We introduce ∂PV, an end-to-end differentiable photovoltaic (PV) cell simulator based on the drift-diffusion model and Beer–Lambert law for optical absorption. ∂PV is programmed in Python using JAX, ...an automatic differentiation (AD) library for scientific computing. Using AD coupled with the implicit function theorem, ∂PV computes the power conversion efficiency (PCE) of an input PV design as well as the derivative of the PCE with respect to any input parameters, all within comparable time of solving the forward problem. We show an example of perovskite solar-cell optimization and multi-parameter discovery, and compare results with random search and finite differences. The simulator can be integrated with optimization algorithms and neural networks, opening up possibilities for data-efficient optimization and parameter discovery.
Program Title:∂PV
CPC Library link to program files:https://doi.org/10.17632/7w7r8mtx3d.1
Developer's repository link:https://github.com/romanodev/deltapv.git
Code Ocean capsule:https://codeocean.com/capsule/0851990
Licensing provisions: MIT
Programming language: Python
Nature of problem: Photovoltaic cell optimization has been traditionally difficult due to the lack of gradients from numerical drift-diffusion solvers. This results in the need to treat the problem as a case of black-box optimization, which incurs high computational costs and low data efficiency.
Solution method: An end-to-end differentiable photovoltaic simulator via the drift-diffusion model was developed using JAX, a growing scientific computation and automatic-differentiation library. To enhance computational speed, the implicit function theorem was used to bypass the need for directly differentiating through iterative solvers.
The article presents a new concept drift detection method based on analyzing the importance of features of instances in the data stream. The data stream contains information about distribution ...patterns that reflect different concepts that may be hidden in the data stream. The presented drift detector concept uses information about the fluctuation of the most informative feature inside chunks of the data stream and compares it with the change of the same feature in neighbor chunks. In the case of data streams, the meaning of features can change over time. These changes affect the quality of the classification but can also be a significant indicator of ongoing concept drift. After detecting the drift, the classifier should be trained with the new dataset. But this issue is not addressed in this article.
In this work, we propose a new concept drift detector in the data stream for the first time. This goal is achieved by observing the changing importance of features in different parts of the data stream. The proposed approach uses the feature significance measure as a drift detector. The obtained results indicate that the method can be introduced in practice. Because these are only preliminary results, in this paper, we focused on presenting the advantages of our strategy without comparison with other methods.
In this study, we utilize ICON observations from 2019 to 2022 to analyze the variability of vertical plasma drift and its relationship with the neutral winds. The results reveal that there are 19% of ...downward plasma drifts at 13–17 LT, which changes with seasons and longitudes. The downward plasma drift occurs less frequently compared to the contemporaneous counter electrojet during solstices. We identify the relationship between vertical plasma drifts and north foot magnetic zonal and meridional wind profiles at 90–300 km altitudes. As the vertical plasma drifts become small or downward, the zonal winds display diverse variations at the altitudes; that is, the disturbances are eastward at 95–120 km altitudes, westward at 120–160 km altitudes, and eastward above 180 km altitudes, while the meridional winds present weak changes in all altitudes. Additionally, we discuss the possible roles of the E‐ and F‐region dynamos on the vertical plasma drifts.
Plain Language Summary
The neutral wind in the Earth's upper atmosphere drives the ionospheric ions to cross the geomagnetic field lines and produces the dynamo effects in the E‐ and F‐regions. The electric field is created due to the divergence free of the total electrical current. The zonal electric field drives the ionospheric plasma to drift upward and downward due to the horizontal field lines, and influences the structures of low latitude ionosphere. One open question is that the vertical plasma drift shows the significant day‐to‐day variability and sometimes remarkably deviates from the climatological pattern during the quiet times. The ICON satellite provides the simultaneous observations of the plasma drifts and neutral winds in low latitudes, which provides us a good chance to investigate the day‐to‐day variability of the vertical plasma drift and its relationship to the neutral wind, as we discuss in the manuscript.
