We present a novel approach to probabilistic electricity price forecasting which utilizes distributional neural networks. The model structure is based on a deep neural network that contains a so-called probability layer. The network's output is a parametric distribution with 2 (normal) or 4 (Johnson's SU) parameters. In a forecasting study involving day-ahead electricity prices in the German market, our approach significantly outperforms state-of-the-art benchmarks, including LASSO-estimated regressions and deep neural networks combined with Quantile Regression Averaging. The obtained results not only emphasize the importance of higher moments when modeling volatile electricity prices, but also -- given that probabilistic forecasting is the essence of risk management -- provide important implications for managing portfolios in the power sector.

This work presents an actuation framework for a bioinspired flapping drone called Aerobat. This drone, capable of producing dynamically versatile wing conformations, possesses 14 body joints and is tail-less. Therefore, in our robot, unlike mainstream flapping wing designs that are open-loop stable and have no pronounced morphing characteristics, the actuation, and closed-loop feedback design can pose significant challenges. We propose a framework based on integrating mechanical intelligence and control. In this design framework, small adjustments led by several tiny low-power actuators called primers can yield significant flight control roles owing to the robot's computational structures. Since they are incredibly lightweight, the system can host the primers in large numbers. In this work, we aim to show the feasibility of joint's motion regulation in Aerobat's untethered flights.

This completion can be formatted as either English sentences or a more structured schema such as a list of JSON documents. Large language models (LLMs) such as GPT-3 [12], PaLM To use this method, one only has to define the desired [25], Megatron [26], OPT [27], Gopher [28], and FLAN [29] output structure--for example, a list of JSON objects with a have been shown to have remarkable ability to leverage semantic predefined set of keys--and annotate 100 500 text passages information between tokens in natural language sequences using this format. GPT-3 is then fine-tuned on these of varying length. They are particularly adept at examples, and the resulting model is able to accurately extract sequence-to-sequence (seq2seq) tasks, where a text input is desired information from text and output information in used to seed a text response from the model. In this paper the same structured representation as shown in Figure 1.

Monitoring and managing Earth's forests in an informed manner is an important requirement for addressing challenges like biodiversity loss and climate change. While traditional in situ or aerial campaigns for forest assessments provide accurate data for analysis at regional level, scaling them to entire countries and beyond with high temporal resolution is hardly possible. In this work, we propose a method based on deep ensembles that densely estimates forest structure variables at country-scale with 10-meter resolution, using freely available satellite imagery as input. Our method jointly transforms Sentinel-2 optical images and Sentinel-1 synthetic-aperture radar images into maps of five different forest structure variables: 95th height percentile, mean height, density, Gini coefficient, and fractional cover. We train and test our model on reference data from 41 airborne laser scanning missions across Norway and demonstrate that it is able to generalize to unseen test regions, achieving normalized mean absolute errors between 11% and 15%, depending on the variable. Our work is also the first to propose a variant of so-called Bayesian deep learning to densely predict multiple forest structure variables with well-calibrated uncertainty estimates from satellite imagery. The uncertainty information increases the trustworthiness of the model and its suitability for downstream tasks that require reliable confidence estimates as a basis for decision making. We present an extensive set of experiments to validate the accuracy of the predicted maps as well as the quality of the predicted uncertainties. To demonstrate scalability, we provide Norway-wide maps for the five forest structure variables.

Computational models are quantitative representations of systems. By analyzing and comparing the outputs of such models, it is possible to gain a better understanding of the system itself. Though as the complexity of model outputs increases, it becomes increasingly difficult to compare simulations to each other. While it is straightforward to only compare a few specific model outputs across multiple simulations, additional useful information can come from comparing model simulations as a whole. However, it is difficult to holistically compare model simulations in an unbiased manner. To address these limitations, we use representation learning to transform model simulations into low-dimensional points, with the neural networks capturing the relationships between the model outputs without the need to manually specify which outputs to focus on. The distance in low-dimensional space acts as a comparison metric, reducing the difference between simulations to a single value. We provide an approach to training neural networks on model simulations and display how the trained networks can then be used to provide a holistic comparison of model outputs. This approach can be applied to a wide range of model types, providing a quantitative method of analyzing the complex outputs of computational models.

