BUSCADOR RECOLECTA

16 pags., 5 figs., 1 tab., We present an inference method utilizing artificial neural networks for parameter estimation of a quantum probe monitored through a single continuous measurement. Unlike existing approaches focusing on the diffusive signals generated by continuous weak measurements, our method harnesses quantum correlations in discrete photon-counting data characterized by quantum jumps. We benchmark the precision of this method against Bayesian inference, which is optimal in the sense of information retrieval. By using numerical experiments on a two-level quantum system, we demonstrate that our approach can achieve a similar optimal performance as Bayesian inference, while drastically reducing computational costs. Additionally, the method exhibits robustness against the presence of imperfections in both measurement and training data. This approach offers a promising and computationally efficient tool for quantum parameter estimation with photon-counting data, relevant for applications such as quantum sensing or quantum imaging, as well as robust calibration tasks in laboratory-based settings., E R was supported by Nippon Telegraph and Telephone Corporation (NTT) Research during the early stages of this work. S A and
M K acknowledge support from the Knut and Alice Wallenberg Foundation through the Wallenberg Centre
for Quantum Technology (WACQT). M G L acknowledges financial support from the Spanish Ministerio de
Ciencia e Innovación, through project PID2020-115864RB-I00 and grant PRE2021-098697. F N is supported
in part by Nippon Telegraph and Telephone Corporation (NTT) Research, the Japan Science and Technology
Agency (JST) [via the Quantum Leap Flagship Program (Q-LEAP) and the Moonshot R&D Grant No.
JPMJMS2061], the Asian Office of Aerospace Research and Development (AOARD) (via Grant No.
FA2386-20-1-4069), and the Office of Naval Research Global (ONR) (via GrantNo. N62909-23-1-2074). C S
M acknowledges that the project that gave rise to these results received the support of a fellowship from ‘la
Caixa’ Foundation (ID 100010434) and from the European Union’s Horizon 2020 research and innovation
programme under the Marie Skłodowska-Curie Grant Agreement No.847648, with fellowship code
LCF/BQ/PI20/11760026, and financial support from the MCINN projects PID2021-126964OB-I00
(QENIGMA) and the Proyecto Sinérgico CAM 2020 Y2020/TCS- 6545 (NanoQuCo-CM). We acknowledge
the usage of the HOKUSAI BigWaterfall (HBW) cluster from the Information System Division of RIKEN.

<p>QUAM–AFM Lite is the scaled-down version of QUAM-AFM, the largest dataset of simulated Atomic Force Microscopy (AFM) images. This reduced version was generated from a selection of 1,755 molecules that span the most relevant bonding structures and chemical species in organic chemistry. Similar to the extended version, QUAM-AFM Lite contains, for each molecule, 24 3D image stacks, each consisting of constant-height images simulated for 10 tip-sample distances (in the relevant imaging range and spanning a variation of 1 Å (0.1 nanometers)) with one of the 24 different combination of AFM operational parameters, resulting in a total of 421,200 images with a resolution of 256x256 pixels.</p>

<p>The operational parameters include six different values for the cantilever oscillation amplitude (0.40, 0.60, 0.80, 1.00, 1.20, 1.40Å), 4 values of the elastic constant describing the tilting of the CO tip (0.40, 0.60, 0.80 and 1.00 N/m). The first parameter is freely chosen in the experiments in order to enhance different features of the image, while the last one reflects differences in the attachment of the CO molecule to the metal tip that are routinely observed and has been characterized in the experiments.</p>

<p>The data provided for each molecule includes, besides a set of AFM images, the ball–and–stick depiction, the IUPAC name, the chemical formula, the atomic coordinates, and the map of atom heights. In order to simplify the use of the collection as a source of information, we have developed a Graphical User Interface (GUI) that allows the search for structures by CID number, IUPAC name or chemical formula.</p>

<p>This dataset arises as a product of the research carried out in collaboration between Quasar Science Resources S.L. (https://quasarsr.com) and the Scanning Probe Microscopy Theory & Nanomechanics Research Group (SPMTH) (http://www.uam.es/spmth) at the Universidad Autónoma de Madrid (UAM), funded by the Comunidad de Madrid under the Industrial Doctorate Programme 2017 (project reference IND2017/IND-7793).</p>

<p>The main goal of this dataset is to provide a simplified version of QUAM-AFM that allows to analyse the distribution of information and/or the graphical interface without the need for a full download. The extended version, QUAM-AFM, supports the development of deep learning methods for molecular identification through AFM imaging. Once this project has concluded, this dataset is made freely accessible in order to facilitate and to promote research in a range of fields including Atomic Force Microscopy, on-surface synthesis and deep learning applications.</p>

<p>QUAM–AFM is the largest dataset of simulated Atomic Force Microscopy (AFM) images generated from a selection of 685,513 molecules that span the most relevant bonding structures and chemical species in organic chemistry. QUAM-AFM contains, for each molecule, 24 3D image stacks, each consisting of constant-height images simulated for 10 tip-sample distances (in the relevant imaging range and spanning a variation of 1 Å (0.1 nanometers)) with one of the 24 different combination of AFM operational parameters, resulting in a total of 165 million images with a resolution of 256x256 pixels. The 3D stacks are especially appropriate to tackle the goal of chemical identification within AFM experiments by using deep learning techniques.</p>

<p>The operational parameters include six different values for the cantilever oscillation amplitude (0.40, 0.60, 0.80, 1.00, 1.20, 1.40 Å), 4 values of the elastic constant describing the tilting of the CO tip (0.40, 0.60, 0.80 and 1.00 N/m). The first parameter is freely chosen in the experiments in order to enhance different features of the image, while the last one reflects differences in the attachment of the CO molecule to the metal tip that are routinely observed and has been characterized in the experiments.</p>

<p>The data provided for each molecule includes, besides a set of AFM images, the ball–and–stick depiction, the IUPAC name, the chemical formula, the atomic coordinates, and the map of atom heights. In order to simplify the use of the collection as a source of information, we have developed a Graphical User Interface (GUI) that allows the search for structures by CID number, IUPAC name or chemical formula.</p>

<p>This dataset arises as a product of the research carried out in collaboration between Quasar Science Resources S.L. (https://quasarsr.com) and the Scanning Probe Microscopy Theory & Nanomechanics Research Group (SPMTH) (http://www.uam.es/spmth) at the Universidad Autónoma de Madrid (UAM), funded by the Comunidad de Madrid under the Industrial Doctorate Programme 2017 (project reference IND2017/IND-7793).</p>

<p>The main goal of this dataset is to support the development of deep learning methods for molecular identification through AFM imaging. Once this project has concluded, this dataset is made freely accessible in order to facilitate and to promote research in a range of fields including Atomic Force Microscopy, on-surface synthesis and deep learning applications.</p>