Estimation Performance Research Articles

An investigation of PPP-B2b coverage and its performance in ZTD estimation and positioning in different regions

This study comprehensively evaluates the Beidou navigation satellite system's PPP-B2b service for real-time positioning and zenith total delay (ZTD) estimation. Despite its operational status, PPP-b2b's effective coverage is underexplored. We define this coverage by analysing satellite visibility and geometry and evaluating ZTD and positioning accuracy at 48 stations. Results show PPP-B2b achieves ZTD Errors of 10–20 mm in China and 15–30 mm in Europe, with kinematic experiments in China and Japan showing consistent accuracy within 20 mm. This study highlights PPP-b2b's potential for enhancing atmospheric monitoring and precise positioning in its effective regions.

SDE-HNN: Accurate and Well-calibrated Forecasting using Stochastic Differential Equations

It is crucial yet challenging for deep learning models to properly characterize uncertainty that is pervasive in real-world environments. Heteroscedastic neural networks (HNNs) are promising methods that capture data uncertainty for forecasting problems, while existing HNNs have difficulties in conjoining calibrated uncertainty estimation and satisfactory predictive performance due to the failure to construct an explicit interaction between the prediction and its associated uncertainty. This paper develops SDE-HNN, an improved HNN equipped with stochastic differential equations (SDE), to characterize the interaction between the predictive mean and variance inside HNNs for accurate and reliable forecasting. The existence and uniqueness of the solution to the devised neural SDE are guaranteed. Moreover, based on the bias-variance trade-off for the optimization in SDE-HNN, we design an enhanced numerical SDE solver to improve learning stability. Finally, we present two new diagnostic uncertainty metrics to systematically evaluate the predictive uncertainty. Experiments on various challenging datasets show that our method significantly outperforms state-of-the-art baselines on both predictive performance and uncertainty quantification, delivering well-calibrated and sharp prediction intervals in time-series forecasting.

Enhancing integration of administrative databases in South Africa's HIV program: Validation of record linkage using non-representative gold standard

IntroductionLinked administrative data are widely used in epidemiology to capture patient data across multiple databases. Linkage error rates, critical to measure linkage performance, are rarely reported due to difficulty in obtaining representative gold standard. We propose a training and validation approach for linkage procedures that yield unbiased performance estimates even with a non-representative gold standard. MethodsWe linked patient records from two non-deduplicated databases for HIV monitoring in South Africa, TIER.Net and NHLS laboratory database, using a network-based probabilistic linkage and deduplication approach. National IDs (gold standard) were available for a non-representative minority of records (10%). We calculated sensitivity (Sen, share of true matches identified by the algorithm) and positive predictive value (PPV, share of algorithm-identified matches that were true matches). We adjusted for bias due to informative missingness in National IDs using inverse probability weights to break the link between missingness and match probability. Results111,755 record pairs were considered. National IDs were not missing completely at random. Match probabilities for National ID record pairs exhibited substantially less uncertainty (mid-range match probabilities), inflating Sen and PPV. Before bias correction, Sen and PPV were estimated at 97.0% and 97.8% respectively. After bias correction for missing National IDs, Sen and PPV were estimated at 95.7% and 96.6%. Failure to address this bias understated the overlinkage rate (100% - PPV) by 35% and the underlinkage rate (100% - Sen) by 30%. ConclusionFailure to adjust for informative missingness in the gold standard may lead to biased validation metrics and over/underconfidence in linked data.

Performance and economic viability assessment of a novel CO2 adsorbent for manufacturing and integration with coal power plants

This study assesses the performance and economic feasibility of a novel CO2 adsorbent for post-combustion capture in DOE/NETL’s 650 MWnet SubC PC power plant (case B11B). Bench-scale tests showed an initial adsorption capacity of 16.3 wt%, which decreased to 12.1 wt% after 41 adsorption–desorption cycles due to induced particle aggregation by over-humidification. With a conservative adsorption capacity of 8.8 wt% and 695 adsorption–desorption cycles, an adsorbent replenishment rate of 10 tonnes/h is necessary to capture 90% of CO2. The breakeven sale price of the adsorbent produced at this rate is $1,293/tonne, which is 40 to 80 times lower than prices for K2CO3 adsorbents reported in the literature (e.g., K2CO3/TiO2, K2CO3/ZrO2) while providing better capture performances. Sensitivity analysis reveals that increasing the plant production rate from 10 to 40 tonnes/h reduces the sale price by 8%. The study also compares the CO2 capture cost to Cansolv, an integrated solvent-based technology. The novel adsorbent requires 2.4 GJ/tonne of CO2 for regeneration, lower than Cansolv’s 2.7 GJ/tonne. With conservative performance estimates, the capture cost is $54/tonne of CO2, slightly higher than Cansolv’s $45/tonne. To achieve lower or comparable capture costs to Cansolv, the adsorbent should meet one of the following conditions at a commercial scale: minimum 950 cycles, 16 wt% capture capacity, 50% of the adsorbent recovery, or a reduced cost to $646/tonne by upscaling the manufactury to 75 tonnes/h.

