Aspen Technology, Inc. (NASDAQ:AZPN), a global leader in asset optimization software, today announced the general availability of the aspenONE V12 software release, which embeds artificial intelligence (AI) across the portfolio, and uses the cloud for delivery of enterprise-wide analytics and insights for increased safety, sustainability, and improved margins. AspenTech's Industrial AI solutions democratize the application of AI where it can deliver most value and is a vital step towards the Self-Optimizing Plant. "Aspen Hybrid Models are a major advance in the field of chemical engineering. Hybrid models are a major step forward in bringing together AspenTech's process models and machine learning and are a game changer in process engineering and plant improvement," said Dr. Karuna Potdar, Vice President, Technology Centre of Excellence, Reliance Industries Limited. Aspen Hybrid Models capture data from assets across the enterprise, and then apply AI, engineering first principles and AspenTech's domain expertise to deliver comprehensive, more accurate models at enterprise speed and scale.

Prescribed burns are currently the most effective method of reducing the risk of widespread wildfires, but a largely missing component in forest management is knowing which fuels one can safely burn to minimize exposure to toxic smoke. Here we show how machine learning, such as spectral clustering and manifold learning, can provide interpretable representations and powerful tools for differentiating between smoke types, hence providing forest managers with vital information on effective strategies to reduce climate-induced wildfires while minimizing production of harmful smoke.

As U.S. particle physicists contemplate their future, they find themselves victims of their own surprising success. Seven years ago, the often fractious community hammered out its current research road map and rallied around it. Thanks to that unity—and generous budgets—the Department of Energy (DOE), the field's main U.S. sponsor, has already started on almost every project on the list. So this week, as U.S. particle physicists start to drum up new ideas for the next decade in a yearlong Snowmass process—named for the Colorado ski resort where such planning exercises once took place—they have no single big project to push for (or against). And in some subfields, the next steps seem far less obvious than they were 10 years ago. “We have to be much more open minded about what particle physics and fundamental physics are,” says Young-Kee Kim of the University of Chicago, chair of the American Physical Society's division of particles and fields, which is sponsoring the planning exercise. Ten years ago, the U.S. particle physics community was in disarray. The high-energy frontier had passed to CERN, the European particle physics laboratory near Geneva, where in 2012 the world's biggest atom smasher, the Large Hadron Collider (LHC), blasted out the long-sought Higgs boson, the last piece in particle physicists' standard model. Some physicists wanted the United States to build a huge experiment to fire elusive particles called neutrinos long distances through Earth to study how they “oscillate”—morph from one of their three types to another—as they zip along. Others wanted the country to help push for the next big collider. Those tensions came to a head during the last Snowmass effort in 2013, and the subsequent deliberations of the Particle Physics Project Prioritization Panel (P5), which wrote the road map. U.S. researchers agreed to build the neutrino experiment, but make it bigger and better by inviting international partners. They also decided to continue to participate fully in the LHC, and to pursue a variety of smaller projects at home (see table, below). The next collider would have to wait. Most important, DOE officials warned, the squabbling and backstabbing had to stop. In fact, physicists recall, the 2013 process had an informal motto: “Bickering scientists get nothing.” ![Figure][1] CREDIT: PARTICLE PHYSICS PROJECT PRIORITIZATION PANEL REPORT (2014) Physicists have just started to build the current plan's centerpiece. The Long-Baseline Neutrino Facility (LBNF) at Fermi National Accelerator Laboratory (Fermilab) in Illinois will shoot the particles through 1300 kilometers of rock to the Deep Underground Neutrino Experiment (DUNE) in South Dakota, a detector filled with 40,000 tons of frigid liquid argon. LBNF/DUNE, which should come online in 2026, aims to be the definitive study of neutrino oscillations and whether they differ between neutrinos and antineutrinos, which could help explain how the universe generated more matter than antimatter. “The angst in the neutrino community is a lot lower than it was last time,” says Kate Scholberg, a neutrino physicist at Duke University. “The DUNE program will be going on at least into the 2030s.” However, researchers are already thinking of upgrades to the $2.6 billion experiment, she notes. In other areas, the future looks less certain. The last time around, for example, scientists had a pretty clear path forward in their search for particles of dark matter—the so-far-unidentified stuff that appears to pervade the galaxies and bind them with its gravity. Researchers had built small underground detectors that searched for the signal of weakly interacting massive particles (WIMPs), the leading dark matter candidate, bumping into atomic nuclei. The obvious plan was to expand the detectors to the ton scale. Now, two multi-ton WIMP detectors are under construction. But so far WIMPs haven't shown up, and scaling up that technology further “is probably not going to work very well anymore,” says Marcelle Soares-Santos, a physicist at the University of Michigan, Ann Arbor. “So we need to think a little bit more out of the box.” Researchers are now contemplating a hunt for other types of dark matter particles, using new detectors that exploit quantum mechanical effects to achieve exquisite levels of sensitivity. A perennial question for the field is what the next great particle collider will be. The obvious need is for one that fires electrons into positrons to crank out copious Higgs bosons and study their properties in detail, says Meenakshi Narain, a physicist at Brown University. But possible designs vary. Physicists in Japan are discussing such a Higgs factory in the form of a 30-kilometer-long linear electron-positron collider. Meanwhile, CERN has begun a study of an 80- to 100-kilometer circular collider. China has plans for a similar circular collider. However, Vladimir Shiltsev, an accelerator physicist at Fermilab, says those aren't the only potential options. “The real picture is much murkier.” Snowmass organizers have received at least 16 different proposals for colliders, including one that would smash together muons—heavier, unstable cousins of electrons—and another that would use photons. Snowmass participants should consider all options, Shiltsev says. Joe Lykken, Fermilab's deputy director for research, suggests physicists could even push for DOE to support a massive experiment that has nothing to do with particles: a next-generation detector of gravitational waves, spacetime ripples set off when massive objects such as black holes collide. Their discovery in 2015 by the Laser Interferometer Gravitational-Wave Observatory (LIGO) opened a new window on the universe. LIGO consists of two L-shaped optical instruments with arms 4 kilometers long in Louisiana and Washington; it was built by the National Science Foundation. The next generation of ground-based detectors could be 10 times as big, and might better fit DOE, which specializes in scientific megaprojects, Lykken says. “It starts to sound like the kind of thing that the DOE would be interested in and maybe required for,” he says. During the coming year, Snowmass participants will air the more than 2000 ideas researchers have already proffered in two-page summaries. Then, a new P5 will formulate a new plan. Whatever ideas scientists come up with, to execute their new plan they'll have to maintain the harmony that in recent years has made their planning process an exemplar to other fields. “Being unified is the new norm for us,” quips Jim Siegrist, DOE's associate director for high energy physics. “So we have to continue to keep a lid on divisiveness and that'll be a challenge.” [1]: pending:yes

