Jilin Jianzhu University

Globally guided multi-agent reinforcement learning with decoupled critics for cooperative UAV path planning

Abstract Cooperative path planning for multiple unmanned aerial vehicles (UAVs) requires the simultaneous achievement of target navigation, collision avoidance, and formation coordination in complex obstacle environments. Existing multi-agent reinforcement learning methods often...

A novel sensitivity-driven multistage feedforward inverse modeling approach for source identification of organic-contaminated aquifer

In the present study, a sensitivity-driven multistage combined search system was established to improve the search capability and accuracy of inverse modeling for the simultaneous identification of DNAPL contamination sources and contaminant transport (CTR) parameters. The system...

Turning Data into Sustainability: Agricultural Big Data Policy, Capital Composition, and Rural Eco-Environmental Sustainability in China

Rural environmental degradation is diffuse, weakly monitored, and hard to govern, and is among the most persistent obstacles to the Sustainable Development Goals (SDGs). Whether treating data as a factor of production relieves this constraint remains unsettled, as does what a rur...

Multi-objective artificial lemming algorithm for optimal operation of carbon capture and power-to-methanol integrated microgrid

Against the global low-carbon energy transition and booming AI power demand, coordinating microgrid economic operation with low-carbon, efficient scheduling has become a core challenge for new power systems. Therefore, this paper proposes a microgrid-integrated energy system with...

Steel surface defect detection based on dynamic receptive field and multi-scale features fusion

Abstract Steel surface defect detection is vital for guaranteeing product quality in contemporary manufacturing. However, traditional steel surface defect detection algorithms often face challenges due to insufficient resilience in feature extraction under complex backgrounds. To...

Study on the heat transfer performance of deep-buried pipe energy piles with different pile length-to-depth ratios

To achieve the “dual carbon” goals, this paper proposes a new structure, the deep-buried pipe energy pile, to overcome the limitations of heat exchange efficiency associated with traditional energy piles. Using a combination of model tests and numerical simulations, a multi-field...

Glimpse into the past: Analyses of the middle and inner ear of extinct rodents (Eusciurida; Rodentia; Mammalia) with implications for their locomotory behaviour

Abstract Rodentia is the most diverse and species-rich group of mammals, inhabiting almost all regions and ecosystems on earth. One of the most specialised subgroups is the Eusciurida, composed of Sciuridae, Gliridae, and Aplodontia rufa , and characterised by arboreal, fossorial...

Deciphering riverine CODMn sources: driver identification and carbon cycle impacts

The large-scale monitoring of riverine organic pollution is of significant practical importance for river basin ecological management and sustainable development to replace the traditional monitoring stations. The development for remote sensing of riverine chemical oxygen demand...

Vehicle Multimodal Trajectory Prediction Integrating Kinematics and Dynamic Interaction Features

Accurate vehicle trajectory prediction is essential for autonomous driving safety. However, existing data-driven models often ignore kinematic constraints, causing lateral jitter and trajectory distortion, while purely kinematics-based models lack flexibility in complex interacti...

Cu2O-modified magnetic iron-nitrogen co-doped biochar effective peroxymonosulfate activation for degradation of phthalate esters in reclaimed water.

O/Fe-N-BC/PMS system demonstrated excellent stability and reusability, offering a promising approach for the treatment of wastewater contaminated with organic pollutants. This system operates efficiently under neutral conditions, is energy-effective, and addresses limitations com...