The autonomous tractor world is heating up, apparently. CNH Industrial has unveiled what it says is the "first" electric light tractor prototype with self-driving features, the New Holland T4 Electric Power. The machine promises zero emissions, quieter operation than diesel models and (according to CNH) lower running costs while reducing the amount of time farmers spend behind the wheel. Sensors and cameras on the roof help the vehicle complete tasks, dodge obstacles and work in harmony with other equipment. You can even activate it from your phone.

China plans to cooperate with Saudi Arabia and other Gulf countries in the fields of nuclear energy, nuclear security and space exploration, President Xi Jinping said on Friday, showcasing his nation's strengthening ties with a region that was once firmly in the U.S. sphere of influence. Mr. Xi was speaking in the Saudi capital, Riyadh, at a summit with rulers and officials from the six Gulf Cooperation Council countries -- Bahrain, Kuwait, Oman, Qatar, Saudi Arabia, and the United Arab Emirates -- during a three-day visit to Saudi Arabia. Later on Friday, he held his third and final summit of the visit with other Arab and African leaders. Both China and Saudi Arabia described Mr. Xi's visit this week as a historic event ushering in a new era of relations between Beijing and the Middle East, a region that once had a mainly oil-based relationship with China, a major consumer of the Gulf's fossil fuel exports. Arab states are increasingly building broader ties with China that extend into arms sales, technology transfers and infrastructure projects.

Analysis of the satellite images by Soar Earth, an Australian startup that aggregates satellite imagery and crowdsourced maps into an online digital atlas, suggests that the workers have already excavated around 26 million cubic meters of earth and rock--78 times the volume of the world's tallest building, the Burj Khalifa. Official drone footage of The Line's construction site, released in October, indeed showed fleets of bulldozers, trucks, and diggers excavating its foundations. Visit The Line's location on Google Maps and Google Earth, however, and you will see little more than bare rock and sand. The strange gap in imagery raises questions about who gets to access high-res satellite technology. And if the largest urban construction site on the planet doesn't appear on Google Maps, what else can't we see? The Line is as controversial as it is futuristic.

We propose a supervised deep learning (DL) approach to perform adaptive zoning on time dependent partial differential equations that model the propagation of 1D shock waves in a compressible medium. We train a neural network on a dataset composed of different static shock profiles associated with the corresponding adapted meshes computed with standard adaptive zoning techniques. We show that the trained DL model learns how to capture the presence of shocks in the domain and generates at each time step an adapted non-uniform mesh that relocates the grid nodes to improve the accuracy of Lax-Wendroff and fifth order weighted essentially non-oscillatory (WENO5) space discretization schemes. We also show that the surrogate DL model reduces the computational time to perform adaptive zoning by at least a 2x factor with respect to standard techniques without compromising the accuracy of the reconstruction of the physical quantities of interest.

Bayesian optimization (BO) is one of the most effective methods for closed-loop experimental design and black-box optimization. However, a key limitation of BO is that it is an inherently sequential algorithm (one experiment is proposed per round) and thus cannot directly exploit high-throughput (parallel) experiments. Diverse modifications to the BO framework have been proposed in the literature to enable exploitation of parallel experiments but such approaches are limited in the degree of parallelization that they can achieve and can lead to redundant experiments (thus wasting resources and potentially compromising performance). In this work, we present new parallel BO paradigms that exploit the structure of the system to partition the design space. Specifically, we propose an approach that partitions the design space by following the level sets of the performance function and an approach that exploits partially-separable structures of the performance function found. We conduct extensive numerical experiments using a reactor case study to benchmark the effectiveness of these approaches against a variety of state-of-the-art parallel algorithms reported in the literature. Our computational results show that our approaches significantly reduce the required search time and increase the probability of finding a global (rather than local) solution.