Capturing the microscopic interactions that determine molecular reactivity poses a challenge across the physical sciences. Even a basic understanding of the underlying reaction mechanisms can substantially accelerate materials and compound design, including the development of new catalysts or drugs. Given the difficulties routinely faced by both experimental and theoretical investigations that aim to improve our mechanistic understanding of a reaction, recent advances have focused on data-driven routes to derive structure-property relationships directly from high-throughput screens. However, even these high-quality, high-volume data are noisy, sparse and biased -- placing them in a regime where machine-learning is extremely challenging. Here we show that a statistical approach based on deep filtering of nonlinear feature networks results in physicochemical models that are more robust, transparent and generalize better than standard machine-learning architectures. Using diligent descriptor design and data post-processing, we exemplify the approach using both literature and fresh data on asymmetric catalytic hydrogenation, Palladium-catalyzed cross-coupling reactions, and drug-drug synergy. We illustrate how the sparse models uncovered by the filtering help us formulate physicochemical reaction ``pharmacophores'', investigate experimental bias and derive strategies for mechanism detection and classification.

The intent of the current study is to analyze the LPG usage consumption and forecasting, by leveraging Time Series, the values to predict the LPG usage – by giving inputs area-wise, dealer-wise, and season-wise on a weekly, monthly, and yearly basis. This case study leverages AI and Machine Learning to predict LPG usage by using a concept mechanism like a trolley enabled with sensors. These trolleys capture the weights of the cylinders and transmit continuous updates on weight of the cylinder, gas leakage occurrences and ambient temperature to the dealers and manufacturers. Qualetics provides a solution that captures the above-mentioned data points continuously and allows the possibility of real-time streaming analytics of the LPG gas usage as well as advanced analytics on data captured over long periods of time. To know how Qualetics gives an effective solution, download the full usecase.

Machine learning (ML) methods reach ever deeper into quantum chemistry and materials simulation, delivering predictive models of interatomic potential energy surfaces1,2,3,4,5,6, molecular forces7,8, electron densities9, density functionals10, and molecular response properties such as polarisabilities11, and infrared spectra12. Large data sets of molecular properties calculated from quantum chemistry or measured from experiment are equally being used to construct predictive models to explore the vast chemical compound space13,14,15,16,17 to find new sustainable catalyst materials18, and to design new synthetic pathways19. Recent research has explored the potential role of machine learning in constructing approximate quantum chemical methods20, as well as predicting MP2 and coupled cluster energies from Hartree–Fock orbitals21,22. There have also been approaches that use neural networks as a basis representation of the wavefunction23,24,25. Most existing ML models have in common that they learn from quantum chemistry to describe molecular properties as scalar, vector, or tensor fields26,27.

Edge computing is helping Newcrest Mining improve throughput and reduce downtime in Australia's largest underground block cave mine, the Cadia Valley gold mine in New South Wales. Newcrest Mining won the best Primary Industry Project in our 2019 IoT Awards for the project, which uses machine learning to optimise the level of crushed ore in bins, preventing downtime. Now Microsoft and its partner Insight Enterprises have released details about the solution and its benefits. The solution is improving productivity, reducing downtime and increasing throughput, Newcrest Mining CIO Gavin Wood stated in a press release. And the company has seen a return on investment within three months of starting to use the solution.

Environmentally benign methods for the industrial production of chemicals are urgently needed. LMU researchers recently described such a procedure for the synthesis of formaldehyde, and have now improved it with the aid of machine learning. Formaldehyde is one of the most important feedstocks employed in the chemical industry, and serves as the point of departure for the synthesis of many more complex chemical products. Industrial production of formaldehyde is currently based on a large-scale procedure which consumes fossil fuels and requires a high energy input. More efficient and more sustainable modes of synthesis are therefore urgently needed, which could make a significant contribution to the mitigation of climate.

We present a simulation framework for spunbond processes and use a design of experiments to investigate the cause-and-effect-relations of process and material parameters onto the fiber laydown on a conveyor belt. The virtual experiments are analyzed by a blocked neural network. This forms the basis for the prediction of the fiber laydown characteristics and enables a quick ranking of the significance of the influencing effects. We conclude our research by an analysis of the nonlinear cause-and-effect relations.

Opportunities for digital technologies implementation, including implementation of artificial intelligence, are being implemented in the mining sector. Technologies help to save money and to solve problems that humans can't solve. McKinseyestimates that by 2035, the use of data analysis and digital technologies will help coal, iron ore, and copper producers save between $290 billion and $390 billion annually. Digital technologies and artificial intelligence enable companies to extract minerals in hard-to-reach places and under extreme weather conditions. This article first appeared in Mining Review Africa Issue 10, 2019 Read the full digimag here or subscribe to receive a print copy here This means that in an environment when mineral resources are becoming increasingly scarce, it is possible to develop deposits that used to be inaccessible, to do it without endangering lives of employees and to minimize human errors that often lead to costly mistakes.

Here is an unavoidable truth. Resource extraction is hard physical work. And perhaps this is the very reason modern investors have wandered away from mining--whether or not it's to their benefit. New AI methods may change that. Just like society, many investors today are overlooking the connection between the products we use and the source of the materials to make them. And yet it's still true that "if you cannot grow it, you have to mine it."

Agricultural fields are no less than a battlefield. Irrespective of terrain, geography and type, crops have to compete against scores of different weeds, species of hungry insects, nematodes and a broad array of diseases. Weeds, or invasive plants, aggressively compete for soil nutrients, light and water, posing a serious threat to agricultural production and biodiversity. Weeds directly and indirectly result in tremendous losses to the farm sector, which convert to billions each year worldwide. To combat these challenges, the farm sector is looking at Artificial Intelligence (AI) based solutions.

In processing and manufacturing industries, there has been a large push to produce higher quality products and ensure maximum efficiency of processes. This requires approaches to effectively detect and resolve disturbances to ensure optimal operations. While the control system can compensate for many types of disturbances, there are changes to the process which it still cannot handle adequately. It is therefore important to further develop monitoring systems to effectively detect and identify those faults such that they can be quickly resolved by operators. In this paper, a novel probabilistic fault detection and identification method is proposed which adopts a newly developed deep learning approach using Bayesian recurrent neural networks (BRNNs) with variational dropout. The BRNN model is general and can model complex nonlinear dynamics. Moreover, compared to traditional statistic-based data-driven fault detection and identification methods, the proposed BRNN-based method yields uncertainty estimates which allow for simultaneous fault detection of chemical processes, direct fault identification, and fault propagation analysis. The outstanding performance of this method is demonstrated and contrasted to (dynamic) principal component analysis, which are widely applied in the industry, in the benchmark Tennessee Eastman process (TEP) and a real chemical manufacturing dataset.