Yan Peng

Ms. Yan Peng

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
15 May 2018 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Wei JiangWei Jiang
Wei Jiang
GHGuojin He
Guojin He
Tengfei longTengfei long
Tengfei long
YNYuan Ni
Yuan Ni
HLHuichan Liu
Huichan Liu
GWGuizhou Wang
Guizhou Wang
Surface water mapping is essential for monitoring climate change, water resources, ecosystem services and the hydrological cycle. In this study, we adopt a multilayer perceptron (MLP) neural network to identify surface water in Landsat 8 satellite images. To evaluate the performance of the proposed method when extracting surface water, eight images of typical regions are collected, and a water index and support vector machine are employed for comparison. Through visual inspection and a quantitative index, the performance of the proposed algorithm in terms of the entire scene classification, various surface water types and noise suppression is comprehensively compared with those of the water index and support vector machine. Moreover, band optimization, image preprocessing and a training sample for the proposed algorithm are analyzed and discussed. We find that (1) based on the quantitative evaluation, the performance of the surface water extraction for the entire scene when using the MLP is better than that when using the water index or support vector machine. The overall accuracy of the MLP ranges from 98.25–100%, and the kappa coefficients of the MLP range from 0.965–1. (2) The MLP can precisely extract various surface water types and effectively suppress noise caused by shadows and ice/snow. (3) The 1–7-band composite provides a better band optimization strategy for the proposed algorithm, and image preprocessing and high-quality training samples can benefit from the accuracy of the classification. In future studies, the automation and universality of the proposed algorithm can be further enhanced with the generation of training samples based on newly-released global surface water products. Therefore, this method has the potential to map surface water based on Landsat series images or other high-resolution images and can be implemented for global surface water mapping, which will help us better understand our changing planet.

7 May 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YPYan Peng
Yan Peng
GHGuojin He
Guojin He
GWGuizhou Wang
Guizhou Wang
HCHongjuan Cao
Hongjuan Cao
Dongting Lake plays an important role in water regulation and biodiversity protection, but it is vulnerable to climate change and human activities. To quantify surface water changes and factors driving them, long-term surface water variation in Dongting Lake was investigated using the multiple spectral indices method based on a decision tree classification for full time-series Landsat and MODIS datasets. Factors influencing surface water changes were explored by combining the annual maximum surface water and annual permanent occurrent water with meteorological and hydrological data. The results showed that both annual maximum surface water and annual permanent water decreased from 1975 to 2019 and the trends of rainfall and runoff at three outlets also changed. The annual maximum surface water surface of Dongting Lake increased during the 1990s due to high rainfall but decreased again after 2000. A significant change in both the hydrological stage and surface water sequence from 1986 to 2019 occurred in 2003, which coincided with the beginning of work to construct the Three Gorges Dam (TGD). The surface water decreased by about 360 km2 and runoff at the three outlets decreased by about 150 × 108 m3 after the impoundment of the TGD, which was likely the main cause of surface water changes after 2003. The area of surface water that changed from permanent water in the pre-TGD period into seasonally occurring water in the post-TGD periods is 209 km2, while the area of surface water that changed from seasonally occurring water in the pre-TGD period into permanent occurrent water in the post-TGD period is 31 km2. Meteorological elements and human activities have had a comprehensive impact on surface water changes in Dongting Lake. Rainfall and temperature account for about one-third of the influence on long-term changes of surface water, and rainfall is the main meteorological driving factor of surface water in the wet season, while temperature is the main factor in the dry season. Runoff at three outlets, four rivers and the Chenglingji explain about half of the change in surface water; the three outlets runoff is mainly affected by human activities and is the main hydrological driving factor of surface water. The monthly maximum surface water fluctuates regularly and Dongting Lake has a strong seasonal characteristic. Indeed, the seasonal changes are significantly altered when drought or flooding occurs, the causes of which are diverse and complex.

Verified
Journal Article
Open access
PDF file
Wei JiangWei Jiang
Wei Jiang
GHGuojin He
Guojin He
WLWanchun Leng
Wanchun Leng
Tengfei longTengfei long
Tengfei long
GWGuizhou Wang
Guizhou Wang
HGHongxiang Guo
Hongxiang Guo
Protected areas (PAs) with natural, ecological, and cultural value play important roles related to biological processes, biodiversity, and ecosystem services. Over the past four decades, the spatial range and intensity of light pollution in China has experienced an unprecedented increase. Few studies have been documented on the light pollution across PAs in China, especially in regions that provide a greater amount of important biodiversity conservation. Here, nighttime light satellite images from the Defense Meteorological Satellite Program Operational Linescan System (DMSP-OLS) were selected to characterize light pollution trends across PAs using nighttime light indexes and hot spot analysis, and then the light pollution changes in PAs were classified. Furthermore, the causes of light pollution changes in PAs were determined using high-resolution satellite images and statistical data. The results showed the following: (1) Approximately 57.30% of PAs had an increasing trend from 1992 to 2012, and these PAs were mainly located in the eastern region, the central region, and a small part of the western region of China. Hot spot analysis showed that the patterns of change for the total night light and night light mean had spatial agglomeration characteristics; (2) The PAs affected by light pollution changes were divided into eight classes, of which PAs with stable trends accounted for 41%, and PAs with high increasing trends accounted for 10%. PAs that had high increasing trends with low density accounted for the smallest amount, i.e., only 1%; (3) The factors influencing light pollution changes in PAs included the distance to urban areas, mineral exploitation, and tourism development and the migration of residents. Finally, based on the status of light pollution encroachment into PAs, strategies to control light pollution and enhance the sustainable development of PAs are recommended.

