Persistent Memory (PMEM), also known as Non-Volatile Memory (NVM), can deliver higher density and lower cost per bit when compared with DRAM. Its main drawback is that it is typically slower than DRAM. On the other hand, DRAM has scalability problems due to its cost and energy consumption. Soon, PMEM will likely coexist with DRAM in computer systems but the biggest challenge is to know which data to allocate on each type of memory. This paper describes a methodology for identifying and characterizing application objects that have the most influence on the application's performance using Intel Optane DC Persistent Memory. In the first part of our work, we built a tool that automates the profiling and analysis of application objects. In the second part, we build a machine learning model to predict the most critical object within large-scale graph-based applications. Our results show that using isolated features does not bring the same benefit compared to using a carefully chosen set of features. By performing data placement using our predictive model, we can reduce the execution time degradation by 12\% (average) and 30\% (max) when compared to the baseline's approach based on LLC misses indicator.

Purely data-driven deep neural networks (DNNs) applied to physical engineering systems can infer relations that violate physics laws, thus leading to unexpected consequences. To address this challenge, we propose a physics-model-based DNN framework, called Phy-Taylor, that accelerates learning compliant representations with physical knowledge. The Phy-Taylor framework makes two key contributions; it introduces a new architectural Physics-compatible neural network (PhN), and features a novel compliance mechanism, we call {\em Physics-guided Neural Network Editing\}. The PhN aims to directly capture nonlinearities inspired by physical quantities, such as kinetic energy, potential energy, electrical power, and aerodynamic drag force. To do so, the PhN augments neural network layers with two key components: (i) monomials of Taylor series expansion of nonlinear functions capturing physical knowledge, and (ii) a suppressor for mitigating the influence of noise. The neural-network editing mechanism further modifies network links and activation functions consistently with physical knowledge. As an extension, we also propose a self-correcting Phy-Taylor framework that introduces two additional capabilities: (i) physics-model-based safety relationship learning, and (ii) automatic output correction when violations of safety occur. Through experiments, we show that (by expressing hard-to-learn nonlinearities directly and by constraining dependencies) Phy-Taylor features considerably fewer parameters, and a remarkably accelerated training process, while offering enhanced model robustness and accuracy.

We demonstrate the adaption of three established methods to the field of surrogate machine learning model development. These methods are data augmentation, custom loss functions and transfer learning. Each of these methods have seen widespread use in the field of machine learning, however, here we apply them specifically to surrogate machine learning model development. The machine learning model that forms the basis behind this work was intended to surrogate a traditional engineering model used in the UK nuclear industry. Previous performance of this model has been hampered by poor performance due to limited training data. Here, we demonstrate that through a combination of additional techniques, model performance can be significantly improved. We show that each of the aforementioned techniques have utility in their own right and in combination with one another. However, we see them best applied as part of a transfer learning operation. Five pre-trained surrogate models produced prior to this research were further trained with an augmented dataset and with our custom loss function. Through the combination of all three techniques, we see an improvement of at least $38\%$ in performance across the five models.

The FAIR Guiding Principles aim to improve the findability, accessibility, interoperability, and reusability of digital content by making them both human and machine actionable. However, these principles have not yet been broadly adopted in the domain of machine learning-based program analyses and optimizations for High-Performance Computing (HPC). In this paper, we design a methodology to make HPC datasets and machine learning models FAIR after investigating existing FAIRness assessment and improvement techniques. Our methodology includes a comprehensive, quantitative assessment for elected data, followed by concrete, actionable suggestions to improve FAIRness with respect to common issues related to persistent identifiers, rich metadata descriptions, license and provenance information. Moreover, we select a representative training dataset to evaluate our methodology. The experiment shows the methodology can effectively improve the dataset and model's FAIRness from an initial score of 19.1% to the final score of 83.0%.

