results: 在过去5年内，机器学习技术已经被广泛应用于提高当前气候模型的准确性，提供了有力的数据分析工具。Abstract
Recent achievements in machine learning (Ml) have had a significant impact on various fields, including climate science. Climate modeling is very important and plays a crucial role in shaping the decisions of governments and individuals in mitigating the impact of climate change. Climate change poses a serious threat to humanity, however, current climate models are limited by computational costs, uncertainties, and biases, affecting their prediction accuracy. The vast amount of climate data generated by satellites, radars, and earth system models (ESMS) poses a significant challenge. ML techniques can be effectively employed to analyze this data and extract valuable insights that aid in our understanding of the earth climate. This review paper focuses on how ml has been utilized in the last 5 years to boost the current state-of-the-art climate models. We invite the ml community to join in the global effort to accurately model the earth climate by collaborating with other fields to leverage ml as a powerful tool in this endeavor.
摘要
Recent advances in machine learning (ML) have had a profound impact on various fields, including climate science. Climate modeling is crucial and plays a vital role in shaping the decisions of governments and individuals in mitigating the impact of climate change. However, current climate models are limited by computational costs, uncertainties, and biases, which affect their prediction accuracy. The vast amount of climate data generated by satellites, radars, and earth system models (ESMs) poses a significant challenge. ML techniques can be effectively employed to analyze this data and extract valuable insights that aid in our understanding of the earth climate. This review paper focuses on how ML has been utilized in the last five years to improve the current state-of-the-art climate models. We invite the ML community to join in the global effort to accurately model the earth climate by collaborating with other fields to leverage ML as a powerful tool in this endeavor.Note: Please note that the translation is in Simplified Chinese, which is the standard form of Chinese used in mainland China and other countries. If you need Traditional Chinese, please let me know.
results: 作者在IBM Quantum Composer中实现了模块，并使用IBM QASM仿真器进行测试。最终，模块被编译使用Python包Qiskit，并将任务分发到分布式的IBM Q System One量子计算机上进行执行。成功运行结果在Friaufhofer Q System One上进行了证明。Abstract
Few of the known quantum algorithms can be reliably executed on a quantum computer. Therefore, as an extension, we propose a Parallel Quantum Hough transform (PQHT) algorithm that we execute on a quantum computer. We give its implementation and discuss the results obtained. The PQHT algorithm is conceptually divided into a parallel rotation stage consisting of a set of connected programmable $\texttt{RZ}$ rotation gates, with adjustable node connections of coincidence detectors realized with quantum logic gates. The modules were developed using IBM Quantum Composer and tested using the IBM QASM simulator. Finally, the modules were programmed using the Python package Qiskit and the jobs were sent to distributed IBM Q System One quantum computers. The successful run results on Fraunhofer Q System One in Ehningen will be presented as a proof of concept for the PQHT algorithm.
摘要
“现有的量子算法中，只有一些可靠地在量子计算机上执行。因此，我们提出了一种并行量子哈夫散度（PQHT）算法，我们在量子计算机上实现。我们将其实现方式和结果讨论。PQHT算法从概念上分为一个并行旋转阶段，包括一组相连的可编程的$\texttt{RZ}$旋转门，其中节点连接的吻合探测器实现使用量子逻辑门。模块使用IBM量子 composer开发，使用IBM QASM simulator进行测试。最后，模块使用Python包Qiskit编程，并将任务分发给分布式IBM Q System One量子计算机。成功运行结果在 Fraunhofer Q System One 上将被提供作为PQHT算法的证明。”Note that the translation is in Simplified Chinese, which is the standard form of Chinese used in mainland China and Singapore. If you need Traditional Chinese, please let me know.
Ultrafast 3-D Super Resolution Ultrasound using Row-Column Array specific Coherence-based Beamforming and Rolling Acoustic Sub-aperture Processing: In Vitro, In Vivo and Clinical Study
paper_authors: Joseph Hansen-Shearer, Jipeng Yan, Marcelo Lerendegui, Biao Huang, Matthieu Toulemonde, Kai Riemer, Qingyuan Tan, Johanna Tonko, Peter D. Weinberg, Chris Dunsby, Meng-Xing Tang
results: 实验结果表明，这种新的图像重建方法可以减少“false”位置的比例，降低杂音水平和提高图像扫描速率，并在人体内进行非侵入式的ultrasound imaging。Abstract
The row-column addressed array is an emerging probe for ultrafast 3-D ultrasound imaging. It achieves this with far fewer independent electronic channels and a wider field of view than traditional 2-D matrix arrays, of the same channel count, making it a good candidate for clinical translation. However, the image quality of row-column arrays is generally poor, particularly when investigating tissue. Ultrasound localisation microscopy allows for the production of super-resolution images even when the initial image resolution is not high. Unfortunately, the row-column probe can suffer from imaging artefacts that can degrade the quality of super-resolution images as `secondary' lobes from bright microbubbles can be mistaken as microbubble events, particularly when operated using plane wave imaging. These false events move through the image in a physiologically realistic way so can be challenging to remove via tracking, leading to the production of 'false vessels'. Here, a new type of rolling window image reconstruction procedure was developed, which integrated a row-column array-specific coherence-based beamforming technique with acoustic sub-aperture processing for the purposes of reducing `secondary' lobe artefacts, noise and increasing the effective frame rate. Using an {\it{in vitro} cross tube, it was found that the procedure reduced the percentage of `false' locations from $\sim$26\% to $\sim$15\% compared to traditional orthogonal plane wave compounding. Additionally, it was found that the noise could be reduced by $\sim$7 dB and that the effective frame rate could be increased to over 4000 fps. Subsequently, {\it{in vivo} ultrasound localisation microscopy was used to produce images non-invasively of a rabbit kidney and a human thyroid.
