Chemicals


Health Catalyst raises $100 million for health care analytics

#artificialintelligence

The artificial intelligence (AI) in health care market is set to top $34 billion by 2025, according to some estimates -- and it's no real wonder why. One startup that's successfully maintained pole position is Health Catalyst, a Salt Lake City, Utah-based health care big data company founded in 2009 by Steven Barlow and Thomas Burton. It aims to drive clinical and operational performance improvements in state and regional health plan providers, physician groups, and extended care facilities through its suite of analytics apps. And it's raising capital to help further progress toward that goal. Health Catalyst today announced that it has secured $100 million in series F equity and debt financing led by health care investment firm OrbiMed, with participation from existing partners Sequoia Capital, Norwest Venture Partners, Sands Capital Ventures, UPMC Enterprises, and Kaiser Permanente Ventures.


Artificial Intelligence: A New Reality for Chemical Engineers - Chemical Engineering Page 1

#artificialintelligence

As in many other sectors, artificial intelligence (AI) technologies are beginning to emerge in the chemical process industries (CPI). While AI-assisted solutions, and other associated technologies, such as robotic process automation (RPA), Internet of Things (IoT), automated drones and quantum computing, are still relatively new for many CPI applications, developers and users alike are realizing their potential benefits for expediting research and development (R&D), predictive maintenance, process optimization and more. Within its Smart Operations initiative, Henkel AG & Co. KGaA (Düsseldorf, Germany; www.henkel.com) is utilizing AI capabilities in its global process operations and supply chain. "We use AI to run efficient analyses of complex data arrays for achieving higher production performance, quick product innovation and scaleup for our self-adjusting production systems," explains Sandeep Sreekumar, global head of Adhesive Digital Operations at Henkel. "Our focus is not only on collecting internal manufacturing data, but also on actively working with customers on data collection opportunities during product usage to make improvements and adjust to changing customer needs," says Sreekumar.


Mountaineer develops new model for environmental and energy uses

#artificialintelligence

A new machine-learning model developed by a West Virginia University student has potential applications in the energy, environmental and health-care fields. The model, which can be used to predict adsorption energies -- i.e., adhesive capabilities in gold nanoparticles -- was developed by Gihan Panapitiya, a doctoral physics student from Sri Lanka. Gold nanoparticles have historically been used by artists to bring out vibrant colors via their interaction with light. Now they are increasingly used in high-technology applications such as electronic conductors and others. "Machine learning recently came into the spotlight, and we wanted to do something linking machine learning with gold nanoparticles as catalysts," Panapitiya said.


Mountaineer develops new model for environmental and energy uses – Tech Check News

#artificialintelligence

A new machine-learning model developed by a West Virginia University student has the potential for energy, environmental and even healthcare applications. The model, which can be used to predict the adsorption energies, i.e. adhesive capabilities in gold nanoparticles, was developed by Gihan Panapitiya, a doctoral physics student from Sri Lanka. Gold nanoparticles have historically been used by artists to bring out vibrant colors via their interaction with light. Now they are increasingly used in high technology applications, electronic conductors and others. "Machine learning recently came into the spotlight, and we wanted to do something linking machine learning with gold nanoparticles as catalysts," he said.


Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning

Science

To demonstrate the viability of our method, we predicted reaction outcomes with substrate combinations and catalysts different from the training data and simulated a situation in which highly selective reactions had not been achieved. In the first demonstration, a model was constructed by using support vector machines and validated with three different external test sets. The first test set evaluated the ability of the model to predict the selectivity of only reactions forming new products with catalysts from the training set. The model performed well, with a mean absolute deviation (MAD) of 0.161 kcal/mol. Next, the same model was used to predict the selectivity of an external test set of catalysts with substrate combinations from the training set.


Podium Data becomes Qlik Data Catalyst

ZDNet

After the acquisition of Podium Data by Qlik last July, we knew a couple of things: consolidation in the analytics market was continuing, and interest in data governance/data management was increasing, even for self-service BI vendors like Qlik. What we didn't know, though, was what would happen to the Podium team and product post-acquisition. The Podium team is apparently intact, now constituting a distinct Enterprise Data Management team at Qlik, with its own P&L. Paul Barth, Podium's erstwhile CEO, is now Managing Director of that group, and carries that P&L responsibility. And in a discussion with both Barth and Joe DosSantos, Qlik's new Global Head of Enterprise Data Strategy (and formerly a Podium Data customer at TD Bank), I found out how the product has evolved as well.


Looking for a Job? Meet Your Machine Learning Interviewer JPMorgan Chase & Co.

#artificialintelligence

This article was originally published by Ozy. In 2016, Houston's petrochemical industry had countless job positions that were unfilled. And at the same time, a number of the city's residents were looking for work. So, how was Houston going to fix this? In an effort to help match eligible candidates with open positions, private companies began to step in.


The Dawn of Life in a $5 Toaster Oven - Issue 68: Context

Nautilus

God might just as well have begun with a toaster oven. A few years ago at a yard sale, Nicholas Hud spotted a good candidate: A vintage General Electric model, chrome-plated with wood-grain panels, nestled in an old yellowed box, practically unused. The perfect appliance for cooking up the chemical precursors of life, he thought. He bought it for $5. At home in his basement, with the help of his college-age son, he cut a rectangular hole in the oven's backside, through which an automated sliding table (recycled from an old document scanner) could move a tray of experiments in and out. He then attached a syringe pump to some inkjet printer parts, and rigged the system to periodically drip water onto the tray.


System lets A.I. play chemist to save months of work - Futurity

#artificialintelligence

You are free to share this article under the Attribution 4.0 International license. A new system combines artificial neural networks with infrared thermal imaging to control and interpret chemical reactions with precision and speed that far outpace conventional methods. Machine learning algorithms can predict stock market fluctuations, control complex manufacturing processes, enable navigation for robots and driverless vehicles, and much more. Now, researchers are tapping a new set of capabilities in this field of artificial intelligence with their new technique. "This system can reduce the decision-making process about certain chemical manufacturing processes from one year to a matter of weeks…" The researchers developed and tested the new method on microreactors that allow chemical discoveries to take place quickly and with far less environmental waste than standard large-scale reactions.


Searching for the best conditions

Science

The vastness of the archival chemistry literature is both a blessing and a curse. The reaction that you're looking for is probably in there, provided you take enough time to search for it. Gao et al. trained a neural network model on 10 million known reactions to speed up this process. Specifically, the model was charged with predicting a catalyst, reagents, solvents, and temperature to achieve a given transformation. When tested, the model's top-10 list of suggestions produced a close match to actual conditions nearly 70% of the time, with a 20 C error margin in temperature.