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

The problem of segregating recyclable waste is fairly daunting for many countries. This article presents an approach for image based classification of plastic waste using one-shot learning techniques. The proposed approach exploits discriminative features generated via the siamese and triplet loss convolutional neural networks to help differentiate between 5 types of plastic waste based on their resin codes. The approach achieves an accuracy of 99.74% on the WaDaBa Database

Scientists have been inspired by Pacman to create a plastic-eating'cocktail', which could help eradicate plastic waste. It's made up of two enzymes – called PETase and MHETase – produced by a type of bacteria that feeds on plastic bottles, called Ideonella sakaiensis. Unlike natural degradation, which can take hundreds of years, the super-enzyme is able to convert the plastic back to its original'building blocks' in a few days. The two enzymes work together like'two Pac-men joined by a piece of string' munching down snack pellets in the popular video game. The new super-enzyme digests plastic up to six times faster than the original PETase enzyme alone, which was discovered by the team in 2018.

Traditional linear subspace reduced order models (LS-ROMs) are able to accelerate physical simulations, in which the intrinsic solution space falls into a subspace with a small dimension, i.e., the solution space has a small Kolmogorov n-width. However, for physical phenomena not of this type, e.g., any advection-dominated flow phenomena, such as in traffic flow, atmospheric flows, and air flow over vehicles, a low-dimensional linear subspace poorly approximates the solution. To address cases such as these, we have developed a fast and accurate physics-informed neural network ROM, namely nonlinear manifold ROM (NM-ROM), which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Our method takes advantage of the existing numerical methods that are used to solve the corresponding full order models. The efficiency is achieved by developing a hyper-reduction technique in the context of the NM-ROM. Numerical results show that neural networks can learn a more efficient latent space representation on advection-dominated data from 1D and 2D Burgers' equations. A speedup of up to 2.6 for 1D Burgers' and a speedup of 11.7 for 2D Burgers' equations are achieved with an appropriate treatment of the nonlinear terms through a hyper-reduction technique. Finally, a posteriori error bounds for the NM-ROMs are derived that take account of the hyper-reduced operators.

LafargeHolcim will implement automation and robotics, artificial intelligence, predictive maintenance and digital twin technologies for its production process. The company is upgrading its production fleet for the future through its'Plants of Tomorrow" program. The program will be rolled out over four years as LafargeHolcim upgrades its technologies in the building materials industry. The company predicts a "Plants of Tomorrow" certified operation will show 15 to 20 percent of operational efficiency gains compared to a conventional cement plant. Among the technologies implemented are predictive operations that can detect abnormal conditions and process anomalies in real-time. This aims to reduce maintenance costs by more than 10 percent and significantly lower energy costs. Digital twins of plants will also be created to optimise training opportunities. Automation and robotics is another important element of the strategy. Unmanned surveillance is being performed for high exposure jobs in the entire plant. Partnering with Swiss start-up Flyability, the company is using drones that allow the frequency of inspections to increase while simultaneously reducing cost and increasing safety for employees by inspecting confined spaces. In addition, the new PACT (Performance and Collaboration) digital tool allows operational decision making from experience-based to data-centric, by combining data from various sources and enabling machine learning applications. LafargeHolcim is currently working on more than 30 pilot projects covering all regions where the company is active. The first integrated cement plant will be at LafargeHolcim's premises in Siggenthal, Switzerland, this plant will test all modules of the'Plants of Tomorrow' program. LafargeHolcim Global Head Cement Manufacturing, Solomon Baumgartner Aviles, said transforming the way we produce cement is one of the focus areas of our digitalisation strategy and the'Plants of Tomorrow' initiative will turn Industry 4.0 into reality at our plants. "These innovative solutions make cement production safer, more efficient and environmentally fit.

The Vatican's Pontifical Academy for Life, which began the year by urging the ethical development and application of artificial intelligence (AI), has announced an effort to use technology to fight world hunger, which has worsened during the pandemic. The Vatican institution, in collaboration with IBM, Microsoft and the UN Food and Agriculture Organization, or FAO, is encouraging governments, nonprofits and corporations to assure that technology is used to feed everyone, and to make farmers' lives more efficient and productive. In its quest to assure the transparent, responsible and inclusive use of AI, the Vatican and FAO are pushing for solutions in agriculture that will benefit not just the well off, but also the poor. "We need to face the biggest challenges on the planet," said John E. Kelly III, executive vice president of IBM. Kelly, who participated in the FAO and Pontifical Academy's Sept. 24 virtual conference announcing the effort against hunger, was one of the signers of the Vatican's call for AI ethics in February. The Vatican's effort to promote ethical AI for social good includes a new program to use digital technology to ensure a more sustainable and efficient global food supply.

SFU researchers have received $300,000 in funding from Innovate BC's Ignite Program to develop technology that allows farmers to grow more food with fewer synthetic pesticides. The research project commenced earlier this year and involves a collaboration with Vancouver-based agtech company Terramera's Actigate technology platform, which aims to reduce global synthetic pesticide use by 80 per cent by 2030. "The growing world population needs more food and we need to grow food that is environmentally sustainable," says SFU computing science professor Martin Ester, who is the principal investigator for the project. "One approach is to develop organic pesticides that are as effective as chemical pesticides, but less harmful to the environment." Distinguished for his research in the fields of data mining and machine learning, Ester was named a Royal Society of Canada (RSC) Fellow last year.

Data mining is a popular term used by machine learning developers. The technique refers to extracting meaningful information from the massive dataset. For the aspiring data scientists, it is important to be familiar with data mining techniques. Here are the top data mining techniques that are used by Data Science and Machine Learning experts. Association rule learning is a standard rule-based ML technique used to discover the relationship between variables in datasets.

As they carry great potential for modeling complex interactions, graph neural network (GNN)-based methods have been widely used to predict quantum mechanical properties of molecules. Most of the existing methods treat molecules as molecular graphs in which atoms are modeled as nodes. They characterize each atom's chemical environment by modeling its pairwise interactions with other atoms in the molecule. Although these methods achieve a great success, limited amount of works explicitly take many-body interactions, i.e., interactions between three and more atoms, into consideration. In this paper, we introduce a novel graph representation of molecules, heterogeneous molecular graph (HMG) in which nodes and edges are of various types, to model many-body interactions. HMGs have the potential to carry complex geometric information. To leverage the rich information stored in HMGs for chemical prediction problems, we build heterogeneous molecular graph neural networks (HMGNN) on the basis of a neural message passing scheme. HMGNN incorporates global molecule representations and an attention mechanism into the prediction process. The predictions of HMGNN are invariant to translation and rotation of atom coordinates, and permutation of atom indices. Our model achieves state-of-the-art performance in 9 out of 12 tasks on the QM9 dataset.