Comparison between deep learning and fully connected neural network in performance prediction of power cycles: Taking supercritical CO 2 Brayton cycle as an example

A bibliometric analysis of carbon neutrality: Research hotspots and future directions

Global attention has shifted in recent years to climate change and global warming. The international community has set the objective of carbon neutrality to address the climate crisis. Carbon neutrality has drawn significant attention as a crucial step in the fight against climate change, with individual nations having established their carbon neutrality targets. This paper aims to use bibliometric analysis to investigate research hotspots and trends in carbon neutrality research, and accesses the literature through the Web of Science (WoS) core database and undertakes an in-depth examination of 909 publications linked to carbon neutrality around the world using Vosviewer and Bibliometrix software. According to the findings, the number of carbon neutrality publications has increased dramatically in recent years. There are also notable differences in carbon neutrality research across countries and regions. China and the US are the primary drivers and leaders of carbon neutrality research, and developing countries have relatively little carbon neutrality research. Research has concentrated on carbon neutrality's practical, technical, policy, and economic aspects, as well as renewable energy sources, carbon conversion technologies, and carbon capture and storage technologies are also research hotspots. The paper also outlines opportunities for the advancement of carbon neutrality research in the future, including how it might be further integrated with Artificial intelligence (AI) and the metaverse, and how to attack the difficulties and uncertainties faced by the post-epidemic rebound. This study aids in understanding the current state of the field of carbon neutrality research and can be used to guide future studies.

Prediction of Maximum Absorption Wavelength Using Deep Neural Networks

Fluorescent molecules are important tools in biological detection, and numerous efforts have been made to develop compounds to meet the desired photophysical properties. For example, tuning the wavelength allows an appropriate penetration depth with minimal interference from the autofluorescence/scattering for a better signal-to-noise contrast. However, there are limited guidelines to rationally design or computationally predict the optical properties from first principles, and factors like the solvent effects will make it more complicated. Herein, we established a database (SMFluo1) of 1181 solvated small-molecule fluorophores covering the ultraviolet-visible-near-infrared absorption window and developed new machine learning models based on deep neural networks for accurately predicting photophysical parameters. The optimal system was applied to 120 out-of-sample compounds, and it exhibited remarkable accuracy with a mean relative error of 1.52%. In this new paradigm, a deep learning algorithm is promising to complement conventional theoretical and experimental studies of fluorophores and to greatly accelerate the discovery of new dyes. Due to its simplicity and efficiency, data from newly developed fluorophores can be easily supplemented to this system to further improve the accuracy across various dye families.