Harmonic voltage phasor reconstruction and harmonic state estimation based on the measurement data of a capacitive voltage transformer

AbstractHarmonic state estimation, which highly depends on accurate synchronised phasors, is a crucial basis for the location, traceability, and governance of harmonics in power systems. However, most existing synchronous phasor measurement units (PMUs) provide power frequency phasors rather than harmonic phasors. In addition, as the dominant voltage signal provider for PMUs in power systems, capacitive voltage transformers (CVTs) have complex frequency responses and cannot be directly used for harmonic measurement. Therefore, accurate harmonic state estimation is difficult to achieve in applications. A method for harmonic voltage phasor reconstruction and harmonic state estimation based on the measurement data of a CVT is proposed. First, the reasons for harmonic voltage measurement errors were analysed. Second, the scattering parameter method was used to measure the wideband voltage transfer characteristics of CVT. Third, a voltage reconstruction method was proposed to improve the measurement accuracy and expand the frequency range of synchronous phasor measurement. Fourth, this method was applied to harmonic state estimation, and the performance of harmonic state estimation before and after voltage reconstruction was quantitatively compared. Results showed that the proposed method can remarkably improve the accuracy of harmonic state estimation. Finally, some factors, such as state observability, complex error disturbances, CVT structure, and harmonic order, influencing the performance of the proposed method were investigated. Results further demonstrated that the method has high accuracy, strong anti‐interference, and adaptability, and can provide basic information for harmonic localisation and traceability.

Hyperspectral Estimation of Chlorophyll Content in Wheat under CO2 Stress Based on Fractional Order Differentiation and Continuous Wavelet Transforms

The leaf chlorophyll content (LCC) of winter wheat, an important food crop widely grown worldwide, is a key indicator for assessing its growth and health status in response to CO2 stress. However, the remote sensing quantitative estimation of winter wheat LCC under CO2 stress conditions also faces challenges such as an unclear spectral sensitivity range, baseline drift, overlapping spectral peaks, and complex spectral response due to CO2 stress changes. To address these challenges, this study introduced the fractional order derivative (FOD) and continuous wavelet transform (CWT) techniques into the estimation of winter wheat LCC. Combined with the raw hyperspectral data, we deeply analyzed the spectral response characteristics of winter wheat LCC under CO2 stress. We proposed a stacking model including multiple linear regression (MLR), decision tree regression (DTR), random forest (RF), and adaptive boosting (AdaBoost) to filter the optimal combination from a large number of feature variables. We use a dual-band combination and vegetation index strategy to achieve the accurate estimation of LCC in winter wheat under CO2 stress. The results showed that (1) the FOD and CWT methods significantly improved the correlation between the raw spectral reflectance and LCC of winter wheat under CO2 stress. (2) The 1.2-order derivative dual-band index (RVI (R720, R522)) constructed by combining the sensitive spectral bands of the CO2 response of winter wheat leaves achieved a high-precision estimation of the LCC under CO2 stress conditions (R2 = 0.901). Meanwhile, the red-edged vegetation stress index (RVSI) constructed based on the CWT technique at specific scales also demonstrated good performance in LCC estimation (R2 = 0.880), verifying the effectiveness of the multi-scale analysis in revealing the mechanism of the CO2 impact on winter wheat. (3) By stacking the sensitive spectral features extracted by combining the FOD and CWT methods, we further improved the LCC estimation accuracy (R2 = 0.906). This study not only provides a scientific basis and technical support for the accurate estimation of LCC in winter wheat under CO2 stress but also provides new ideas and methods for coping with climate change, optimizing crop-growing conditions, and improving crop yield and quality in agricultural management. The proposed method is also of great reference value for estimating physiological parameters of other crops under similar environmental stresses.

