The practical implementation of machine learning in flow control is limited due to its significant training expenses. In the present study the convolutional neural network (CNN) trained with the data of the restricted nonlinear (RNL) model is used to predict the normal velocity on a detection plane at $y^+=10$ in a turbulent channel flow, and the predicted velocity is used as wall blowing and suction for drag reduction. An active control test is carried out by using the well-trained CNN in direct numerical simulation (DNS). Substantial drag reduction rates up to 19 % and 16 % are obtained based on the spanwise and streamwise wall shear stresses, respectively. Furthermore, we explore the online control of wall turbulence by combining the RNL model with reinforcement learning (RL). The RL is constructed to determine the optimal wall blowing and suction based on its observation of the wall shear stresses without using the label data on the detection plane for training. The controlling and training processes are conducted synchronously in a RNL flow field. The control strategy discovered by RL has similar drag reduction rates with those obtained previously by the established method. Also, the training cost decreases by over thirty times at $Re_{\tau }=950$ compared with the DNS-RL model. The present results provide a perspective that combining the RNL model with machine learning control for drag reduction in wall turbulence can be effective and computationally economical. Also, this approach can be easily extended to flows at higher Reynolds numbers.

We present a data-driven feedforward control to attenuate large transient lift experienced by an airfoil disturbed by an extreme level of discrete vortex gust. The current analysis uses a nonlinear machine-learning technique to compress the high-dimensional flow dynamics onto a low-dimensional manifold. While the interaction dynamics between the airfoil and extreme vortex gust are parametrized by its size, gust ratio and position, the wake responses are well captured on this simple manifold. The effect of extreme vortex disturbance about the undisturbed baseline flows can be extracted in a physically interpretable manner. Furthermore, we call on phase-amplitude reduction to model and control the complex nonlinear extreme aerodynamic flows. The present phase-amplitude reduction model reveals the sensitivity of the dynamical system in terms of the phase shift and amplitude change induced by external forcing with respect to the baseline periodic orbit. By performing the phase-amplitude analysis for a latent dynamical model identified by sparse regression, the sensitivity functions of low-dimensionalized aerodynamic flows for both phase and amplitude are derived. With the phase and amplitude sensitivity functions, optimal forcing can be determined to quickly suppress the effect of extreme vortex gusts towards the undisturbed states in a low-order space. The present optimal flow modification built upon the machine-learned low-dimensional subspace quickly alleviates the impact of transient vortex gusts for a variety of extreme aerodynamic scenarios, providing a potential foundation for flight of small-scale air vehicles in adverse atmospheric conditions.

When humans solve complex problems, they typically construct, reflect, and revise sequences of ideas, hypotheses, and beliefs until a final decision or conclusion is reached. Contrary to this, current machine learning models are mostly trained to map an input to one single and fixed output. In this paper, we investigate how we can equip models with the ability to represent, construct, and evaluate a second, third, and $k$-th thought within their prediction process. Drawing inspiration from Hegel’s dialectics, we propose and evaluate the thought flow concept which constructs a sequence of predictions. We present a self-correction mechanism which (a) is trained to estimate the model’s correctness and which (b) performs iterative prediction updates based on the gradient of the correctness prediction. We introduce our method focusing initially on question answering (QA) and carry out extensive experiments which demonstrate that (i) our method is able to correct its own predictions and that (ii) it can improve model performance by a large margin. In addition, we conduct a qualitative analysis of thought flow correction patterns and explore how thought flow predictions affect users’ human-AI collaboration in a crowdsourcing study. We find that (iii) thought flows improve user performance and are perceived as more natural, correct, and intelligent regarding single and/or top-3 predictions.

In 2022, the world experienced the deadliest year of armed conflict since the 1994 Rwandan genocide. Much of the intensity and frequency of recent conflicts has drawn more attention to failures in forecasting—that is, a failure to anticipate conflicts. Such capabilities have the potential to greatly reduce the time, motivation, and opportunities peacemakers have to intervene through mediation or peacekeeping operations. In recent years, the growth in the volume of open-source data coupled with the wide-scale advancements in machine learning suggests that it may be possible for computational methods to help the international community forecast intrastate conflict more accurately, and in doing so reduce the rise of conflict. In this commentary, we argue for the promise of conflict forecasting under several technical and policy conditions. From a technical perspective, the success of this work depends on improvements in the quality of conflict-related data and an increased focus on model interpretability. In terms of policy implementation, we suggest that this technology should be used primarily to aid policy analysis heuristically and help identify unexpected conflicts.

