Yuwei Guan

Yuwei Guan


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 February 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JHJiarun Huang
Jiarun Huang
ZHZhili He
Zhili He
YGYuwei Guan
Yuwei Guan
HZHongguo Zhang
Hongguo Zhang
Forest fires can destroy forest and inflict great damage to the ecosystem. Fortunately, forest fire detection with video has achieved remarkable results in enabling timely and accurate fire warnings. However, the traditional forest fire detection method relies heavily on artificially designed features; CNN-based methods require a large number of parameters. In addition, forest fire detection is easily disturbed by fog. To solve these issues, a lightweight YOLOX-L and defogging algorithm-based forest fire detection method, GXLD, is proposed. GXLD uses the dark channel prior to defog the image to obtain a fog-free image. After the lightweight improvement of YOLOX-L by GhostNet, depth separable convolution, and SENet, we obtain the YOLOX-L-Light and use it to detect the forest fire in the fog-free image. To evaluate the performance of YOLOX-L-Light and GXLD, mean average precision (mAP) was used to evaluate the detection accuracy, and network parameters were used to evaluate the lightweight effect. Experiments on our forest fire dataset show that the number of the parameters of YOLOX-L-Light decreased by 92.6%, and the mAP increased by 1.96%. The mAP of GXLD is 87.47%, which is 2.46% higher than that of YOLOX-L; and the average fps of GXLD is 26.33 when the input image size is 1280 × 720. Even in a foggy environment, the GXLD can detect a forest fire in real time with a high accuracy, target confidence, and target integrity. This research proposes a lightweight forest fire detection method (GXLD) with fog removal. Therefore, GXLD can detect a forest fire with a high accuracy in real time. The proposed GXLD has the advantages of defogging, a high target confidence, and a high target integrity, which makes it more suitable for the development of a modern forest fire video detection system.

1 September 2025 in Frontiers in Environmental Science
Verified
Journal Article
Open access
PDF file
QLQingqu Luo
Qingqu Luo
YGYuwei Guan
Yuwei Guan
XLXiangqi Lei
Xiangqi Lei
The rapid acceleration of urbanization, coupled with intensified human activities, has exacerbated the tension between human development and the ecological environment. This issue is particularly pronounced in Jiangsu Province, a major economic and commercial hub in China. Achieving a balance between ecological environmental quality and urbanization levels is critical for promoting regional sustainable development, with significant implications for both ecosystem management and urban planning. To investigate the intricate interactions between the ecological environment and urbanization in Jiangsu Province, we employed the Modified Remote Sensing Ecological Index (MRSEI) model, utilizing Google Earth Engine (GEE) and MODIS imagery to construct an ecological environmental quality assessment for the province from 2002 to 2022. Concurrently, the Population–Economic–Sociology–Space (PESS) model, combined with socioeconomic data and the Analytical Hierarchy Process–Criteria Importance Through Intercriteria Correlation (AHP-CRITIC) weighting method, was used to develop the Urbanization Level Index (ULI). The coupling coordination degree (CCD) model was applied to analyze the coordination relationship between the ecological environment and urbanization, while the Geodetector was used to identify the key factors influencing the MRSEI. The findings include: (1) the MRSEI incorporates more comprehensive indicator information than the RSEI and demonstrates greater sensitivity in capturing greenness and dryness variations in Jiangsu Province; (2) the ecological environment in northern Jiangsu has shown steady improvement, whereas southern Jiangsu experienced significant deterioration from 2002 to 2010, followed by recovery and stabilization from 2010 to 2022; (3) the urbanization level in southern Jiangsu is higher and has grown rapidly, while urbanization in northern Jiangsu accelerated after 2014 but remains at a lower level compared to the south; (4) the urbanization lag in northern Jiangsu and the eco-environment lag in southern Jiangsu have both improved, enhancing the overall coordination between ecological environment and urbanization; and (5) Jiangsu Province exhibits a significant heat island effect, with improvements in greenness, heat, and dryness having a positive influence on the MRSEI. This research provides an analytical framework and theoretical insights to address the persistent conflict between urbanization and ecological sustainability. The findings offer a scientific basis for policy formulation, supporting regional sustainable development strategies and urban planning in rapidly urbanizing areas.

14 September 2017 in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Verified
Journal Article
Open access
PDF file
MMM. Ma
M. Ma
BHBinbin He
Binbin He
YGYuwei Guan
Yuwei Guan
HZHongguo Zhang
Hongguo Zhang
SSS. Song
S. Song
Keywords: Wind energy resource, Assessment, Global, Utilization potential, Remote sensing, ERA-Interim, Data mining Development of wind energy resource (WER) is a key to deal with climate change and energy structure adjustment. A crucial issue is to obtain the distribution and variability of WER, and mine the suitable location to exploit it. In this paper, a multicriteria evaluation (MCE) model is constructed by integrating resource richness and stability, utilization value and trend of resource, natural environment with weights. The global resource richness is assessed through wind power density (WPD) and multi-level wind speed. The utilizable value of resource is assessed by the frequency of effective wind. The resource stability is assessed by the coefficient of variation of WPD and the frequency of prevailing wind direction. Regression slope of long time series WPD is used to assess the trend of WER. All of the resource evaluation indicators are derived from the atmospheric reanalysis data ERA-Interim with spatial resolution 0.125°. The natural environment factors mainly refer to slope and land-use suitability, which are derived from multi-resolution terrain elevation data 2010 (GMTED 2010) and GlobalCover2009. Besides, the global WER utilization potential map is produced, which shows most high potential regions are located in north of Africa. Additionally, by verifying that 22.22 % and 48.8 9% operational wind farms fall on medium-high and high potential regions respectively, the result can provide a basis for the macroscopic siting of wind farm.