On Dagum-Pareto mixture distribution: properties, simulation and application in insurance

The most principal subject in actuarial science is the modeling of claims amount. There are two types of distributions associated with two types of risk. We speak of light-tailed distributions as opposed to heavy-tailed distributions or extreme value distribution. Among the distributions of the amount of heavy tail claim is: Weibull, Log-Normal, Pareto and Burr “Also named DAGUM”. Many attempts were implemented in expanding the classes of mixed and compound distributions. In this article, we present a new distribution by mixing Dagum distribution (α, λ, r) and Pareto distribution (α, λ) named Dagum-Pareto mixture distribution. Some of statistical properties of this new distribution are obtained which include reliability function, hazard function, skewness, kurtosis and quantile function. Also we use the maximum likelihood method to estimate the model parameters. A Simulation study was carried out to examine the performance and accuracy of the maximum likelihood estimates of the proposed distribution. An application of the new model to no-life insurance real data set is presented to illustrate its usefulness and applicability. In our case, it is proven that Dagum-Pareto mixture distribution provides better fit compared to others existing probability distributions using some goodness of fit measures.

Robust Liu Estimator Used to Combat Some Challenges in Partially Linear Regression Model by Improving LTS Algorithm Using Semidefinite Programming

Outliers are a common problem in applied statistics, together with multicollinearity. In this paper, robust Liu estimators are introduced into a partially linear model to combat the presence of multicollinearity and outlier challenges when the error terms are not independent and some linear constraints are assumed to hold in the parameter space. The Liu estimator is used to address the multicollinearity, while robust methods are used to handle the outlier problem. In the literature on the Liu methodology, obtaining the best value for the biased parameter plays an important role in model prediction and is still an unsolved problem. In this regard, some robust estimators of the biased parameter are proposed based on the least trimmed squares (LTS) technique and its extensions using a semidefinite programming approach. Based on a set of observations with a sample size of n, and the integer trimming parameter h ≤ n, the LTS estimator computes the hyperplane that minimizes the sum of the lowest h squared residuals. Even though the LTS estimator is statistically more effective than the widely used least median squares (LMS) estimate, it is less complicated computationally than LMS. It is shown that the proposed robust extended Liu estimators perform better than classical estimators. As part of our proposal, using Monte Carlo simulation schemes and a real data example, the performance of robust Liu estimators is compared with that of classical ones in restricted partially linear models.

Performance evaluation of microbial fuel cells for bioelectricity generation: influence of potential scan-rate and real-time external load

AbstractThe electrochemical performance of microbial fuel cells is conventionally assessed through linear sweep voltammetry at predefined potential scan rates. Nevertheless, this approach frequently falls short in representing the long-term behavior of microbial fuel cells under actual external loads, highlighting the need for a standardized evaluation method incorporating both linear sweep voltammetry and external loads. To address this gap, this study evaluates the performance of single-chamber microbial fuel cells under different loads and scan rates. The MFCs were tested with external loads of 1200, 470, and 270 Ω, derived from maximum power points of polarization sweeps at scan rates of 0.1, 0.5, and 1 mV/s at two operational phases. Power estimates at these scan rates were 61.96, 87.88, and 166.68 mW/m2 at current densities of 116.5, 229.6, and 403 mA/m2, respectively. In the initial two hours, average power densities with 1200, 470, and 270 Ω were 73 ± 16.7, 36.3 ± 42, and 88.5 ± 120.1 mW/m2, respectively. Over the long term, the fuel cells under constant loading with resistance estimated at 0.1 mV/s showed average power 73.7% and 89.1% higher than those with resistances estimated at 0.5 mV/s and 1 mV/s, respectively, indicating that higher scan rates lead to overestimation of power. Although initially underestimated, the 0.1 mV/s scan rate more accurately reflected the true long-term performance of the fuel cells. This study emphasizes the importance of using appropriate scan rates for linear sweep voltammetry to obtain realistic long-term performance estimates of microbial fuel cells under real-time loads.

Allometry and biomass dynamics in temperate mixed and monospecific stands: Contrasting response of Scots pine (Pinus sylvestris L.) and sessile oak (Quercus petraea (Matt.) Liebl.)

