Abstract

Abstract

Abstract

Abstract
Remote sensing, particularly satellite-based, can play a valuable role in monitoring areas prone to geohazards. The high spatial and temporal coverage provided by satellite data can be used to reconstruct past events and continuously monitor sensitive areas for potential hazards. This paper presents a range of techniques and methods that were applied for in-depth analysis and utilization of Earth observation data, with a particular emphasis on: (1) detecting mining subsidence, where a novel approach is proposed by combining an improved U-Net model and Interferometry Synthetic Aperture Radar (InSAR) technology. The results showed that the Efficient Channel Attention (ECA) U-Net model performed better than the U-Net (baseline) model in terms of Mean Intersection over Union (MIoU) and Intersection over Union (IoU) indicators; (2) monitoring water conservancy and hydropower engineering. The Xiaolangdi multipurpose dam complex was monitored using Small BAsline Subsets (SBAS) InSAR method on Sentinel-1 time series data and four small regions with high deformation rates were identified on the slope of the reservoir bank on the north side. The dam body also showed obvious deformation with a velocity exceeding 60 mm/a; (3) the evaluation of the potential of InSAR results to integrate monitoring and warning systems for valuable heritage and architectural preservation. The overall outcome of these methods showed that the use of Artificial Intelligence (AI) techniques in combination with InSAR data leads to more efficient analysis and interpretation, resulting in improved accuracy and prompt identification of potential hazards; and (4) finally, this study also presents a method for detecting landslides in mountainous regions, using optical imagery. The new temporal landslide detection method is evaluated over a 7-year analysis period and unlike conventional bi-temporal change detection methods, this approach does not depend on any prior-knowledge and can potentially detect landslides over extended periods of time such as decades.

Abstract
Reinforcement Learning (RL) is a well-suited paradigm to train robots since it does not require any previous information or database to train an agent. This paper explores using Deep Reinforcement Learning (DRL) to train a robot to navigate in maps containing different sorts of obstacles and which emulate hallways. Training and testing were performed using the Flatland 2D simulator and a Deep Q-Network (DQN) provided by OpenAI gym. Different sets of maps were used for training and testing. The experiments illustrate how well the robot is able to navigate in maps distinct from the ones used for training by learning new behaviours (namely following walls) and highlight the key challenges when solving this task using DRL, including the appropriate definition of the state space and reward function, as well as of the stopping criteria during training.

Abstract
Accurate predictions of time series are increasingly required to support judgments in a variety of decisions. Several predictive models are available to support these predictions, depending on how each field offers a data variety with varied behavior. The use of artificial neural networks (ANN) at the beginning of the COVID-19 pandemic was significant since the tool may offer forecasting data for various conditions and hence assist in governing critical choices. In this context, this paper describes a system for predicting the daily number of cases, fatalities, and Intensive Care Unit (ICU) patients for the next 28 days in five European countries: Portugal, the United Kingdom, France, Italy, and Germany. The database selection is based on comparable mitigation processes to analyze the impact of safety procedure flexibilization with the most recent numbers of COVID-19. Additionally, it is intended to check the algorithm's adaptability to different variants throughout time. The network's input data has been normalized to account for the size of the countries in the study and smoothed by seven days. The mean absolute error (MAE) was employed as a comparing criterion of two datasets, one with data from the beginning of the pandemic and another with data from the last year, since all variables (cases, deaths, and ICU patients) may be tendentious in percentage analysis. The best architecture produced a general MAE prediction for the 28 days ahead of 256,53 daily cases, 0,59 daily deaths, and 1,63 ICU patients, all numbers normalized by million people. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.