Zephyr, a solar-powered unmanned aerial vehicle (UAV) built by Airbus, was used to deliver next generation wireless internet, as part of a test flight over Arizona. Airbus was testing the'High Altitude Platform Station' (HAPS), onboard the British-built UAV, as part of an 18-day flight in the stratosphere, 76,100ft above the surface. The test was in partnership with Japanese mobile operator, NTT DOCOMO, and could one day lead to super-fast broadband in remote areas, without the need to send a fleet of satellites into low Earth orbit, according to Airbus. It carried an onboard radio transmitter that let it provide a datalink to simulate future systems that would send internet signals between the UAV and a computer. The successful test could pave the way for a fleet of Zephyr aircraft delivering 5G and 6G mobile internet to the most remote parts of the planet, or providing a short-term signal boost during a major event in a densely populated area, Airbus says.

We describe a novel metric-based learning approach that introduces a multimodal framework and uses deep audio and geophone encoders in siamese configuration to design an adaptable and lightweight supervised model. This framework eliminates the need for expensive data labeling procedures and learns general-purpose representations from low multisensory data obtained from omnipresent sensing systems. These sensing systems provide numerous applications and various use cases in activity recognition tasks. Here, we intend to explore the human footstep movements from indoor environments and analyze representations from a small self-collected dataset of acoustic and vibration-based sensors. The core idea is to learn plausible similarities between two sensory traits and combining representations from audio and geophone signals. We present a generalized framework to learn embeddings from temporal and spatial features extracted from audio and geophone signals. We then extract the representations in a shared space to maximize the learning of a compatibility function between acoustic and geophone features. This, in turn, can be used effectively to carry out a classification task from the learned model, as demonstrated by assigning high similarity to the pairs with a human footstep movement and lower similarity to pairs containing no footstep movement. Performance analyses show that our proposed multimodal framework achieves a 19.99\% accuracy increase (in absolute terms) and avoided overfitting on the evaluation set when the training samples were increased from 200 pairs to just 500 pairs while satisfactorily learning the audio and geophone representations. Our results employ a metric-based contrastive learning approach for multi-sensor data to mitigate the impact of data scarcity and perform human movement identification with limited data size.

Application of machine learning in earth sciences is the use of computer systems to classify, cluster, identify and analyze vast and complex data in earth science study, for example, geological mapping, gas leakage detection and geological features identification. Machine learning (ML) is a type of Artificial Intelligence (AI) that allows computer systems to interpret data while eliminating the need for explicit instructions and programming. The Earth system can be subdivided into four major components including the solid earth, atmosphere, hydrosphere and biosphere[3]. A variety of algorithms may be applied depending on the nature of the earth science exploration. Some algorithms may perform significantly better than others for particular objectives. For example, Convolutional Neural Networks (CNN) are good at interpreting images, Artificial Neural Network (ANN) performs well in soil classification[4] but more computationally expensive to train than Support Vector Machine (SVM) learning.

We demonstrate that extremely low resolution quantized (nominally 5-state) synapses with large stochastic variations in Domain Wall (DW) position can be both energy efficient and achieve reasonably high testing accuracies compared to Deep Neural Networks (DNNs) of similar sizes using floating precision synaptic weights. Specifically, voltage controlled DW devices demonstrate stochastic behavior as modeled rigorously with micromagnetic simulations and can only encode limited states; however, they can be extremely energy efficient during both training and inference. We show that by implementing suitable modifications to the learning algorithms, we can address the stochastic behavior as well as mitigate the effect of their low-resolution to achieve high testing accuracies. In this study, we propose both in-situ and ex-situ training algorithms, based on modification of the algorithm proposed by Hubara et al. [1] which works well with quantization of synaptic weights. We train several 5-layer DNNs on MNIST dataset using 2-, 3- and 5-state DW device as synapse. For in-situ training, a separate high precision memory unit is adopted to preserve and accumulate the weight gradients, which are then quantized to program the low precision DW devices. Moreover, a sizeable noise tolerance margin is used during the training to address the intrinsic programming noise. For ex-situ training, a precursor DNN is first trained based on the characterized DW device model and a noise tolerance margin, which is similar to the in-situ training. Remarkably, for in-situ inference the energy dissipation to program the devices is only 13 pJ per inference given that the training is performed over the entire MNIST dataset for 10 epochs.

Artificial Intelligence (AI) algorithms are increasingly providing decision making and operational support across multiple domains. AI includes a wide library of algorithms for different problems. One important notion for the adoption of AI algorithms into operational decision process is the concept of assurance. The literature on assurance, unfortunately, conceals its outcomes within a tangled landscape of conflicting approaches, driven by contradicting motivations, assumptions, and intuitions. Accordingly, albeit a rising and novel area, this manuscript provides a systematic review of research works that are relevant to AI assurance, between years 1985 - 2021, and aims to provide a structured alternative to the landscape. A new AI assurance definition is adopted and presented and assurance methods are contrasted and tabulated. Additionally, a ten-metric scoring system is developed and introduced to evaluate and compare existing methods. Lastly, in this manuscript, we provide foundational insights, discussions, future directions, a roadmap, and applicable recommendations for the development and deployment of AI assurance.