Mixed forests generally outperform monospecific forests in terms of productivity, stability, and resilience and are becoming increasingly important for sustainable forest management. However, accurate estimates of tree biomass allocation, as well as aboveground and component biomass in mixed forests, remain scarce. Our study addressed three different objectives to identify differences in biomass between mixed and monocultures and develop biomass models: (1) identification of biomass growth patterns in mixed and monoculture stands using analysis of covariance (ANCOVA), (2) investigation of the best fitting approach to modeling aboveground biomass using logarithmic regression and nonlinear mixed-effects models, and (3) fitting compartment biomass proportion models by Dirichlet regression, considering the additivity property. We analyzed 52 harvested trees from six plots within an experimental triplet in northern Spain, consisting of mixed and single-species stands of Scots pine (Pinus sylvestris L.) and sessile oak (Quercus petraea (Matt.) Liebl.). Moreover, diameter at breast height and tree height were used as covariate variables to determine the most accurate and unbiased models. The research findings showed that (i) allometric patterns of individual-tree biomass in mixed stands significantly differed from those in monospecific stands for sessile oak, while those in Scots pine did not change; (ii) nonlinear mixed-effect models demonstrated a better fit – indicated by lower Furnival index values – than logarithmic regression models in predicting aboveground biomass; and (iii) the fitted biomass equations provided good performance and accurate estimates of biomass component proportions compared to those of existing models. Consequently, our results offer a better understanding of biomass and carbon storage within mixed and monoculture forests in the context of climate change.

Dynamic BIM Adoption Impact on Contract Cost Variance Factors Using PLS-SEM Techniques

This paper investigates the Building Information Modeling (BIM) adoption impact on the factors of Contract Cost Variance (CCV) over time. The study considers qualitative and quantitative data to identify the most common causes of CCV through pre-tendering. A partial least square-structure model (PLS-SEM) procedure was used to develop a causal model and rank CCV factors based on their effect, partially based on prior survey raw data conducted in 2022 and the data from 94 projects. Construction industry experts assessed the prior five-year rate of BIM adoption on construction projects to infer the expected trend in BIM adoption in the future (until 2037). Based on the causal model of CCV factors and the future rates of BIM adoption, the dynamic impact of BIM on CCV factors over time was modeled and analyzed. The analysis shows that BIM reduces CCV over time by improving Estimator Performance (EP), Information Quality (IQ), and contractual procedure (CP). The results showed that the CP, EP, and EF have directly impacted CCV, and the PC and IQ indirectly affect the CCV. This paper considers the temporal aspect, examining how the impact of BIM on CCV factors evolves. This dynamic analysis is crucial for long-term strategic planning in construction management.

Iterative UKF under generalized maximum correntropy criterion for intermittent observation systems with complex non-Gaussian noise

The traditional unscented Kalman filters (UKFs) under the maximum correntropy criterion provide a powerful tool for nonlinear state estimation with heavy-tailed non-Gaussian noise. Nevertheless, the above-mentioned filters may yield biased estimates because the Gaussian kernel function can only handle certain types of non-Gaussian noise. Additionally, the use of statistical linearization methods can result in approximation errors when solving linear observation equations, while the system may also experience observation data loss. Therefore, a new iterative UKF with intermittent observations under the generalized maximum correntropy criterion is proposed for systems with complex non-Gaussian noise, called GMCC-IO-IUKF. Firstly, the connection between the UKF with and without intermittent observations is established by designing a coefficient matrix including intermittent observation variables, so as to derive the UKF with intermittent observations under the maximum correntropy criterion. Secondly, for the measurement update of GMCC-IO-IUKF, a nonlinear regression augmented model that can deal with both prediction and observation errors is established using the coefficient matrix and the nonlinear function. To better adapt to different types of non-Gaussian noise, the generalized Gaussian kernel function is substituted for the traditional Gaussian kernel function. Theoretically, GMCC-IO-IUKF can achieve better estimation performance by directly employing the nonlinear function and the latest iteration value. Finally, a classical target tracking model is used to evaluate the estimation performance and feasibility of our proposed GMCC-IO-IUKF algorithm. It appears from the experiment results that our proposed GMCC-IO-IUKF can not only promote estimation precision but also handle complex non-Gaussian noise flexibly.

