Methane is a potent greenhouse gas that is being added to the atmosphere through both natural processes and human activities, such as energy production and agriculture. To predict the impacts of human emissions, researchers need a complete picture of the atmosphere's methane cycle. They need to know the size of the inputs--both natural and human--as well as the outputs. They also need to know how long methane resides in the atmosphere. For more information see the IDTechEx report on Smart City Opportunities: Infrastructure, Systems, Materials 2019-2029.

To predict the impacts of human emissions, researchers need a complete picture of the atmosphere's methane cycle. They need to know the size of the inputs -- both natural and human -- as well as the outputs. They also need to know how long methane resides in the atmosphere. To help develop this understanding, Tom Weber, an assistant professor of earth and environmental sciences at the University of Rochester; undergraduate researcher Nicola Wiseman '18, now a graduate student at the University of California, Irvine; and their colleague Annette Kock at the GEOMAR Helmholtz Centre for Ocean Research in Germany, used data science to determine how much methane is emitted from the ocean into the atmosphere each year. Their results, published in the journal Nature Communications, fill a longstanding gap in methane cycle research and will help climate scientists better assess the extent of human perturbations.

On 10th of June, 2019, twenty-two AI researchers, including Andrew Ng and Yoshua Bengio, published a paper on how to tackle climate change with machine learning. I really enjoyed reading it and I am convinced that the paper as well as the climatechange.ai For that reason i created a series of blog posts and videos which provide a dense summary, listing many of the proposed solutions and linking research work as well as ongoing projects. In the big picture, all solutions aim to reduce greenhouse gas emissions. As my contribution to the global #ClimateStrike week from September 20th to 27th, i will post one chapter (video and blog post) on every working day.

AI heralds a step-change in the performance and capability of wireless networks and other critical infrastructures. However, it may also cause irreversible environmental damage due to their high energy consumption. Here, we address this challenge in the context of 5G and beyond, where there is a complexity explosion in radio resource management (RRM). On the one hand, deep reinforcement learning (DRL) provides a powerful tool for scalable optimization for high dimensional RRM problems in a dynamic environment. On the other hand, DRL algorithms consume a high amount of energy over time and risk compromising progress made in green radio research. This paper reviews and analyzes how to achieve green DRL for RRM via both architecture and algorithm innovations. Architecturally, a cloud based training and distributed decision-making DRL scheme is proposed, where RRM entities can make lightweight deep local decisions whilst assisted by on-cloud training and updating. On the algorithm level, compression approaches are introduced for both deep neural networks and the underlying Markov Decision Processes, enabling accurate low-dimensional representations of challenges. To scale learning across geographic areas, a spatial transfer learning scheme is proposed to further promote the learning efficiency of distributed DRL entities by exploiting the traffic demand correlations. Together, our proposed architecture and algorithms provide a vision for green and on-demand DRL capability.

Learned representations of source code enable various software developer tools, e.g., to detect bugs or to predict program properties. At the core of code representations often are word embeddings of identifier names in source code, because identifiers account for the majority of source code vocabulary and convey important semantic information. Unfortunately, there currently is no generally accepted way of evaluating the quality of word embeddings of identifiers, and current evaluations are biased toward specific downstream tasks. This paper presents IdBench, the first benchmark for evaluating to what extent word embeddings of identifiers represent semantic relatedness and similarity. The benchmark is based on thousands of ratings gathered by surveying 500 software developers. We use IdBench to evaluate state-of-the-art embedding techniques proposed for natural language, an embedding technique specifically designed for source code, and lexical string distance functions, as these are often used in current developer tools. Our results show that the effectiveness of embeddings varies significantly across different embedding techniques and that the best available embeddings successfully represent semantic relatedness. On the downside, no existing embedding provides a satisfactory representation of semantic similarities, e.g., because embeddings consider identifiers with opposing meanings as similar, which may lead to fatal mistakes in downstream developer tools. IdBench provides a gold standard to guide the development of novel embeddings that address the current limitations.

Despite an ever growing literature on reinforcement learning algorithms and applications, much less is known about their statistical inference. In this paper, we investigate the large sample behaviors of the Q-value estimates with closed-form characterizations of the asymptotic variances. This allows us to efficiently construct confidence regions for Q-value and optimal value functions, and to develop policies to minimize their estimation errors. This also leads to a policy exploration strategy that relies on estimating the relative discrepancies among the Q estimates. Numerical experiments show superior performances of our exploration strategy than other benchmark approaches.

October 14, 2019 A BSTRACT Expressivity is one of the most significant issues in assessing neural networks. In this paper, we provide a quantitative analysis of the expressivity from dynamic models, where Hilbert space is employed to analyze its convergence and criticality. From the feature mapping of several widely used activation functions made by Hermite polynomials, We found sharp declines or even saddle points in the feature space, which stagnate the information transfer in deep neural networks, then present an activation function design based on the Hermite polynomials for better utilization of spatial representation. Moreover, we analyze the information transfer of deep neural networks, emphasizing the convergence problem caused by the mismatch between input and topological structure. We also study the effects of input perturbations and regularization operators on critical expressivity. Finally, we verified the proposed method by multivariate time series prediction. The results show that the optimized DeepESN provides higher predictive performance, especially for long-term prediction. Our theoretical analysis reveals that deep neural networks use spatial domains for information representation and evolve to the edge of chaos as depth increases. In actual training, whether a particular network can ultimately arrive that depends on its ability to overcome convergence and pass information to the required network depth. K eywords Deep neural networks; expressivity; criticality theory; convergence; activation function; Hilbert transform 1 Introduction Deep neural networks (DNNs) have achieved outstanding performance in many fields, from the automatic translation to speech and image recognition [1, 2].

Knowledge about frequency and location of snow avalanche activity is essential for forecasting and mapping of snow avalanche hazard. Traditional field monitoring of avalanche activity has limitations, especially when surveying large and remote areas. In recent years, avalanche detection in Sentinel-1 radar satellite imagery has been developed to overcome this monitoring problem. Current state-of-the-art detection algorithms, based on radar signal processing techniques, have highly varying accuracy that is on average much lower than the accuracy of visual detections from human experts. To reduce this gap, we propose a deep learning architecture for detecting avalanches in Sentinel-1 radar images. We trained a neural network on 6345 manually labelled avalanches from 117 Sentinel-1 images, each one consisting of six channels with backscatter and topographical information. Then, we tested the best network configuration on one additional SAR image. Comparing to the manual labelling (the gold standard), we achieved an F1 score above 66%, while the state-of-the-art detection algorithm produced an F1 score of 38%. A visual interpretation of the network's results shows that it only fails to detect small avalanches, while it manages to detect some that were not labelled by the human expert.

Dynamical system models (including RNNs) often lack the ability to adapt the sequence generation or prediction to a given context, limiting their real-world application. In this paper we show that hierarchical multi-task dynamical systems (MTDSs) provide direct user control over sequence generation, via use of a latent code $\mathbf{z}$ that specifies the customization to the individual data sequence. This enables style transfer, interpolation and morphing within generated sequences. We show the MTDS can improve predictions via latent code interpolation, and avoid the long-term performance degradation of standard RNN approaches.

There's no getting around the fact that oil and gas plays a critical role in the global energy infrastructure. While renewable technologies have made remarkable progress, we still rely on fuels like oil and gas to power our vehicles, to keep our lights on and to move goods and people around the world. Therefore, problems in the industry -- like a talent crisis -- can have serious global consequences. If global energy infrastructure and efficiency is negatively impacted, so too will be the wider economy that depends on it. The bad news is that the oil and gas industry does have a talent problem right now.