AI Researcher, Cognitive Technologist Inventor - AI Thinking, Think Chain Innovator - AIOT, XAI, Autonomous Cars, IIOT Founder Fisheyebox Spatial Computing Savant, Transformative Leader, Industry X.0 Practitioner In order to stabilize #climatechange, we need to hold Earth's temperature at 1.5 C above pre-industrial levels. This means we need to halve global greenhouse gas emissions by 2030 and reach net zero before 2050. The world requires larger, more positive transformational changes than a pandemic to address climate change and meet its targets. At the same time, as we progress into 2022 and 2030 edges closer, the need for fast, scalable change only grows. Digitalization is an enabling technology representing a fast, scalable tool to help address climate change.

This paper focuses on learning rate analysis of Nystr\"{o}m regularization with sequential sub-sampling for $\tau$-mixing time series. Using a recently developed Banach-valued Bernstein inequality for $\tau$-mixing sequences and an integral operator approach based on second-order decomposition, we succeed in deriving almost optimal learning rates of Nystr\"{o}m regularization with sequential sub-sampling for $\tau$-mixing time series. A series of numerical experiments are carried out to verify our theoretical results, showing the excellent learning performance of Nystr\"{o}m regularization with sequential sub-sampling in learning massive time series data. All these results extend the applicable range of Nystr\"{o}m regularization from i.i.d. samples to non-i.i.d. sequences.

In this work we aim to mimic the human ability to acquire the intuition to estimate the performance of a design from visual inspection and experience alone. We study the ability of convolutional neural networks to predict static and dynamic properties of cantilever beams directly from their raw cross-section images. Using pixels as the only input, the resulting models learn to predict beam properties such as volume maximum deflection and eigenfrequencies with 4.54% and 1.43% Mean Average Percentage Error (MAPE) respectively, compared to the Finite Element Analysis (FEA) approach. Training these models doesn't require prior knowledge of theory or relevant geometric properties, but rather relies solely on simulated or empirical data, thereby making predictions based on "experience" as opposed to theoretical knowledge. Since this approach is over 1000 times faster than FEA, it can be adopted to create surrogate models that could speed up the preliminary optimization studies where numerous consecutive evaluations of similar geometries are required. We suggest that this modeling approach would aid in addressing challenging optimization problems involving complex structures and physical phenomena for which theoretical models are unavailable.

The need for a rapid transition to clean energy is enabling new developments in the renewable sector. Businesses and industries are moving towards renewable energy to reduce emissions, lower energy costs, and improve eco-friendliness. The major trends in the renewable sector include digitization, energy-efficient integrations, and solutions that overcome the intermittency in renewable energy production. For these reasons, the use of big data, artificial intelligence (AI), and the internet of energy (IoE) are emerging as popular trends in addition to innovations in renewable energy sources. Although renewable energies such as solar, wind, and hydroelectricity have been around for a long time, recent rapid innovations make these some of the most trending technologies. Moreover, they dominate the industry due to their competitive advantages. Relatively newer areas of research in the renewable sector include energy from green hydrogen and water energy forms such as tidal, wave, and ocean currents. For this in-depth research on the Top Renewable Energy Trends & Startups, we analyzed a sample of 5 152 global startups and scaleups. The result of this research is data-driven innovation intelligence that improves strategic decision-making by giving you an overview of emerging technologies & startups in the renewable energy industry. These insights are derived by working with our Big Data & Artificial Intelligence-powered StartUs Insights Discovery Platform, covering 2 093 000 startups & scaleups globally.

While significant progress has been made towards explaining black-box machine-learning (ML) models, there is still a distinct lack of diagnostic tools that elucidate the spatial behaviour of ML models in terms of predictive skill and variable importance. This contribution proposes spatial prediction error profiles (SPEPs) and spatial variable importance profiles (SVIPs) as novel model-agnostic assessment and interpretation tools for spatial prediction models with a focus on prediction distance. Their suitability is demonstrated in two case studies representing a regionalization task in an environmental-science context, and a classification task from remotely-sensed land cover classification. In these case studies, the SPEPs and SVIPs of geostatistical methods, linear models, random forest, and hybrid algorithms show striking differences but also relevant similarities. Limitations of related cross-validation techniques are outlined, and the case is made that modelers should focus their model assessment and interpretation on the intended spatial prediction horizon. The range of autocorrelation, in contrast, is not a suitable criterion for defining spatial cross-validation test sets. The novel diagnostic tools enrich the toolkit of spatial data science, and may improve ML model interpretation, selection, and design.