Research challenges encountered across science, engineering, and economics can frequently be formulated as optimization tasks. In chemistry and materials science, recent growth in laboratory digitization and automation has sparked interest in optimization-guided autonomous discovery and closed-loop experimentation. Experiment planning strategies based on off-the-shelf optimization algorithms can be employed in fully autonomous research platforms to achieve desired experimentation goals with the minimum number of trials. However, the experiment planning strategy that is most suitable to a scientific discovery task is a priori unknown while rigorous comparisons of different strategies are highly time and resource demanding. As optimization algorithms are typically benchmarked on low-dimensional synthetic functions, it is unclear how their performance would translate to noisy, higher-dimensional experimental tasks encountered in chemistry and materials science. We introduce Olympus, a software package that provides a consistent and easy-to-use framework for benchmarking optimization algorithms against realistic experiments emulated via probabilistic deep-learning models. Olympus includes a collection of experimentally derived benchmark sets from chemistry and materials science and a suite of experiment planning strategies that can be easily accessed via a user-friendly python interface. Furthermore, Olympus facilitates the integration, testing, and sharing of custom algorithms and user-defined datasets. In brief, Olympus mitigates the barriers associated with benchmarking optimization algorithms on realistic experimental scenarios, promoting data sharing and the creation of a standard framework for evaluating the performance of experiment planning strategies

Evaluating the mechanical response of fiber-reinforced composites can be extremely time consuming and expensive. Machine learning (ML) techniques offer a means for faster predictions via models trained on existing input-output pairs and have exhibited success in composite research. This paper explores a fully convolutional neural network modified from StressNet, which was originally for lin-ear elastic materials and extended here for a non-linear finite element (FE) simulation to predict the stress field in 2D slices of segmented tomography images of a fiber-reinforced polymer specimen. The network was trained and evaluated on data generated from the FE simulations of the exact microstructure. The testing results show that the trained network accurately captures the characteristics of the stress distribution, especially on fibers, solely from the segmented microstructure images. The trained model can make predictions within seconds in a single forward pass on an ordinary laptop, given the input microstructure, compared to 92.5 hours to run the full FE simulation on a high-performance computing cluster. These results show promise in using ML techniques to conduct fast structural analysis for fiber-reinforced composites and suggest a corollary that the trained model can be used to identify the location of potential damage sites in fiber-reinforced polymers.