摘要
矩阵列 Addressed 数组是一种emerging probe дляultrafast 3D 超声成像。它通过使用 fewer independent electronic channels 和更广阔的视场，可以与传统的2D 矩阵数组相比，提供更高的图像质量，这使其成为临床翻译的好选择。然而，矩阵列数组的图像质量通常较差，特别是在调查组织时。超声成像微scopic allow for the production of super-resolution images even when the initial image resolution is not high. Unfortunately, the row-column probe can suffer from imaging artifacts that can degrade the quality of super-resolution images as "secondary" lobes from bright microbubbles can be mistaken as microbubble events, particularly when operated using plane wave imaging. These false events move through the image in a physiologically realistic way so can be challenging to remove via tracking, leading to the production of 'false vessels'. Here, a new type of rolling window image reconstruction procedure was developed, which integrated a row-column array-specific coherence-based beamforming technique with acoustic sub-aperture processing for the purposes of reducing "secondary" lobe artifacts, noise, and increasing the effective frame rate. Using an in vitro cross tube, it was found that the procedure reduced the percentage of 'false' locations from approximately 26% to approximately 15% compared to traditional orthogonal plane wave compounding. Additionally, it was found that the noise could be reduced by approximately 7 dB and that the effective frame rate could be increased to over 4000 fps. Subsequently, in vivo ultrasound localization microscopy was used to produce images non-invasively of a rabbit kidney and a human thyroid.
Degradation Estimation Recurrent Neural Network with Local and Non-Local Priors for Compressive Spectral Imaging
results: 这个论文的实验结果表明，DERNN-LNLT可以提高CASSI系统中HSI重建的精度和效率，并且可以更好地利用本地和非本地的彩色спектраль图像约束。Abstract
In coded aperture snapshot spectral imaging (CASSI) systems, a core problem is to recover the 3D hyperspectral image (HSI) from the 2D measurement. Current deep unfolding networks (DUNs) for the HSI reconstruction mainly suffered from three issues. Firstly, in previous DUNs, the DNNs across different stages were unable to share the feature representations learned from different stages, leading to parameter sparsity, which in turn limited their reconstruction potential. Secondly, previous DUNs fail to estimate degradation-related parameters within a unified framework, including the degradation matrix in the data subproblem and the noise level in the prior subproblem. Consequently, either the accuracy of solving the data or the prior subproblem is compromised. Thirdly, exploiting both local and non-local priors for the HSI reconstruction is crucial, and it remains a key issue to be addressed. In this paper, we first transform the DUN into a Recurrent Neural Network (RNN) by sharing parameters across stages, which allows the DNN in each stage could learn feature representation from different stages, enhancing the representativeness of the DUN. Secondly, we incorporate the Degradation Estimation Network into the RNN (DERNN), which simultaneously estimates the degradation matrix and the noise level by residual learning with reference to the sensing matrix. Thirdly, we propose a Local and Non-Local Transformer (LNLT) to effectively exploit both local and non-local priors in HSIs. By integrating the LNLT into the DERNN for solving the prior subproblem, we propose the DERNN-LNLT, which achieves state-of-the-art performance.
摘要
在coded aperture snapshot spectral imaging（CASSI）系统中，核心问题是从2D测量数据中回归3D彩色спектраль成像（HSI）。目前的深度 unfolding network（DUN）for HSI重建主要受到以下三个问题的限制：首先，在前一代DUN中，不同阶段的神经网络（DNN）无法共享不同阶段学习的特征表示，导致参数稀缺，从而限制了重建的潜力。第二，前一代DUN无法在一个框架下 simultanously 估计数据偏移矩阵和噪声水平，这两者都是重建HSI的关键参数。如果仅仅解决数据问题或先验问题，则其准确性将受到限制。第三，在HSIs中利用本地和非本地的假设是重要的，但是在前一代DUN中，这些假设并未得到充分利用。在本文中，我们首先将DUN转换为回归神经网络（RNN），使得不同阶段的DNN可以共享特征表示，从而提高DUN的表现。其次，我们将偏移估计网络（DERNN） incorporated into RNN，以同时估计数据偏移矩阵和噪声水平，通过对准测试矩阵的学习。最后，我们提出了本地和非本地转换器（LNLT），以有效地利用HSIs中的本地和非本地假设。通过将LNLTintegrated into DERNN，我们提出了DERNN-LNLT，实现了state-of-the-art的性能。