Global geo-data and exploration company Fugro has opened its largest remote operations centre to date, a multi-million-dollar multi-user facility in Perth's central business district called the Australian Space Automation, Artificial Intelligence and Robotics Control Complex, or SpAARC. The opening on Tuesday, November 2, was attended by WA Deputy Premier Roger Cook and the head of the Australian Space Agency (ASA), Enrico Palermo. SpAARC makes available a world-leading commercial facility where users ranging from small sole operators in the space sector to government and defence agencies can demonstrate and test remote robotic capabilities to deploy into space and other remote environments. "The opening itself is a milestone," said Dawn McIntosh, Space Systems Director at Fugro Australia. "We're building out a capability so you can come in and we've got content you can build off of, or you can do your own pipeline and end-to-end solution. The breadth of the type of mission you can bring in isn't dictated by the facility itself."

SkySpecs is simplifying renewable energy asset management by offering purpose-built technologies and services that help our customers deliver industry-leading productivity, efficiency, and returns. Every day we help our customers unlock the power of their data so they can make confident, informed decisions. Our team brings deep industry experience and a willingness to get our hands dirty to first understand and then solve customer problems on the ground. SkySpecs launched the world's first completely autonomous blade inspection product in 2016 with a custom designed drone system. Since then, SkySpecs has inspected over 90% of the wind turbines in the US and we've expanded globally, becoming the world leader in understanding the health of turbine blades.

From chemicals to energy, artificial intelligence (AI) is already showing just how far it can help achieve global sustainability targets across different industrial sectors. One example is Petroliam Nasional Berhad (PETRONAS), has committed to achieving net-zero carbon emissions by 2050. For the Malaysian oil and gas multinational, plant reliability is key to achieving its sustainability goals. PETRONAS identified that early insight into impending equipment failure would enable plant operators to fix equipment proactively before small issues become bigger problems. Proof of concept came via a pilot project in their corporate cloud on Microsoft Azure at four upstream and two downstream units.

Sustainability and digitisation are like twins; they go hand in hand. They both have the potential to change the way businesses operate and the way people work -- at any role, and any level. In particular, artificial intelligence (AI) is a key tenet of both sustainability and digitalisation, empowering companies with real-time visibility and a myriad of insights as they take the winding path towards net zero. However, time waits for no one, and the challenges of becoming sustainable will only multiply if businesses don't start deploying AI alongside their talented humans right now. After all, the clock is ticking: the IPCC notes we must halve emissions by 2030 to stop irreversible climate change. Let's be clear: clean energy and efficient energy management are key to attacking the climate crisis.

In an article published in the journal Foods, researchers tested a CNN algorithm to assess its potential for olive classification for industrial purposes, specifically its potential integration and sorting performance evaluation. A staple of the Mediterranean diet is olive oil. Italy produces extra virgin olive oil (EVOO), which is well-known around the globe due to its high nutritional content. Therefore, it is critical to process the harvested olives and to take extra care during mechanical harvesting to prevent internal damage, which might impair the quality of the finished product, and to preserve the chemical and sensory quality criteria of EVOO. Optoelectronic equipment is often used to improve batch quality and the sorting and grading of items.

Making the countless numbers of N95 masks that have protected millions of Americans from COVID requires a process that not only demands attention to detail but also requires lots of energy. Many of the materials in these masks are produced by a technique called melt blowing, in which tiny plastic fibers are spun at high temperatures that necessitate the use of a lot of energy. The process is also used for other products like furnace filters, coffee filters and diapers. Thanks to a new computational effort being pioneered by the U.S. Department of Energy's (DOE) Argonne National Laboratory in conjunction with 3M and supported by the DOE'S High Performance Computing for Energy Innovation (HPC4EI) program, researchers are finding new ways to dramatically reduce the amount of energy required for melt blowing the materials needed in N95 masks and other applications. Currently, the process used to create a nozzle to spin nonwoven materials produces a very high-quality product, but it is quite energy intensive.