Search

The rising severity and frequency of wildfires in recent years in the United States have raised numerous concerns regarding the improvement in wildfire emergency response management and decision-making systems, which require operational high temporal and spatial resolution monitoring capabilities. Satellites are one of the tools that can be used for wildfire monitoring. However, none of the currently available satellite systems provide both high temporal and spatial resolution. For example, GOES-17 geostationary satellite fire products have high temporal (1–5 min) but low spatial resolution (≥2 km), and VIIRS polar orbiter satellite fire products have low temporal (~12 h) but high spatial resolution (375 m). This work aims to leverage currently available satellite data sources, such as GOES and VIIRS, along with deep learning (DL) advances to achieve an operational high-resolution, both spatially and temporarily, wildfire monitoring tool. Specifically, this study considers the problem of increasing the spatial resolution of high temporal but low spatial resolution GOES-17 data products using low temporal but high spatial resolution VIIRS data products. The main idea is using an Autoencoder DL model to learn how to map GOES-17 geostationary low spatial resolution satellite images to VIIRS polar orbiter high spatial resolution satellite images. In this context, several loss functions and DL architectures are implemented and tested to predict both the fire area and the corresponding brightness temperature. These models are trained and tested on wildfire sites from 2019 to 2021 in the western U.S. The results indicate that DL models can improve the spatial resolution of GOES-17 images, leading to images that mimic the spatial resolution of VIIRS images. Combined with GOES-17 higher temporal resolution, the DL model can provide high-resolution near-real-time wildfire monitoring capability as well as semi-continuous wildfire progression maps. [ABSTRACT FROM AUTHOR]

Technology always leaping more forward than before this can happen because there's a many inovations and work of mankind, as example we can take it from the development of Artificial Intelligence with this kind of development is a subject of a Research and Development from Technologies itself that can make work more easier than before and of course Artificial Intelligence always related to Big data and computing power that can think and make conclusions like human being, on the side of Law this development is a pretty game changer such as on Indonesia itself there was a website called a HukumOnline who has already launching an platform LIA (Legal Intelligence Assistant) that using an A.I based for the public, for next example we can take it from America that using an A.I too called "Do Not Pay" in short this Apps is a lawyer based on A.I, but on February 2023 this Apps only used for ticketing Case only In the case example above, of course, questions will arise about how AI is positioned in the criminal justice process in Indonesia, therefore this journal will explain the subject matter. [ABSTRACT FROM AUTHOR]

This article contemplates and advocates for the use of Artificial Intelligence (“AI”) through Large Language Models (“LLM”) in legal practice. The author ultimately addresses the need to orient LMMs within varying legal contexts including academia, private practice, as well as the U.S. court system. Additionally, the author emphasizes the inevitability of AI and LLM systems infiltrating legal practice, and the reality that the industry must acknowledge and accept these systems to regulate and to provide better while still ethical legal services. Large Language Models: AI’s Legal Revolution, begins by walking the reader through the history of technological innovation of AI, all the way to modern LLM systems. This in turn lays a foundation for understanding what exactly the product is that should shape the legal landscape, and why we should be paying better attention to it. The article then compares and contrasts the current LLM products on the market, including a discussion of their capabilities in the context of legal work. Finally, the article discusses the different practical areas of law where LLMs can prove to enhance the legal industry, how so, and the benefits that LLMs may bring to the landscape of law in the twenty-first century. [ABSTRACT FROM AUTHOR]

As China's ascendancy in Artificial Intelligence (AI) potentially surpasses that of the United States in specific dimensions, this research article critically assesses the existing and proposed AI policies of the United States, incorporating recommendations from the U.S. National Security Commission on AI (NSCAI). The research uses dual-scoring metrics based on the NSCAI-proposed AI stack and an original stakeholder metric to provide quantifiable variables to assess the potential impact of a policy, capturing feasible policy proposals. This analysis creates a practical tool for policy analysts and researchers to evaluate AI policies, which includes a tiered policy structure based on overall scores from the dualscoring metrics. Given the significance of AI in future national development, our model aims to aid policymakers in discerning the merit and feasibility of specific AI policies, thereby facilitating informed policymaking and development. [ABSTRACT FROM AUTHOR]

Seasonal snow-derived water is a critical component of the water supply in the mountains and downstream regions, and the accurate characterization of available water in the form of snow-water-equivalent (SWE), peak SWE, and snowmelt onset are essential inputs for water management efforts. Arising from recent advancements in artificial intelligence (AI) and machine learning (ML), we introduce a large-scale ML SWE model leveraging publicly available data sources and open-source software. The model demonstrates the application of a limited feature space in a relatively simple ML architecture without the need for process-based formulations to effectively estimate spatially continuous SWE at a daily temporal resolution. Beginning with in situ SWE measurements (i.e., SNOTEL), lidar-derived terrain features, and temporal variables, we employ localized feature engineering and optimization via gradient-boosting decision trees to identify regionally unique drivers of snowpack dynamics and use the optimal features to train regionally independent artificial neural networks to estimate regional SWE at a 1 km spatial resolution. The model results yield respectable skill in reconstructed 1 km gridded SWE magnitudes in a hindcast simulation of the 2019 water year that is independent of the training and testing data. Comparing model estimates to over 6200 observations, the model demonstrates a weighted RMSE of 15.4 cm, Kling-Gupta Efficiency metric of 0.86, and a percent bias of 0.71% across 23 snow-influenced regions in the western U.S. The model simulation produces peak SWE estimates within 10 cm for twenty of the twenty-three regions, demonstrating capability in effectively capturing regional snow accumulation processes. The demonstration of low-error ML workflows capable of providing near-real-time, spatially continuous SWE estimates at a high spatial resolution provides proof-of-concept and a foundation to effectively update snow state variables that drive water supply forecasts in snow-dominated regions. • A new Machine Learning-based SWE estimation model for the Western United States. • Utilization of open-source tools and up-to-date in-situ observations to estimate SWE. • Reconstructed SWE magnitudes exhibit respectable skill in a hindcast simulation. • Output may serve as a supplemental state-of-snowpack input to hydrologic models. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is an emerging technology with widespread applications. The National Defense Strategy highlights the importance of AI to military operations for the United States to retain an advantage against its near-peer competitors. To fully realise this advantage, it will be necessary to integrate AI not only at the tactical level but also at the operational level of war. AI can be integrated into the complex task of operational planning most efficiently by subdividing it into its component operational functions, which can be processed by narrow AI. This organisation reduces problems to a size that can be parsed by an AI and maintains human oversight over machine supported decision-making. [ABSTRACT FROM AUTHOR]