London-based fintech company Util announced today the release of an AI-based analytics solution designed to measure companies' impact on the 17 United Nations Sustainable Development Goals (SDGs). According to Util, the new solution aims to fill a gap in the market for data that can keep investors informed of the true impact of their investments, as demand for sustainable funds grows, while the effectiveness of ESG-themed products remains inconsistent. The company noted, for example, that only 6.7% of European funds labelled as'sustainable' explicitly screen out or reduce exposure to fossil fuels. "The disparity between growing demand and inadequate supply is a recipe for greenwashing at best, a bubble at worst. It has led to investments being mis-sold as sustainable, when in reality, they're inconsistent with investors' values."

Since carbon sequestration is such an important factor for mitigating climate change, it's critical to understand the efficacy of reforestation efforts and develop solid estimates of forest carbon storage capacity. However, measuring forest properties can be difficult, especially in places that aren't easily reachable. Purdue University's Jingjing Liang, an assistant professor of quantitative forest ecology and co-chair of the Forest Advanced Computing and Artificial Intelligence (FACAI) Laboratory in the Department of Forestry and Natural Resources, led an international team to measure forest carbon capacity in northeast Asia. Their research, which blends remote sensing, field work and machine learning, offers the most up-to-date estimates of carbon capture potential in reclusive North Korea and details the benefits of reforestation efforts over the last two decades in China and South Korea. "Because there is historically scant data from North Korea, people know little about how much carbon is stored in this region," said Liang, whose findings were published in the journal Global Change Biology.

Production of news content is growing at an astonishing rate. To help manage and monitor the sheer amount of text, there is an increasing need to develop efficient methods that can provide insights into emerging content areas, and stratify unstructured corpora of text into `topics' that stem intrinsically from content similarity. Here we present an unsupervised framework that brings together powerful vector embeddings from natural language processing with tools from multiscale graph partitioning that can reveal natural partitions at different resolutions without making a priori assumptions about the number of clusters in the corpus. We show the advantages of graph-based clustering through end-to-end comparisons with other popular clustering and topic modelling methods, and also evaluate different text vector embeddings, from classic Bag-of-Words to Doc2Vec to the recent transformers based model Bert. This comparative work is showcased through an analysis of a corpus of US news coverage during the presidential election year of 2016.

Citing opinions is a powerful yet understudied strategy in argumentation. For example, an environmental activist might say, "Leading scientists agree that global warming is a serious concern," framing a clause which affirms their own stance ("that global warming is serious") as an opinion endorsed ("[scientists] agree") by a reputable source ("leading"). In contrast, a global warming denier might frame the same clause as the opinion of an untrustworthy source with a predicate connoting doubt: "Mistaken scientists claim [...]." Our work studies opinion-framing in the global warming (GW) debate, an increasingly partisan issue that has received little attention in NLP. We introduce DeSMOG, a dataset of stance-labeled GW sentences, and train a BERT classifier to study novel aspects of argumentation in how different sides of a debate represent their own and each other's opinions. From 56K news articles, we find that similar linguistic devices for self-affirming and opponent-doubting discourse are used across GW-accepting and skeptic media, though GW-skeptical media shows more opponent-doubt. We also find that authors often characterize sources as hypocritical, by ascribing opinions expressing the author's own view to source entities known to publicly endorse the opposing view. We release our stance dataset, model, and lexicons of framing devices for future work on opinion-framing and the automatic detection of GW stance.

A sustainable burn platform through inertial confinement fusion (ICF) has been an ongoing challenge for over 50 years. Mitigating engineering limitations and improving the current design involves an understanding of the complex coupling of physical processes. While sophisticated simulations codes are used to model ICF implosions, these tools contain necessary numerical approximation but miss physical processes that limit predictive capability. Identification of relationships between controllable design inputs to ICF experiments and measurable outcomes (e.g. yield, shape) from performed experiments can help guide the future design of experiments and development of simulation codes, to potentially improve the accuracy of the computational models used to simulate ICF experiments. We use sparse matrix decomposition methods to identify clusters of a few related design variables. Sparse principal component analysis (SPCA) identifies groupings that are related to the physical origin of the variables (laser, hohlraum, and capsule). A variable importance analysis finds that in addition to variables highly correlated with neutron yield such as picket power and laser energy, variables that represent a dramatic change of the ICF design such as number of pulse steps are also very important. The obtained sparse components are then used to train a random forest (RF) surrogate for predicting total yield. The RF performance on the training and testing data compares with the performance of the RF surrogate trained using all design variables considered. This work is intended to inform design changes in future ICF experiments by augmenting the expert intuition and simulations results.

