The estimation performance of three spectral fusion strategies, CVM, outer-product analysis (OPA), and Granger-Ramanathan averaging (GRA), was discussed. The results showed that the accuracy and efficiency of the CARS algorithm in the fused spectra estimation model were superior to those of the WOA algorithm, with an average coefficient of determination (R2) value of 0.9226 and an average root mean square error (RMSE) of 0.1984. The accuracy of the estimation models established, based on the different spectral types, to predict the Pb content of the soil was ranked as follows: the CVM model > the XRF spectral model > the vis-NIR spectral model. Within the CVM fusion strategy, the estimation model based on CARS and PLSR (CARS_D1+D2) performed the best, with R2 and RMSE values of 0.9546 and 0.2035, respectively. Among the three spectral fusion strategies, CVM had the highest accuracy, OPA had the smallest errors, and GRA showed a more balanced performance. This study provides technical means for on-site rapid estimation of Pb content based on multi-source spectral fusion and lays the foundation for subsequent research on dynamic, real-time, and large-scale quantitative monitoring of soil heavy metal pollution using high-spectral remote sensing images.

Power Saving Approach of a Smart Watch for Monitoring the Heart Rate of a Runner

Heart Rate (HR) monitoring in a smart watch is a battery consuming process. Therefore, some smart watches prevent continuous HR sampling during low-level physical activities for improving the power usage of batteries. However, high acceleration events like running require continuous HR sampling for recording the varying HR readings, which consumes a lot of battery power. Therefore, the challenge is to reduce the sampling during running while recording an individual’s HR variation (HRV). Our approach prevents continuous HR sampling for long-running events without missing important HR information. In this context, we analyze the existing real-life HRs and acceleration datasets recorded on humans during long runs. We design an adaptive HR sampling algorithm, A-HeaRing, from the extracted HR variation details. A-HeaRing reduces the battery power consumption of a smart watch by more than 50% while recording a running event. Additionally, we design a data regeneration system for missing HR readings. The regeneration system provides a minimum of 90% accuracy in the HR zone estimation.

Multibiosensor Data Sampling and Transmission Reduction With Decision-Making for Remote Patient Monitoring in IoMT Networks

The rise in chronic diseases and the aging of the population led to an increase in the demand for remote healthcare systems that employ biosensors to monitor people’s health status. The increasing need for these automated systems has led to the emergence of the Internet of Medical Things (IoMT) networks. In the IoMT networks, the biosensor devices collect vital signs and transmit them to the gateway for further analysis and fusion. In light of the limited biosensor device resources (power, storage, and computation) and the periodical transmission of a large amount of data, it is necessary to optimize the transmission of data in order to conserve power while maintaining data quality at the gateway. Also, it became important to have a decision-making-based machine learning model at the gateway to evaluate a patient’s health and make a quick, accurate decision in case of an emergency. This paper proposes Multibiosensor Data Sampling and Transmission Reduction with Decision-making (MuDaSaTReD) for Remote Patient Monitoring in the IoMTs Networks. The MuDaSaTReD achieves this goal on two levels: biosensors and a fog gateway. It uses an Energy-saving Lightweight Data Transmission (ELiDaT) algorithm to get rid of the repeated data and then adapts the sampling rate of each biosensor using an Adaptive Data Sampling (ADaS) algorithm. The MuDaFuDeC implements the machine learning model at the fog gateway to learn and decide the situation of the patient according to the received data from the biosensors. The performance evaluation shows that the MuDaFuDeC outperforms other approaches in terms of the data reduction percentage and energy consumption. It keeps a good representation of all the scores at the fog gateway and makes automated, fast, and accurate decisions based on the patient’s condition.

3-D Adaptive AUV Sampling for Classification of Water Masses

Autonomous underwater vehicles with onboard computing units foster innovative approaches for sampling oceanographic phenomena. Feedback of observations via the onboard model for planning algorithms enable adaptive sampling for such robotic units. In this work, we develop, implement, and test an adaptive sampling algorithm for efficient sampling of water masses in a 3-D frontal system. Focusing on a river plume, salinity variations are used to characterize the water masses. A threshold in salinity is assumed to distinguish the ocean and river waters, so that excursions below the threshold define river waters. The onboard model builds on a Gaussian random field representation of the salinity variations in (north, east, depth) coordinates. This model is initially trained from numerical ocean model data, and then updated with data gathered by the vehicle sensor. The Gaussian random field model further allows closed-form expressions of the expected spatially integrated Bernoulli variance of the salinity excursion set, which is used to reward sampling efforts. Combining these results with forward-looking planning algorithms, we suggest a workflow for 3-D adaptive sampling to map river plume systems. Simulation studies are used to compare the suggested approach with others. Results of field trials in the Nidelva river plume in Norway are presented and discussed.

An Adaptive Frequency Sampling Algorithm for Dynamic Condensation-Based Frequency Response Analysis

This paper proposed an efficient and adaptive frequency sampling algorithm for frequency response analysis using dynamic condensation-based reduced-order modeling. For the degree of freedom-based model reduction method, the reduced-order basis becomes a frequency-dependent matrix since the relationship between master and slave degrees of freedom stems from partial equations of a second-order dynamical system. Such frequency-dependency makes the analysis inefficient for investigating the frequency response of the system. Considering that the coverage of a local reduced-order basis at a single frequency varies depending on the frequency, a new frequency sampling algorithm was proposed with a strategy of constructing multiple local reduced-order models (ROMs) at sample frequencies. For adaptive sampling, the frequency range of a local ROM was evaluated, and a new sample was added if there was a gap between two adjacent ROMs. As a result, the accuracy of the local ROM can be estimated, and the efficiency in the online stage was greatly enhanced. The proposed method was verified by performing frequency response analysis with several numerical examples, including a large-scale structural and dynamic system.

