Chinese fishing is increasing security risks near South Korea's tense nautical border, said a top Cabinet member in Seoul, pledging to deploy advanced technology to crack down on illegal trawling. Minister of Oceans and Fisheries Moon Seong-hyeok said in an interview that illegal fishing must be "completely eradicated," joining in calls from across Asia to end what many see as Beijing's assertive push into regional waters. South Korea has long complained about Chinese trawlers operating in the Yellow Sea -- what Koreans call the West Sea -- near its islands off the coast of North Korea. "When it comes to illegal fishing, whether it be foreign or domestic vessels, we will crack down," Moon told Bloomberg News on Friday, saying South Korea will from next year increase its maritime surveillance systems using drones at sea and artificial intelligence. South Korea, which lists the U.S. as its main military ally and China as its biggest trading partner, turned up the pressure on Beijing over the weekend when it won from Washington a termination of bilateral missile guidelines that have long restricted Seoul's development of missiles to under the range of 800 kilometers (500 miles).

The detection of critical infrastructures is of high importance in several fields such as security, anomaly detection, land use planning and land use change detection. However, critical infrastructures detection in aerial and satellite images is still a challenge as each one has completely different size and requires different spacial resolution to be identified correctly. Heretofore, there are no special datasets for training critical infrastructures detectors. This paper presents a smart dataset as well as a resolution-independent critical infrastructure detection system. In particular, guided by the performance of the detection model, we built a dataset organized into two scales, small and large scale, and designed a two-stage deep learning detection of different scale critical infrastructures (DetDSCI) methodology in ortho-images. DetDSCI methodology first determines the input image zoom level using a classification model, then analyses the input image with the appropriate scale detection model. Our experiments show that DetDSCI methodology achieves up to 37,53% F1 improvement with respect to the baseline detector.

AI is providing new opportunities in a range of fields, from business to industrial design to entertainment. How might machine- and deep-learning help us create safer, more sustainable, and resilient built environments? A team of researchers from the NSF NHERI SimCenter, computational modeling and simulation center for the natural hazards engineering community-based at the University of California, Berkeley, have developed a suite of tools called BRAILS--Building Recognition using AI at Large-Scale--that can automatically identify characteristics of buildings in a city and even detect the risks that a city's structures would face in an earthquake, hurricane, or tsunami. Charles (Chaofeng) Wang, a postdoctoral researcher at the University of California, Berkeley, and the lead developer of BRAILS, says the project grew out of a need to quickly and reliably characterize the structures in a city. "We want to simulate the impact of hazards on all of the buildings in a region, but we don't have a description of the building attributes," Wang said. "For example, in the San Francisco Bay area, there are millions of buildings.

Artificial intelligence is providing new opportunities in a range of fields, from business to industrial design to entertainment. How might machine- and deep-learning help us create safer, more sustainable, and resilient built environments? A team of researchers from the NSF NHERI SimCenter, a computational modeling and simulation center for the natural hazards engineering community based at the University of California, Berkeley, have developed a suite of tools called BRAILS--Building Recognition using AI at Large-Scale--that can automatically identify characteristics of buildings in a city and even detect the risks that a city's structures would face in an earthquake, hurricane, or tsunami. Charles (Chaofeng) Wang, a postdoctoral researcher at the University of California, Berkeley, and the lead developer of BRAILS, says the project grew out of a need to quickly and reliably characterize the structures in a city. "We want to simulate the impact of hazards on all of the buildings in a region, but we don't have a description of the building attributes," Wang said. "For example, in the San Francisco Bay area, there are millions of buildings.

