Climate change impacts on wildfire risk indices forecast based on an improved genetic neural network algorithm: a case study of Guangxi, China

Earth Science Informatics, Journal Year: 2025, Volume and Issue: 18(3)

Published: Feb. 27, 2025

Language: Английский

---

The Role of Generative Artificial Intelligence in Digital Agri-Food

Journal of Agriculture and Food Research, Journal Year: 2025, Volume and Issue: unknown, P. 101787 - 101787

Published: March 1, 2025

Language: Английский

---

Machine Learning-Based Wildfire Susceptibility Mapping: A Gis-Integrated Predictive Framework

Published: Jan. 1, 2025

Language: Английский

---

Application of geographic information system and remote sensing technology in ecosystem services and biodiversity conservation

Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 97 - 122

Published: Jan. 1, 2025

Language: Английский

---

FIRE-YOLOv8s: A Lightweight and Efficient Algorithm for Tunnel Fire Detection

Fire, Journal Year: 2025, Volume and Issue: 8(4), P. 125 - 125

Published: March 24, 2025

To address the challenges of high algorithmic complexity and low accuracy in current fire detection algorithms for highway tunnel scenarios, this paper proposes a lightweight algorithm, FIRE-YOLOv8s. First, novel feature extraction module, P-C2f, is designed using partial convolution (PConv). By dynamically determining kernel’s range action, module significantly reduces model’s computational load parameter count. Additionally, ADown introduced downsampling, employing branching design to minimize requirements while preserving essential information. Secondly, neck fusion network redesigned CNN-based cross-scale (CCFF). This leverages operations achieve efficient fusion, further reducing model enhancing efficiency multi-scale features. Finally, dynamic head introduced, incorporating multiple self-attention mechanisms better capture key information complex scenes. improvement enhances robustness detecting targets under challenging conditions. Experimental results on self-constructed dataset demonstrate that, compared baseline YOLOv8s, FIRE-YOLOv8s by 47.2%, decreases number parameters 52.2%, size 50% original, achieving 4.8% 1.7% increase [email protected]. Furthermore, deployment experiments emergency firefighting robot platform validate algorithm’s practical applicability, confirming its effectiveness real-world scenarios.

Language: Английский

---

Visualization of Post-Fire Remote Sensing Using CiteSpace: A Bibliometric Analysis

Forests, Journal Year: 2025, Volume and Issue: 16(4), P. 592 - 592

Published: March 28, 2025

At present, remote sensing serves as a key approach to track ecological recovery after fires. However, systematic and quantitative research on the progress of post-fire remains insufficient. This study presents first global bibliometric analysis (1994–2024), analyzing 1155 Web Science publications using CiteSpace reveal critical trends gaps. The findings include following: As multi-sensor big data technologies evolve, focus is increasingly pivoting toward interdisciplinary, multi-scale, intelligent methodologies. Since 2020, AI-driven such machine learning have become hotspots continue grow. In future, more extensive time-series monitoring, holistic evaluations under compound disturbances, enhanced fire management strategies will be required addressing climate change challenge sustainability. USA, Canada, China, multiple European nations work jointly ecology technology development, but Africa, high wildfire-incidence area, currently lacks appropriate local research. Remote environment forests maintain pivotal role in scholarly impact information exchange. redefines nexus urgency social justice, demanding inclusive innovation address climate-driven regimes.

Language: Английский

---

Development and Application of Self-Supervised Machine Learning for Smoke Plume and Active Fire Identification from the Fire Influence on Regional to Global Environments and Air Quality Datasets

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(7), P. 1267 - 1267

Published: April 2, 2025

Fire Influence on Regional to Global Environments and Air Quality (FIREX-AQ) was a field campaign aimed at better understanding the impact of wildfires agricultural fires air quality climate. The FIREX-AQ took place in August 2019 involved two aircraft multiple coordinated satellite observations. This study applied evaluated self-supervised machine learning (ML) method for active fire smoke plume identification tracking sub-orbital remote sensing datasets collected during campaign. Our unique methodology combines observations with different spatial spectral resolutions. With as much 10% increase agreement between our produced masks high-certainty hand-labeled pixels, relative operational products, demonstrated approach successfully differentiates pixels plumes from background imagery. enables generation per-instrument mask product, well created fusion selected data independent instruments. ML has potential enhance wildfire monitoring systems improve decision-making management through fast could climate studies

Language: Английский

---

UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 103158 - 103158

Published: April 1, 2025

Language: Английский

---

Improving Fire and Smoke Detection with You Only Look Once 11 and Multi-Scale Convolutional Attention

Fire, Journal Year: 2025, Volume and Issue: 8(5), P. 165 - 165

Published: April 22, 2025

Fires pose significant threats to human safety, health, and property. Traditional methods, with their inefficient use of features, struggle meet the demands fire detection. You Only Look Once (YOLO), as an efficient deep learning object detection framework, can rapidly locate identify smoke objects in visual images. However, research utilizing latest YOLO11 for remains sparse, addressing scale variability well practicality models continues be a focus. This study first compares classic YOLO series analyze its advantages tasks. Then, tackle challenges model practicality, we propose Multi-Scale Convolutional Attention (MSCA) mechanism, integrating it into create YOLO11s-MSCA. Experimental results show that outperforms other by balancing accuracy, speed, practicality. The YOLO11s-MSCA performs exceptionally on D-Fire dataset, improving overall accuracy 2.6% recognition 2.8%. demonstrates stronger ability small objects. Although remain handling occluded targets complex backgrounds, exhibits strong robustness generalization capabilities, maintaining performance complicated environments.

Language: Английский

---

DMPNet: A Lightweight Remote Sensing Forest Wildfire Detection Network Based on Multi-Scale Heterogeneous Attention Mechanism and Dynamic Scaling Fusion Strategy

Digital Signal Processing, Journal Year: 2025, Volume and Issue: unknown, P. 105252 - 105252

Published: April 1, 2025

Language: Английский

---