On the characterization of reflective surfaces using dual-polarization GNSS-R

Global navigation satellite systems reflectometry (GNSS-R) is a technique to extract information from reflecting surfaces by the reflected GNSS signals. GNSS-R has garnered increasing attention in the scientific literature due to its continuous global coverage and its superior spatial resolution. Moreover, operating in the L-band renders GNSS-R relatively immune to adverse weather conditions and affords high sensitivity to soil electrical properties. This work introduces a new approach with a dual-polarization antenna, left-hand circular polarized (LHCP) and right-hand circular polarized (RHCP), receiving the reflected signal from a sufficiently smooth surface so that all reflected energy arrives from the specular reflection point. The objective is to characterize the reflecting surface by extracting the relative permittivity and conductivity from the reflected signal. In contrast to other studies found in the literature, the reflection of the GNSS signal on different materials, including dielectric and conductive materials is considered. We derive a maximum likelihood estimator (MLE) for estimating the dielectric parameters of the reflective surface and other parameters of the reflected signal. We also derive the respective Cramer–Rao Lower Bound (CRLB) evaluating the performance of the MLE. The attained results are assessed based on the signal-to-noise ratio (SNR) and the angle of reflection of the reflected signal, which are the parameters that predominantly influence the proposed approach. Lower elevation angles, for instance, lead to higher estimation accuracy, while for reflective surfaces composed of metallic materials a higher SNR is needed to yield favorable estimation performance. Regarding dielectric materials, the estimation results are encouraging and thus enable diverse remote sensing applications by GNSS-R using the proposed setup.

Design and performance estimation of a novel solar multiplate mirror concentration PVT system based on nanofluid spectral filter

This paper presents the design and performance evaluation of a novel solar multiplate mirror concentration photovoltaic and thermal (MPVT) system using ethylene glycol/indium tin oxide liquid spectral filter (LSF). The LSF is prepared, and the test results show that its average spectral transmissivity and average spectral absorptivity are 69.2 % and 30.8 %. Optical characteristics and operation performance of the MPVT system are evaluated, and parametric interaction analysis is also carried out to reveal the relationships of optical and structural parameters of the MPVT system. The results indicate that the MPVT system is technically feasible and has acceptable adaptability on solar tracking error. The decrease in LSF flow channel width and increase in LSF flow channel installation height can increase the concentration ratio. The electric power and photoelectric efficiency of the photovoltaic module are 818.2 W and 29.07 %. The thermal and exergy efficiencies of the MPVT system are 23.88 % and 32.81 %. By increasing the inlet LSF flow velocity and ambient temperature or decreasing the inlet LSF temperature properly, the thermal performance of the MPVT system can be improved. But the effects of the three parameters on the exergy efficiency of the MPVT system are all relatively small.

Nested case–control sampling without replacement

Nested case–control design (NCC) is a cost-effective outcome-dependent design in epidemiology that collects all cases and a fixed number of controls at the time of case diagnosis from a large cohort. Due to inefficiency relative to full cohort studies, previous research developed various estimation methodologies but changing designs in the formulation of risk sets was considered only in view of potential bias in the partial likelihood estimation. In this paper, we study a modified design that excludes previously selected controls from risk sets in view of efficiency improvement as well as bias. To this end, we extend the inverse probability weighting method of Samuelsen which was shown to outperform the partial likelihood estimator in the standard setting. We develop its asymptotic theory and a variance estimation of both regression coefficients and the cumulative baseline hazard function that takes account of the complex feature of the modified sampling design. In addition to good finite sample performance of variance estimation, simulation studies show that the modified design with the proposed estimator is more efficient than the standard design. Examples are provided using data from NIH-AARP Diet and Health Cohort Study.

Unit-Power Half-Normal Distribution Including Quantile Regression with Applications to Medical Data

In this paper, we present the unit-power half-normal distribution, derived from the power half-normal distribution, for data analysis in the open unit interval. The statistical properties of the unit-power half-normal model are described in detail. Simulation studies are carried out to evaluate the performance of the parameter estimators. Additionally, we implement the quantile regression for this model, which is applied to two real healthcare data sets. Our findings suggest that the unit power half-normal distribution provides a robust and flexible alternative for existing models for proportion data.