Optimizing multiple competing black-box objectives is a challenging problem in many fields, including science, engineering, and machine learning. Multi-objective Bayesian optimization is a powerful approach for identifying the optimal trade-offs between the objectives with very few function evaluations. However, existing methods tend to perform poorly when observations are corrupted by noise, as they do not take into account uncertainty in the true Pareto frontier over the previously evaluated designs. We propose a novel acquisition function, NEHVI, that overcomes this important practical limitation by applying a Bayesian treatment to the popular expected hypervolume improvement criterion to integrate over this uncertainty in the Pareto frontier. We further argue that, even in the noiseless setting, the problem of generating multiple candidates in parallel reduces that of handling uncertainty in the Pareto frontier. Through this lens, we derive a natural parallel variant of NEHVI that can efficiently generate large batches of candidates. We provide a theoretical convergence guarantee for optimizing a Monte Carlo estimator of NEHVI using exact sample-path gradients. Empirically, we show that NEHVI achieves state-of-the-art performance in noisy and large-batch environments.

Many businesses and industries nowadays rely on large quantities of time series data making time series forecasting an important research area. Global forecasting models that are trained across sets of time series have shown a huge potential in providing accurate forecasts compared with the traditional univariate forecasting models that work on isolated series. However, there are currently no comprehensive time series archives for forecasting that contain datasets of time series from similar sources available for the research community to evaluate the performance of new global forecasting algorithms over a wide variety of datasets. In this paper, we present such a comprehensive time series forecasting archive containing 20 publicly available time series datasets from varied domains, with different characteristics in terms of frequency, series lengths, and inclusion of missing values. We also characterise the datasets, and identify similarities and differences among them, by conducting a feature analysis. Furthermore, we present the performance of a set of standard baseline forecasting methods over all datasets across eight error metrics, for the benefit of researchers using the archive to benchmark their forecasting algorithms.

Nayat Sánchez-Pi is the Director of the Inria Chile Research Center. We asked her about her research and about the OcéanIA project which she leads. The aim of the OcéanIA project is to develop new artificial intelligence and mathematical modeling tools to contribute to the understanding of the oceans and their role in regulating and sustaining the biosphere, and tackling the climate change. I have been working in the area of artificial intelligence and machine learning for more than 15 years now. During this time I have always had an interest in finding ways of taking the state-of-the-art of my area of research and applying it to have a direct impact on the real world.

In this paper we show how using satellite images can improve the accuracy of housing price estimation models. Using Los Angeles County's property assessment dataset, by transferring learning from an Inception-v3 model pretrained on ImageNet, we could achieve an improvement of ~10% in R-squared score compared to two baseline models that only use non-image features of the house.

The deepest regions of the oceans still remain one of the least explored areas on Earth, despite their considerable scientific interest and the richness of lifeforms inhabiting them. Two reasons for this are the low temperatures and enormous pressures exerted at such depths, which require the exploration equipment be carefully shielded inside high-strength metal or ceramic chambers to withstand them. This makes deep-sea exploration vessels bulky, expensive and unwieldy, as well as difficult to design, manufacture and transport. But a new small self-powered underwater robotic fish appears to offer an alternative. According to a recent paper, the robot was able to reach the deepest part of the Pacific Ocean – the Mariana Trench – at a depth of almost 11 km (6.8 miles).

The quantification of positively buoyant marine plastic debris is critical to understanding how concentrations of trash from across the world's ocean and identifying high concentration garbage hotspots in dire need of trash removal. Currently, the most common monitoring method to quantify floating plastic requires the use of a manta trawl. Techniques requiring manta trawls (or similar surface collection devices) utilize physical removal of marine plastic debris as the first step and then analyze collected samples as a second step. The need for physical removal before analysis incurs high costs and requires intensive labor preventing scalable deployment of a real-time marine plastic monitoring service across the entirety of Earth's ocean bodies. Without better monitoring and sampling methods, the total impact of plastic pollution on the environment as a whole, and details of impact within specific oceanic regions, will remain unknown. This study presents a highly scalable workflow that utilizes images captured within the epipelagic layer of the ocean as an input. It produces real-time quantification of marine plastic debris for accurate quantification and physical removal. The workflow includes creating and preprocessing a domain-specific dataset, building an object detection model utilizing a deep neural network, and evaluating the model's performance. YOLOv5-S was the best performing model, which operates at a Mean Average Precision (mAP) of 0.851 and an F1-Score of 0.89 while maintaining near-real-time speed.