New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health, and societal well-being. Could artificial intelligence (AI) accelerate science to meet these global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here that it could be more holistic and encompassing. We introduce the concept of virtual laboratories as a new perspective on scientific knowledge generation and a means to incentivize new AI research and development. Despite the often perceived domain-specific research practices and inherent tacit knowledge, we argue that many elements of the research process recur across scientific domains and that even common software platforms for serving different domains may be possible. We outline how virtual laboratories will make it easier for AI researchers to contribute to a broad range of scientific domains, and highlight the mutual benefits virtual laboratories offer to both AI and domain scientists.

Archival aerial photographs are a unique but underused and potentially game-changing source to study twentieth-century environmental and climate change dynamics. While satellite imagery with comparable high resolution appeared only in the early twenty-first century, archival aerial imagery with native sub-1-meter resolution became ubiquitous in the 1940s. Archival aerial photography therefore quadruples the time depth of high-resolution analysis to eighty years, allowing for a more reliable identification of structural trends. Moreover, the greater time-depth brings into focus the Great Acceleration that started in the 1940s, and virtually in real time. The article uses a human manual analysis of a sample from two time series (1943 and 1971) of archival photographs of the Oshikango area of Namibia (see Figure 1) to demonstrate how aerial photography complements conventional datasets. Namibia was one of the first places in colonial Africa where what subsequently became the standard protocol for “aerial mapping” was used and for which the imagery and the “flight plans” have survived. The standard protocol makes the imagery compatible with any archival aerial photography from the 1940s to 1990s and the flight plans contain key information to identify, interpret, and combine the individual photographs into orthomosaics. Although the use of manual analysis of aerial photography is not new, unlocking the full explanatory potential of high-resolution mass data requires machine reading and analysis. Current machine reading methods, however, are based on the pixel method, which identifies such features as farms, water holes, and trees only as low-resolution pixel aggregates. In contrast, the object method of machine analysis, combined with Geographical Information Systems (GIS) technology to unlock the sub-1-meter native resolution of historical aerial photography, renders visible individual trees and other features, including their precise location and size, allowing for the dimensions of trees and other features to be measured between different time series of images. The interrelationships between different features in the environment can thus be assessed more precisely in space and over time, for example comparing tree growth and surface water sources. A major challenge is that the object method used for high resolution geospatial imagery cannot be easily applied to monochromatic archival aerial photography because it has been designed for analyzing multispectral satellite imagery. As discussed in the article, using the manual sample as a training data set for an experimental machine-learning protocol demonstrates proof of concept for automatically extracting such features as farms, water holes and trees as individual objects from archival aerial photography. This increases the time depth of available high-resolution land use, environmental, and climate data from 2000 back to the 1940s and provides a base line for the Great Acceleration and brings the massive changes from the 1940s through the 1990s in focus as captured in aerial photography.

We optimize jet mixing using large eddy simulations (LES) at a Reynolds number of $3000$. Key methodological enablers consist of Bayesian optimization, a surrogate model enhanced by deep learning and persistent data topology for physical interpretation. The mixing performance is characterized by an equivalent jet radius ($R_{eq}$) derived from the streamwise velocity in a plane located $8$ diameters downstream. The optimization is performed in a 22-dimensional actuation space that comprises most known excitations. This search space parameterizes the distributed actuation imposed on the bulk flow and at the periphery of the nozzle in the streamwise and radial directions. The momentum flux measures the energy input of the actuation. The optimization quadruples the jet radius $R_{eq}$ with a $7$-armed blooming jet after around $570$ evaluations. The control input requires $2\,\%$ momentum flux of the main flow, which is one order of magnitude lower than an ad hoc dual-mode excitation. Intriguingly, a pronounced suboptimum in the search space is associated with a double-helix jet, a new flow pattern. This jet pattern results in a mixing improvement comparable to the blooming jet. A state-of-the-art Bayesian optimization converges towards this double-helix solution. The learning is accelerated and converges to another better optimum by including a deep-learning-enhanced surrogate model trained along the optimization. Persistent data topology extracts the global and many local minima in the actuation space. These minima can be identified with flow patterns beneficial to the mixing.

Different types of neural networks have been used to solve the flow sensing problem in turbulent flows, namely to estimate velocity in wall-parallel planes from wall measurements. Generative adversarial networks (GANs) are among the most promising methodologies, due to their more accurate estimations and better perceptual quality. This work tackles this flow sensing problem in the vicinity of the wall, addressing for the first time the reconstruction of the entire three-dimensional (3-D) field with a single network, i.e. a 3-D GAN. With this methodology, a single training and prediction process overcomes the limitation presented by the former approaches based on the independent estimation of wall-parallel planes. The network is capable of estimating the 3-D flow field with a level of error at each wall-normal distance comparable to that reported from wall-parallel plane estimations and at a lower training cost in terms of computational resources. The direct full 3-D reconstruction also unveils a direct interpretation in terms of coherent structures. It is shown that the accuracy of the network depends directly on the wall footprint of each individual turbulent structure. It is observed that wall-attached structures are predicted more accurately than wall-detached ones, especially at larger distances from the wall. Among wall-attached structures, smaller sweeps are reconstructed better than small ejections, while large ejections are reconstructed better than large sweeps as a consequence of their more intense footprint.