The TriRhenaTech alliance presents a collection of accepted papers of the cancelled tri-national 'Upper-Rhine Artificial Inteeligence Symposium' planned for 13th May 2020 in Karlsruhe. The TriRhenaTech alliance is a network of universities in the Upper-Rhine Trinational Metropolitan Region comprising of the German universities of applied sciences in Furtwangen, Kaiserslautern, Karlsruhe, and Offenburg, the Baden-Wuerttemberg Cooperative State University Loerrach, the French university network Alsace Tech (comprised of 14 'grandes \'ecoles' in the fields of engineering, architecture and management) and the University of Applied Sciences and Arts Northwestern Switzerland. The alliance's common goal is to reinforce the transfer of knowledge, research, and technology, as well as the cross-border mobility of students.

A few years ago, when Tata Sampann was working on a recast and new visual brand identity, it experimented with a new way of figuring out what would work and what would not. Rather than the usual focus group discussions and surveys, it opted for neuro research. "The thought was to use the technique and understand elements that capture attention, high points of emotional engagement and trigger memory retention to create packaging for the brand to make it stand out from the rest," says Richa Arora, president, packaged foods, India, Tata Consumer Products. From eye tracking to virtual reality-based tests, Tata Sampann used novel techniques to gauge the subconscious feelings of consumers about the design and how they reacted to it. As a result, says Arora, it could come up with clutter-breaking appeal in its final packaging and visual identity.

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the models also plays an essential role in achieving the best generalizing models. Generally, a dataset that is best suited for a specific task tends to be small. In such a case, it is the standard solution to transfer knowledge from a large or clean dataset in the same domain. In this paper, we conduct a systematic and intensive examination of data transfer approaches on end-to-end generative models, in application to retrosynthesis. Experimental results show that typical data transfer methods can improve test prediction scores of an off-the-shelf Transformer baseline model. Especially, the pre-training plus fine-tuning approach boosts the accuracy scores of the baseline, achieving the new state-of-the-art. In addition, we conduct a manual inspection for the erroneous prediction results. The inspection shows that the pre-training plus fine-tuning models can generate chemically appropriate or sensible proposals in almost all cases.

A typical chemist running a known reaction will start by finding the method described in a published paper. Mehr et al. report a software platform that uses natural language processing to translate the organic chemistry literature directly into editable code, which in turn can be compiled to drive automated synthesis of the compound in the laboratory. The synthesis procedure is intended to be universally applicable to robotic systems operating in a batch reaction architecture. The full process is demonstrated for synthesis of an analgesic as well as common oxidizing and fluorinating agents. Science , this issue p. [101][1] Robotic systems for chemical synthesis are growing in popularity but can be difficult to run and maintain because of the lack of a standard operating system or capacity for direct access to the literature through natural language processing. Here we show an extendable chemical execution architecture that can be populated by automatically reading the literature, leading to a universal autonomous workflow. The robotic synthesis code can be corrected in natural language without any programming knowledge and, because of the standard, is hardware independent. This chemical code can then be combined with a graph describing the hardware modules and compiled into platform-specific, low-level robotic instructions for execution. We showcase automated syntheses of 12 compounds from the literature, including the analgesic lidocaine, the Dess-Martin periodinane oxidation reagent, and the fluorinating agent AlkylFluor. [1]: /lookup/doi/10.1126/science.abc2986

Reinforcement Learning algorithms require a large number of samples to solve complex tasks with sparse and delayed rewards. Complex tasks can often be hierarchically decomposed into sub-tasks. A step in the Q-function can be associated with solving a sub-task, where the expectation of the return increases. RUDDER has been introduced to identify these steps and then redistribute reward to them, thus immediately giving reward if sub-tasks are solved. Since the problem of delayed rewards is mitigated, learning is considerably sped up. However, for complex tasks, current exploration strategies as deployed in RUDDER struggle with discovering episodes with high rewards. Therefore, we assume that episodes with high rewards are given as demonstrations and do not have to be discovered by exploration. Typically the number of demonstrations is small and RUDDER's LSTM model as a deep learning method does not learn well. Hence, we introduce Align-RUDDER, which is RUDDER with two major modifications. First, Align-RUDDER assumes that episodes with high rewards are given as demonstrations, replacing RUDDER's safe exploration and lessons replay buffer. Second, we replace RUDDER's LSTM model by a profile model that is obtained from multiple sequence alignment of demonstrations. Profile models can be constructed from as few as two demonstrations as known from bioinformatics. Align-RUDDER inherits the concept of reward redistribution, which considerably reduces the delay of rewards, thus speeding up learning. Align-RUDDER outperforms competitors on complex artificial tasks with delayed reward and few demonstrations. On the MineCraft ObtainDiamond task, Align-RUDDER is able to mine a diamond, though not frequently. Github: https://github.com/ml-jku/align-rudder, YouTube: https://youtu.be/HO-_8ZUl-UY