7 July 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FHFangzhou Hong
Fangzhou Hong
GHGuojin He
Guojin He
GWGuizhou Wang
Guizhou Wang
Zhaoming ZhangZhaoming Zhang
Zhaoming Zhang
YPYan Peng
Yan Peng
Coal is the most prevalent energy source in China and plays an important role in ensuring energy security. The continuous monitoring of coal mining activities is helpful to clarify the incremental space of coal production and establish a rational framework for future coal production capacity. In this study, a multi-source remote sensing approach utilizing SPOT 4, GF, and Landsat data is employed to monitor land cover and vegetation changes in the Juhugeng mining area of the Muli coalfield over a span of nearly 20 years. The analysis incorporates an object-oriented classification method and a vegetation parameter to derive insights. The findings reveal that the mining operations can be divided into two periods, since their initiation in 2003 until their cessation in 2021, with a dividing point around 2013/2014. The initial phase witnessed rapid and even accelerated expansion of the mine, while the subsequent phase was characterized by more stable development and the implementation of some restorative measures for the mine environment. Although the vegetation parameter, Fractional Vegetation Cover (FVC), indicates some reclamation efforts within the mining area, the extent of the reclaimed land remains limited. This study demonstrates the effective application of object-oriented classification in conjunction with the vegetation parameter FVC for monitoring coal mining areas.

19 October 2024 in Earth's Future
Verified
Journal Article
Open access
BQBaoye Qi
Baoye Qi
Zhaoming ZhangZhaoming Zhang
Zhaoming Zhang
Tengfei longTengfei long
Tengfei long
GHGuojin He
Guojin He
GWGuizhou Wang
Guizhou Wang
ZXZekun Xu
Zekun Xu
Fire significantly contributes to greenhouse gas emissions. The current global burned area (BA) products mainly have coarse native spatial resolution, which leads to underestimation of global BA and carbon emissions from biomass burning. Performances of BA products in Africa from GABAM (30 m), MCD64A1 (500 m), GFED4s (0.25°), FireCCI51 (250 m), and GFED5 (0.25°) were compared. From 2014 to 2020, GFED5 detected the most BA, 1.58 times more than GABAM during the same period. GABAM detected 0.09 Mkm2 more burned area than FireCCI51 on average. From 2014 to 2016, GABAM detected an average of 2.99 Mkm2 of BA in Africa, which was 1.03 times more than GFED4s. From 2014 to 2021, the average African BA derived from GABAM was 2.89 Mkm2, 1.22 times more than MCD64A1. The increase in BA will inevitably lead to an increase in the estimation of carbon emissions from biomass burning. Based on GABAM products and GFED framework, we estimated the average vegetation burning carbon emissions in Africa from 2014 to 2021 to be 1113.25 Tg, which is higher than GFED4s' carbon emissions in the same time period. This shows that the use of high‐resolution (30 m) burned area products to estimate carbon emissions can effectively avoid the underestimation of overall fire carbon emissions.

25 April 2019 in Remote Sensing
Verified
Journal Article
Open access
PDF file
YPYan Peng
Yan Peng
Zhaoming ZhangZhaoming Zhang
Zhaoming Zhang
GHGuojin He
Guojin He
MWMingyue Wei
Mingyue Wei
An improved GrabCut method based on a visual attention model is proposed to extract rare-earth ore mining area information using high-resolution remote sensing images. The proposed method makes use of advantages of both the visual attention model and GrabCut method, and the visual attention model was referenced to generate a saliency map as the initial of the GrabCut method instead of manual initialization. Normalized Difference Vegetation Index (NDVI) was designed as a bound term added into the Energy Function of GrabCut to further improve the accuracy of the segmentation result. The proposed approach was employed to extract rare-earth ore mining areas in Dingnan County and Xunwu County, China, using GF-1 (GaoFen No.1 satellite launched by China) and ALOS (Advanced Land Observation Satellite) high-resolution remotely-sensed satellite data, and experimental results showed that FPR (False Positive Rate) and FNR (False Negative Rate) were, respectively, lower than 12.5% and 6.5%, and PA (Pixel Accuracy), MPA (Mean Pixel Accuracy), MIoU (Mean Intersection over Union), and FWIoU (frequency weighted intersection over union) all reached up to 90% in four experiments. Comparison results with traditional classification methods (such as Object-oriented CART (Classification and Regression Tree) and Object-oriented SVM (Support Vector Machine)) indicated the proposed method performed better for object boundary identification. The proposed method could be useful for accurate and automatic information extraction for rare-earth ore mining areas.