As a promising machine learning method for active flow control (AFC), deep reinforcement learning (DRL) has been successfully applied in various scenarios, such as the drag reduction for stationary cylinders under both laminar and weakly turbulent conditions. However, current applications of DRL in AFC still suffer from drawbacks including excessive sensor usage, unclear search paths and insufficient robustness tests. In this study, we aim to tackle these issues by applying DRL-guided self-rotation to suppress the vortex-induced vibration (VIV) of a circular cylinder under the lock-in condition. With a state space consisting only of the acceleration, velocity and displacement of the cylinder, the DRL agent learns an effective control strategy that successfully suppresses the VIV amplitude by $99.6\,\%$. Through systematic comparisons between different combinations of sensory-motor cues as well as sensitivity analysis, we identify three distinct stages of the search path related to the flow physics, in which the DRL agent adjusts the amplitude, frequency and phase lag of the actions. Under the deterministic control, only a little forcing is required to maintain the control performance, and the VIV frequency is only slightly affected, showing that the present control strategy is distinct from those utilizing the lock-on effect. Through dynamic mode decomposition analysis, we observe that the growth rates of the dominant modes in the controlled case all become negative, indicating that DRL remarkably enhances the system stability. Furthermore, tests involving various Reynolds numbers and upstream perturbations confirm that the learned control strategy is robust. Finally, the present study shows that DRL is capable of controlling VIV with a very small number of sensors, making it effective, efficient, interpretable and robust. We anticipate that DRL could provide a general framework for AFC and a deeper understanding of the underlying physics.

Climate change is a complex global issue that requires widespread understanding, support and collaboration for effective solutions. This research delves into the crucial role of communication in tackling climate change and reaching net-zero goals. Leveraging advanced machine learning techniques, we focus on 10 core climate change topics derived from social media conversations over time. This analysis underscores the importance of a holistic and interconnected approach, involving a diverse array of policies at local, national and global levels to combat climate change effectively and attain net-zero objectives. We offer key policy suggestions that can significantly contribute to this vital cause.

Morphological analysis is a crucial preprocessing stage for building the state-of-the-art natural language processing applications. We propose a bidirectional LSTM (long short-term memory)-based approach to develop the morphological analyzer for the Gujarati language. Our morph analyzer predicts a root word and the morphological features for the given inflected word. We have experimented with two different methods for label representation for predicting morphological features: the monolithic representation method and the individual label representation method. We have also created the gold morphological dataset of 16,234 unique words for the Gujarati language. The dataset contains morpheme splitting and grammatical feature information for each inflected word. Due to the change in the label representation technique in the proposed model, the accuracy of the present baseline system is improved by a large margin. The proposed system performs very well across the POS categories without the knowledge of language-specific suffix rules.

This study proposes a self-learning algorithm for closed-loop cylinder wake control targeting lower drag and lower lift fluctuations with the additional challenge of sparse sensor information, taking deep reinforcement learning (DRL) as the starting point. The DRL performance is significantly improved by lifting the sensor signals to dynamic features (DFs), which predict future flow states. The resulting DF-based DRL (DF-DRL) automatically learns a feedback control in the plant without a dynamic model. Results show that the drag coefficient of the DF-DRL model is 25 % less than the vanilla model based on direct sensor feedback. More importantly, using only one surface pressure sensor, DF-DRL can reduce the drag coefficient to a state-of-the-art performance of approximately 8 % at Reynolds number $(Re) = 100$ and significantly mitigates lift coefficient fluctuations. Hence, DF-DRL allows the deployment of sparse sensing of the flow without degrading the control performance. This method also exhibits strong robustness in flow control under more complex flow scenarios, reducing the drag coefficient by 32.2 % and 46.55 % at $Re =500$ and 1000, respectively. Additionally, the drag coefficient decreases by 28.6 % in a three-dimensional turbulent flow at $Re =10\,000$. Since surface pressure information is more straightforward to measure in realistic scenarios than flow velocity information, this study provides a valuable reference for experimentally designing the active flow control of a circular cylinder based on wall pressure signals, which is an essential step toward further developing intelligent control in a realistic multi-input multi-output system.