Key Points
The equatorial vertical plasma drifts show large variability and 19% downward plasma drift at 13–17 LT
The occurrence of the downward plasma drift presents a significant longitudinal and seasonal variations
The E‐ and F‐region zonal winds play vital roles on the large variability and the occurrence of the downward plasma drift
Load forecasting is a crucial topic in energy management systems (EMS) due to its vital role in optimizing energy scheduling and enabling more flexible and intelligent power grid systems. As a ...result, these systems allow power utility companies to respond promptly to demands in the electricity market. Deep learning (DL) models have been commonly employed in load forecasting problems supported by adaptation mechanisms to cope with the changing pattern of consumption by customers, known as concept drift. A drift magnitude threshold should be defined to design change detection methods to identify drifts. While the drift magnitude in load forecasting problems can vary significantly over time, existing literature often assumes a fixed drift magnitude threshold, which should be dynamically adjusted rather than fixed during system evolution. To address this gap, in this paper, we propose a dynamic drift-adaptive Long Short-Term Memory (DA-LSTM) framework that can improve the performance of load forecasting models without requiring a drift threshold setting. We integrate several strategies into the framework based on active and passive adaptation approaches. To evaluate DA-LSTM in real-life settings, we thoroughly analyze the proposed framework and deploy it in a real-world problem through a cloud-based environment. Efficiency is evaluated in terms of the prediction performance of each approach and computational cost. The experiments show performance improvements on multiple evaluation metrics achieved by our framework compared to baseline methods from the literature. Finally, we present a trade-off analysis between prediction performance and computational costs.
•Presenting a drift-adaptive LSTM (DA-LSTM) framework for interval load forecasting•Proposing a dynamic drift adaptation methodology without fixing a drift threshold.•Integrating different drift adaptation approaches in the framework.•Conducting an extensive evaluation of the approach in terms of performance and cost.•Performing analysis of the trade-off between performance and cost.
Previous studies have revealed large anomalies in vertical ExB drift during the sudden stratospheric warming (SSW), and little attention focused on the behaviors of field‐aligned plasma drift. We ...report the first simultaneous observations of the equatorial ionospheric vertical ExB and field‐aligned plasma drifts and neutral winds during the 2020–2021 SSW, using the Ionospheric Connections Explorer (ICON) satellite measurements. The downward ExB drift is observed in the afternoon equatorial topside ionosphere in longitudes of ∼180°–270°E, in good agreement with the Jicamarca incoherent scatter radar measurements. What is more, the ICON records the afternoon northward disturbance in field‐aligned plasma drift, which is mainly due to the disturbance meridional wind. The enhanced semidiurnal tides maybe contribute to the disturbances in equatorial topside plasma drifts and neutral winds. This study indicates that the field‐aligned motion is an important factor in the ionosphere‐thermosphere responses to SSW.
Plain Language Summary
Previous studies have revealed that the sudden stratospheric warming causes large anomalies in the low‐latitude ionosphere via the vertical ExB plasma drift driven by the E region wind dynamo. However, ionospheric electron density distributions are not only influenced by the vertical ExB drifts, but also by the plasma drifts along geomagnetic field lines driven by the F region neutral wind and plasma pressure gradient and gravity. In the past studies, little attention focused on the behaviors of the F region field‐aligned plasma drifts during the sudden stratospheric warming (SSW). Ionospheric Connections Explorer (ICON) provides the first simultaneous observations of the E and F region neutral winds and topside ionospheric vertical ExB and field‐aligned plasma drift. The results show that the enhanced semidiurnal tides can cause the significant disturbances in both the F region vertical ExB and field‐aligned plasma drift and neutral winds during the 2020–2021 SSW. The observed neutral wind and plasma drift will likely impact Earth's ionospheric plasma environment and imply a substantial impact of the lower atmosphere on ionospheric space weather.
Key Points
The Ionospheric Connections Explorer satellite observes the afternoon downward plasma drift during sudden stratospheric warming (SSW)
Disturbance in the F region neutral wind and their contribution to the field‐aligned plasma drift during SSW are observed for the first time
The enhanced semidiurnal tides may contribute to the F region ExB and field‐aligned plasma drifts
Frequency drift correction is an important postprocessing step in MRS that yields improvements in spectral quality and metabolite quantification. Although routinely applied in single-voxel MRS, drift ...correction is much more challenging in MRSI due to the presence of phase-encoding gradients. Thus, separately acquired navigator scans are normally required for drift estimation. In this work, we demonstrate the use of self-navigating rosette MRSI trajectories combined with time-domain spectral registration to enable retrospective frequency drift corrections without the need for separately acquired navigator echoes.
A rosette MRSI sequence was implemented to acquire data from the brains of 5 healthy volunteers. FIDs from the center of k-space (
FIDs) were isolated from each shot of the rosette acquisition, and time-domain spectral registration was used to estimate the frequency offset of each
FID relative to a reference scan (the first
FID in the series). The estimated frequency offsets were then used to apply corrections throughout
-space. Improvements in spectral quality were assessed before and after drift correction.