Non-Intrusive Load Monitoring (NILM) aims to predict the status or consumption of domestic appliances in a household only by knowing the aggregated power load. NILM can be formulated as regression problem or most often as a classification problem. Most datasets gathered by smart meters allow to define naturally a regression problem, but the corresponding classification problem is a derived one, since it requires a conversion from the power signal to the status of each device by a thresholding method. We treat three different thresholding methods to perform this task, discussing their differences on various devices from the UK-DALE dataset. We analyze the performance of deep learning state-of-the-art architectures on both the regression and classification problems, introducing criteria to select the most convenient thresholding method.

Convolutional neural networks (CNN) have achieved great success in analyzing tropical cyclones (TC) with satellite images in several tasks, such as TC intensity estimation. In contrast, TC structure, which is conventionally described by a few parameters estimated subjectively by meteorology specialists, is still hard to be profiled objectively and routinely. This study applies CNN on satellite images to create the entire TC structure profiles, covering all the structural parameters. By utilizing the meteorological domain knowledge to construct TC wind profiles based on historical structure parameters, we provide valuable labels for training in our newly released benchmark dataset. With such a dataset, we hope to attract more attention to this crucial issue among data scientists. Meanwhile, a baseline is established with a specialized convolutional model operating on polar-coordinates. We discovered that it is more feasible and physically reasonable to extract structural information on polar-coordinates, instead of Cartesian coordinates, according to a TC's rotational and spiral natures. Experimental results on the released benchmark dataset verified the robustness of the proposed model and demonstrated the potential for applying deep learning techniques for this barely developed yet important topic.

U.S. Customs and Border Protection wants to apply artificial intelligence to the ingestion and analysis of increasing amounts of data coming out of its efforts to secure the U.S. supply chain. CBP needs to analyze data earlier along the supply chain because currently, it's getting involved too late after products have been manufactured and already begun international transit, Vincent Annunziato, director of the agency's Business Transformation and Innovation Division, said during ACT-IAC's Reimagine Nation ELC 2020 on Monday. The agency is responsible for ensuring importer and exporter compliance with laws and regulations that prevent harmful or counterfeit products from entering or exiting the U.S. The volume of supply chain data CBP is dealing with has skyrocketed since the agency started piloting blockchain to secure various industries like steel and oil, and only AI and machine learning can make sense of it all. "All of this now is starting to play into that AI and machine learning arena because, one, we're getting data that we've never seen before," Annunziato said. "Two … the government is going to look into designing a system that's flexible for the data that's coming in so that, even if you don't have all the appropriate data at the time that you submit it, you can update it as you go along."

We're proud to announce that the IOTA Foundation has partnered on a project initiated by Best Materia and IMC, Japanese maintenance-related companies, and funded by NEDO (New Energy and Industrial Technology Development Organization). NEDO is Japan's largest public management organization promoting research and development as well as the deployment of industrial, energy, and environmental technologies. The goal of the project is to develop technology to strengthen the security, longevity, and durability of critical infrastructure assets in Japan and abroad. By adding artificial intelligence and the IOTA Tangle technology to Risk-Based Maintenance (RBM) Systems deployed in power plants, energy plants, industrial plants, petrochemicals, and oil refining plants, the group hopes to capture a large share of the domestic social infrastructure conservation market, valued at 170 Trillion Yen (1.5 Trillion USD). This type of predictive maintenance system that shares industry data using a distributed database is set to be the first of its kind in the world. While damage prediction assessment based on the current RBM standards exists, most processes are still left up to field workers to do manually.

Data is a central piece of the climate change debate. With the climate change datasets on this list, many data scientists have created visualizations and models to measure and track the change in surface temperatures, sea ice levels, and more. Many of these datasets have been made public to allow people to contribute and add valuable insight into the way the climate is changing and its causes. We hope this collection provides you with a jumping off point to use your skills to contribute to one of the biggest and most important challenges of our time. It covers various topics such as greenhouse gas emissions, energy consumption, and more. The total time period of the data covers 1990 – 2011.