This study systematically analyzes reservoir formation mechanisms under deep burial conditions, integrating macroscopic observations from representative ultra-deep clastic reservoirs in four major sedimentary basins in central and western China. Deve...
The lunar south polar region’s extreme illumination conditions impose strict energy constraints for solar-powered rover operations. Traditional Sun-synchronous path planning relies on dynamic time-dependent illumination evaluation, leading to h...
The Jiaodong Peninsula hosts the main large gold deposits and was the first gold production area in China; multisource and multiscale geoscience datasets are available. The area is the biggest drilling mineral-exploration zone in China. This study us...
As a type of widely used geophysical exploration equipment, artificial-source electromagnetic instruments are effectively used for resource and energy exploration due to their simple operation, deep-detecting depth, and higher resolution in the field...
In terms of deep reinforcement learning (RL), exploration is highly significant in achieving better generalization. In benchmark studies, ε-greedy random actions have been used to encourage exploration and prevent over-fitting, thereby improv...
Judging from the current global exploration trend, ultra-deep layers have become the main battlefield for energy exploration. China has made great progress in the ultra-deep field in recent decades, with the Tarim Basin and Sichuan Basin as the focus...
Effective exploration is one of the critical factors affecting performance in deep reinforcement learning. Agents acquire data to learn the optimal policy through exploration, and if it is not guaranteed, the data quality deteriorates, which leads to...
In recent years, the recommendation system and robot learning are undoubtedly the two most popular application fields, and the core algorithms supporting these two fields are deep learning based on perception and reinforcement learning based on explo...
Complex and unknown terrains in deep space exploration present great challenges to existing exploration robots. In this paper, a multi-mode motion spherical robot with flexible motion and strong environmental adaptability is presented. The spherical...
This paper investigates the solution to a mobile-robot exploration problem following autonomous driving principles. The exploration task is formulated in this study as a process of building a map while a robot moves in an indoor environment beginning...
The Sichuan Basin serves as a key arena for ultra-deep natural gas exploration. The Nanhuan System Gucheng Formation, characterized by its ancient geological age and great burial depth, lacks almost any drilling data within the basin interior, and it...
This paper is an initial endeavor to bridge the gap between powerful Deep Reinforcement Learning methodologies and the problem of exploration/coverage of unknown terrains. Within this scope, MarsExplorer, an openai-gym compatible environment tailored...
Deep interactive evolution (DeepIE) combines the capacity of interactive evolutionary computation (IEC) to capture a user’s preference with the domain-specific robustness of a trained generative adversarial network (GAN) generator, allowing the...
The Qingchengzi orefield is an important polymetallic ore concentration zone in the northern margin of the North China Craton (NCC). The region has significant metallogenic potential for deep mining. Many areas with gold mineralization have been foun...
With the development of technology and methodologies, Raman spectrometers are becoming efficient candidate payloads for planetary materials characterizations in deep space exploration missions. The National Aeronautics and Space Administration (NASA)...
Deep reinforcement learning often suffers from inefficient exploration, which is commonly addressed by introducing an auxiliary model that assigns intrinsic rewards when the agent encounters novel scenarios. However, such approaches increase training...
Very Long Baseline Interferometry (VLBI) solution can yield accurate information of angular position, and has been successfully used in the field of deep space exploration, such as astrophysics, imaging, detector positioning, and so on. The increase...
The exploration of deep mineral resources is an important prerequisite for meeting the continuous demand of resources. The geophysical method is one of the most effective means of exploring the deep mineral resources with a large depth and a high res...
Multi-robot collaborative autonomous exploration in communication-constrained scenarios is essential in areas such as search and rescue. During the exploration process, the robot teams must minimize the occurrence of redundant scanning of the environ...
The increasing demand for critical minerals is forcing the mineral exploration industry to search for deposits beneath deeper cover and over larger areas. MobileMT, an airborne passive, broadband, total-field AFMAG-class system, couples three-compone...
In this paper, we address the problem of autonomous exploration in unknown environments for ground mobile robots with deep reinforcement learning (DRL). To effectively explore unknown environments, we construct an exploration graph considering histor...
Porphyry molybdenum deposits hold significant potential for deep exploration. However, in the Dasuji molybdenum deposit, quartz porphyry, granite porphyry, and syenogranite are sporadically exposed beneath low mountains and hilly terrain, limiting th...
With the rapid development of the economy, the demand for mineral resources has increased dramatically. Because it is difficult to explore new mines in deep and peripheral areas, new theories, technologies, methods, and equipment are needed. How to a...
The remarkably long distances covered by deep space probes result in extremely weak downlink signals, which poses great challenges for ground measurement systems. In the current climate, improving the comprehensive utilization of downlink signal powe...
The Heyu ore-concentrated area in western Henan, situated within the East Qinling metallogenic belt, represents a strategic fluorite resource base currently confronting severe challenges of reserve depletion. Given this critical status, this study fo...
Effective ways to optimise real-time pump scheduling to maximise energy efficiency are being sought to meet the challenges in the energy market. However, the considerable number of evaluations of popular optimisation methods based on metaheuristics c...