Spectral registration resulted in significant improvements in signal-to-noise ratio (12.9%) and spectral linewidths (18.5%). Metabolite quantification was performed using LCModel, and the average Cramer-Rao lower bounds uncertainty estimates were reduced by 5.0% for all metabolites, following field drift correction.
This study demonstrated the use of self-navigating rosette MRSI trajectories to retrospectively correct frequency drift errors in in vivo MRSI data. This correction yields meaningful improvements in spectral quality.
As machine learning models are increasingly deployed in production, robust monitoring and detection of concept and covariate drift become critical. This paper addresses the gap in the widespread ...adoption of drift detection techniques by proposing a serverless-based approach for batch covariate drift detection in ML systems. Leveraging the open-source OSCAR framework and the open-source Frouros drift detection library, we develop a set of services that enable parallel execution of two key components: the ML inference pipeline and the batch covariate drift detection pipeline. To this end, our proposal takes advantage of the elasticity and efficiency of serverless computing for ML pipelines, including scalability, cost-effectiveness, and seamless integration with existing infrastructure. We evaluate this approach through an edge ML use case, showcasing its operation on a simulated batch covariate drift scenario. Our research highlights the importance of integrating drift detection as a fundamental requirement in developing robust and trustworthy AI systems and encourages the adoption of these techniques in ML deployment pipelines. In this way, organizations can proactively identify and mitigate the adverse effects of covariate drift while capitalizing on the benefits offered by serverless computing.
•Serverless-based architecture enables efficient data drift detection in ML systems.•Drift detection should be a requirement in the development of ML deployment pipelines.•An edge ML system can incorporate data drift detection mechanisms.
Purpose
The PLANET method was designed to simultaneously reconstruct maps of T1 and T2, the off‐resonance, the RF phase, and the banding free signal magnitude. The method requires a stationary B0 ...field over the course of a phase‐cycled balanced SSFP acquisition. In this work we investigated the influence of B0 drift on the performance of the PLANET method for single‐component and two‐component signal models, and we propose a strategy for drift correction.
Methods
The complex phase‐cycled balanced SSFP signal was modeled with and without frequency drift. The behavior of the signal influenced by drift was mathematically interpreted as a sum of drift‐dependent displacement of the data points along an ellipse and drift‐dependent rotation around the origin. The influence of drift on parameter estimates was investigated experimentally on a phantom and on the brain of healthy volunteers and was verified by numerical simulations. A drift correction algorithm was proposed and tested on a phantom and in vivo.
Results
Drift can be assumed to be linear over the typical duration of a PLANET acquisition. In a phantom (a single‐component signal model), drift induced errors of 4% and 8% in the estimated T1 and T2 values. In the brain, where multiple components are present, drift only had a minor effect. For both single‐component and two‐component signal models, drift‐induced errors were successfully corrected by applying the proposed drift correction algorithm.
Conclusion
We have demonstrated theoretically and experimentally the sensitivity of the PLANET method to B0 drift and have proposed a drift correction method.
Detailed analysis of convective fluxes caused by E × B drifts is carried out in a realistic JET configuration, based on a series of EDGE2D-EIRENE runs. The EDGE2D-EIRENE code includes all guiding ...centre drifts, E × B as well as ∇B and centrifugal drifts. Particle sources created by divergences of radial and poloidal components of the E × B drift are separately calculated for each flux tube in the divertor. It is demonstrated that in high recycling divertor conditions radial E × B drift creates particle sources in the common flux region (CFR) consistent with experimentally measured divertor and target asymmetries, with the poloidal E × B drift creating sources of an opposite sign but smaller in absolute value. That is, the experimentally observed asymmetries in the CFR are the opposite to what poloidal E × B drift by itself would cause. In the private flux region (PFR), the situation is reversed, with poloidal E × B drift being dominant. In this region poloidal E × B drift by itself contributes to experimentally observed asymmetries. Thus, in each region, the dominant component of the E × B drift acts so as to create the density (and hence, also temperature) asymmetries that are observed both in experiment and in 2D edge fluid codes. Since the total number of charged particles is much greater in the CFR than in PFR, divertor asymmetries caused by the E × B drift should be attributed primarily to particle sources in the CFR caused by radial E × B drift.