Forecasting Pathogen Dynamics with Bayesian Model-Averaging: Application to Xylella fastidiosa.

Forecasting invasive-pathogen dynamics is paramount to anticipate eradication and containment strategies. Such predictions can be obtained using a model grounded on partial differential equations (PDE; often exploited to model invasions) and fitted to surveillance data. This framework allows the construction of phenomenological but concise models relying on mechanistic hypotheses and real observations. However, it may lead to models with overly rigid behavior and possible data-model mismatches. Hence, to avoid drawing a forecast grounded on a single PDE-based model that would be prone to errors, we propose to apply Bayesian model averaging (BMA), which allows us to account for both parameter and model uncertainties. Thus, we propose a set of different competing PDE-based models for representing the pathogen dynamics, we use an adaptive multiple importance sampling algorithm (AMIS) to estimate parameters of each competing model from surveillance data in a mechanistic-statistical framework, we evaluate the posterior probabilities of models by comparing different approaches proposed in the literature, and we apply BMA to draw posterior distributions of parameters and a posterior forecast of the pathogen dynamics. This approach is applied to predict the extent of Xylella fastidiosa in South Corsica, France, a phytopathogenic bacterium detected in situ in Europe less than 10 years ago (Italy 2013, France 2015). Separating data into training and validation sets, we show that the BMA forecast outperforms competing forecast approaches.

GLaSDI: Parametric physics-informed greedy latent space dynamics identification

A parametric adaptive physics-informed greedy Latent Space Dynamics Identification (gLaSDI) method is proposed for accurate, efficient, and robust data-driven reduced-order modeling of high-dimensional nonlinear dynamical systems. In the proposed gLaSDI framework, an autoencoder discovers intrinsic nonlinear latent representations of high-dimensional data, while dynamics identification (DI) models capture local latent-space dynamics. An interactive training algorithm is adopted for the autoencoder and local DI models, which enables identification of simple latent-space dynamics and enhances accuracy and efficiency of data-driven reduced-order modeling. To maximize and accelerate the exploration of the parameter space for the optimal model performance, an adaptive greedy sampling algorithm integrated with a physics-informed residual-based error indicator and random-subset evaluation is introduced to search for the optimal training samples on the fly. Further, to exploit local latent-space dynamics captured by the local DI models for an improved modeling accuracy with a minimum number of local DI models in the parameter space, a k-nearest neighbor convex interpolation scheme is employed. The effectiveness of the proposed framework is demonstrated by modeling various nonlinear dynamical problems, including Burgers equations, nonlinear heat conduction, and radial advection. The proposed adaptive greedy sampling outperforms the conventional predefined uniform sampling in terms of accuracy. Compared with the high-fidelity models, gLaSDI achieves 17 to 2,658× speed-up with 1 to 5% relative errors.

The GeMS/GSAOI Galactic Globular Cluster Survey (G4CS). II. Characterization of 47 Tuc with Bayesian Statistics

We present a photometric analysis of globular cluster 47 Tuc (NGC 104) using near-IR imaging data from the GeMS/GSAOI Galactic Globular Cluster Survey (G4CS), which is in operation at Gemini-South telescope. Our survey is designed to obtain AO-assisted deep imaging with near diffraction-limited spatial resolution of the central fields of Milky Way globular clusters. The G4CS near-IR photometry was combined with an optical photometry catalog that was obtained from Hubble Space Telescope survey data to produce a high-quality color–magnitude diagram that reaches down to K s ≈ 21 Vega mag. We used the software suite BASE-9, which uses an adaptive Metropolis sampling algorithm to perform a Markov chain Monte Carlo Bayesian analysis, and obtained probability distributions and precise estimates for the age, distance, and extinction cluster parameters. Our best estimate for the age of 47 Tuc is ± 0.08 Gyr and our true distance modulus estimate is (m−M)0 = 13.250 ± 0.028 mag, which are in tight agreement with previous studies using Gaia DR2 parallax and detached eclipsing binaries.

Toward implementing autonomous adaptive data acquisition for scanning hyperspectral imaging of biological systems

Autonomous experimentation is an emerging area of research, primarily related to autonomous vehicles, scientific combinatorial discovery approaches in materials science and drug discovery, and iterative research loops of planning, experimentation, and analysis. However, autonomous approaches developed in these contexts are difficult to apply to high-dimensional mapping technologies, such as scanning hyperspectral imaging of biological systems, due to sample complexity and heterogeneity. We briefly cover the history of adaptive sampling algorithms and surrogate modeling in order to define autonomous adaptive data acquisition as an objective-based, flexible building block for future biological imaging experimentation driven by intelligent infrastructure. We subsequently summarize the recent implementations of autonomous adaptive data acquisition (AADA) for scanning hyperspectral imaging, assess how these address the difficulties of autonomous approaches in hyperspectral imaging, and highlight the AADA design variation from a goal-oriented perspective. Finally, we present a modular AADA architecture that embeds AADA-driven flexible building blocks to address the challenge of time resolution for high-dimensional scanning hyperspectral imaging of nonequilibrium dynamical systems. In our example research-driven experimental design case, we propose an AADA infrastructure for time-resolved, noninvasive, and label-free scanning hyperspectral imaging of living biological systems. This AADA infrastructure can accurately target the correct state of the system for experimental workflows that utilize subsequent expensive, high-information-content analytical techniques.