A Novel Transformer-CNN Approach for Predicting Soil Properties from LUCAS Vis-NIR Spectral Data

Soil, a non-renewable resource, requires continuous monitoring to prevent degradation and support sustainable agriculture. Visible-near-infrared (Vis-NIR) spectroscopy is a rapid and cost-effective method for predicting soil properties. While traditional machine learning methods are commonly used for modeling Vis-NIR spectral data, large datasets may benefit more from advanced deep learning techniques. In this study, based on the large soil spectral library LUCAS, we aimed to enhance regression model performance in soil property estimation by combining Transformer and convolutional neural network (CNN) techniques to predict 11 soil properties (clay, silt, pH in CaCl2, pH in H2O, CEC, OC, CaCO3, N, P, and K). The Transformer-CNN model accurately predicted most soil properties, outperforming other methods (partial least squares regression (PLSR), random forest regression (RFR), support vector machine regression (SVR), Long Short-Term Memory (LSTM), ResNet18) with a 10–24 percentage point improvement in the coefficient of determination (R2). The Transformer-CNN model excelled in predicting pH in CaCl2, pH in H2O, OC, CaCO3, and N (R2 = 0.94–0.96, RPD > 3) and performed well for clay, sand, CEC, P, and K (R2 = 0.77–0.85, 2 < RPD < 3). This study demonstrates the potential of Transformer-CNN in enhancing soil property prediction, although future work should aim to optimize computational efficiency and explore a wider range of applications to ensure its utility in different agricultural settings.

The mean scatterer spacing estimation with the Gabor atoms selected based on the Nakagami distribution

Abstract Mean scatterer spacing (MSS) is a quantitative signature for disease diagnosis and tissue characterization. However, it is difficult to objectively extract the coherent components from the ultrasound RF echo signals to improve the accuracy performance of the MSS estimation. In the present study, a novel MSS estimation method with the matched Gabor atoms selected based on Nakagami parameters is proposed. Firstly, the ultrasound signals are decomposed into a series of Gabor atoms, and the envelopes of the residual signals are fitted with the Nakagami distribution. Then, the second order difference (SOD) of the shape parameters in Nakagami distribution is calculated to select the optimal atoms to match the coherent components. Finally, the locations of the selected Gabor atoms are used to estimate the MSS. In order to evaluate the performance of the proposed method, the simulated RF echo signals are modelled based on four regular degrees of the scatterer distributions, and then the optimally matched atoms are selected to estimate MSSs. The results based on simulated signals demonstrate that the propose method can provide accurate MSS estimation, which are advantageous for improving quantitative diagnosis of diseases and tissue characterization

98 Treatment Planning System Performance for Epidermal Dose Estimation in the Context of Planning Dose Constraints to Avoid Moist Desquamation

98 Treatment Planning System Performance for Epidermal Dose Estimation in the Context of Planning Dose Constraints to Avoid Moist Desquamation

Investigating the use of signal detection information in supervised learning-based image denoising with consideration of task-shift.

Recently, learning-based denoising methods that incorporate task-relevant information into the training procedure have been developed to enhance the utility of the denoised images. However, this line of research is relatively new and underdeveloped, and some fundamental issues remain unexplored. Our purpose is to yield insights into general issues related to these task-informed methods. This includes understanding the impact of denoising on objective measures of image quality (IQ) when the specified task at inference time is different from that employed for model training, a phenomenon we refer to as "task-shift." A virtual imaging test bed comprising a stylized computational model of a chest X-ray computed tomography imaging system was employed to enable a controlled and tractable study design. A canonical, fully supervised, convolutional neural network-based denoising method was purposely adopted to understand the underlying issues that may be relevant to a variety of applications and more advanced denoising or image reconstruction methods. Signal detection and signal detection-localization tasks under signal-known-statistically with background-known-statistically conditions were considered, and several distinct types of numerical observers were employed to compute estimates of the task performance. Studies were designed to reveal how a task-informed transfer-learning approach can influence the tradeoff between conventional and task-based measures of image quality within the context of the considered tasks. In addition, the impact of task-shift on these image quality measures was assessed. The results indicated that certain tradeoffs can be achieved such that the resulting AUC value was significantly improved and the degradation of physical IQ measures was statistically insignificant. It was also observed that introducing task-shift degrades the task performance as expected. The degradation was significant when a relatively simple task was considered for network training and observer performance on a more complex one was assessed at inference time. The presented results indicate that the task-informed training method can improve the observer performance while providing control over the tradeoff between traditional and task-based measures of image quality. The behavior of a task-informed model fine-tuning procedure was demonstrated, and the impact of task-shift on task-based image quality measures was investigated.