Compression of remotely sensed astronomical images is an essential part of deep space exploration. This study proposes a wavelet-based compressed sensing (CS) algorithm for astronomical image compression in a miniaturized independent optical sensor s...
Driven by the energy transition and carbon-neutrality targets, global demand for critical minerals is increasing rapidly, while the discovery of new mineral deposits has become increasingly challenging because easily detectable outcropping deposits a...
As the depth of mineral exploration increases, integrated geophysical methods are increasingly playing a crucial role in prospecting deep structures at the district scale. The Nanling-Xuancheng ore district is the eighth ore district in the middle-lo...
Significant progress has been made in exploring ultra-deep tight sandstone gas in the Tarim Basin, but sweet spot prediction remains challenging in the Keshen block of the Kuqa Depression. Based on integrated geological, experimental, and seismic dat...
In recent years, unmanned aerial vehicles (UAVs) have increasingly become carrying platforms for Earth observation systems equipped with optical, microwave, and other types of sensors, primarily enabling high-resolution observations of above-ground t...
For the detection of deep-sea natural gas hydrates, it is very important to accurately detect the 13CO2/12CO2 isotope ratio of dissolved gas in seawater. In this paper, a 13CO2/12CO2 isotope ratio sensor is investigated, which uses a tunable diode la...
Traditional autonomous celestial navigation usually uses astronomical angle as measurement, which is a function of spacecraft’s position and can’t resolve the spacecraft’s velocity directly. To solve this problem, velocity measureme...
Deep lower-crustal detachments may control the development of fold-and-thrust belts, but their seismic expression and role in upper–lower-crustal deformation partitioning remain poorly constrained. Here, we present a 2-D deep seismic reflection...
The Jurassic reservoirs in the Fukang Sag of the Junggar Basin exhibit heterogeneous overpressure. As the mechanisms underlying overpressure generation remain poorly constrained, this poses challenges for accurate pre-drilling-pressure prediction and...
A near-source electromagnetic method known as the short-offset transient electromagnetic (SOTEM) method was proposed. Compared with the traditional far-source methods, the offset of the SOTEM method is greatly reduced, to only 0.3~2 times of the maxi...
In recent years, machine learning (and as a result artificial intelligence) has experienced considerable progress. As a result, robots in different shapes and with different purposes have found their ways into our everyday life. These robots, which h...
To address the high costs and inefficiencies of blind prospecting in deep geothermal exploration, this study develops a three-dimensional heat transfer model for quantitative prediction of geothermal enrichment targets. Unlike traditional qualitative...
Small Celestial Body (SCB) image matching is essential for deep space exploration missions. In this paper, a large-scale invariant method is proposed to improve the matching accuracy of SCB images under large-scale variations. Specifically, we design...
This paper investigates the application of genetic algorithms (GAs) for hyperparameter optimisation in deep reinforcement learning (RL), focusing on the Deep Q-Learning (DQN) algorithm. This study aims to identify approaches that enhance RL model per...
The Northern Jiangsu Basin (NJB), located at the northeast edge of the Yangtze block, is not only rich in oil and gas resources but also contains abundant geothermal resources. Nevertheless, the distribution of geothermal resources at medium depth in...
Large amounts of video images have been collected for decades by scientific and governmental organizations in deep (>1000 m) water using manned and unmanned submersibles and towed cameras. The collected images were analyzed individually or were mo...
Deep space exploration offers the most profound opportunity for the expansion of humanity and our understanding of the universe but remains extremely challenging. Progress will continue to be paced by uncrewed missions followed up by crewed missions...
In recent years, deep–penetrating geochemical exploration techniques have played a crucial role in the detection of concealed minerals. These methods effectively detect deep−seated anomalies and have been tested in various landscape&ndash...
Remote drilling technologies play a crucial role in automating both underground and open-pit hard rock mining operations. These technologies enhance efficiency and, most importantly, improve safety in the mining sector. Autonomous drilling rigs can n...
Subject-independent emotion recognition based on physiological signals has become a research hotspot. Previous research has proved that electrodermal activity (EDA) signals are an effective data resource for emotion recognition. Benefiting from their...
The Offshore Indus Basin is located on the western margin of the Indian Plate, adjacent to the onshore Lower Indus Basin in Pakistan and the Kutch Basin along India’s western coast. Deepwater and deep formations in this basin are characterized...
Many types of volcanic rock oil and gas reservoirs have been found in China, showing great petroleum exploration potential. Volcanic reservoir also is one of the key fields of exploration in the Junggar Basin and mainly concentrated in the middle and...
In this paper, we formulate the active SLAM paradigm in terms of model-free Deep Reinforcement Learning, embedding the traditional utility functions based on the Theory of Optimal Experimental Design in rewards, and therefore relaxing the intensive c...
This study proposes a solution for Active Simultaneous Localization and Mapping (Active SLAM) of robots in unknown indoor environments using a combination of Deep Deterministic Policy Gradient (DDPG) path planning and the Cartographer algorithm. To e...
of 176