Impact of landscape patterns on ecological vulnerability and ecosystem service values: An empirical analysis of Yancheng Nature Reserve in China

Zang, Zheng; Zou, Xinqing; Zuo, Ping; Song, Qiaochu; Wang, Chenglong; Wang, Junjie

doi:10.1016/j.ecolind.2016.08.019

Cited by 126 publications

(56 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remote sensing imageries were masked using the region boundary. ENVI V4.3 and ArcGIS V10.0 were used to conduct a series of preprocessing procedures, including geometric correction (Map Registration), band synthesis (Layer Stacking), and interpretation (Zuo et al 2004;Zang et al 2017).…”

Section: Image Interpretationmentioning

confidence: 99%

“…These indices are a collection of indicators in landscape ecology that can be computed with the aid of geographic information systems and patch statistics software (McGarigal et al 2012;Plexida et al 2014). Landscape fragmentation is the process of gradual landscape evolution from a single, homogeneous, continuous whole landscape to complex, heterogeneous, discontinuous patch mosaics due to the combined effects of human and natural factors (Zang et al 2017).…”

Section: Landscape Pattern Indicesmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of the spatiotemporal correlation between vegetation pattern and human activity intensity in Yancheng coastal wetland, China

Zang

Zou

Song

et al. 2019

Anthropocene Coasts

Self Cite

View full text Add to dashboard Cite

Remote sensing images were used to reproduce the changes in wetland vegetation since 1987, and the potential impact of policy changes and human activities on vegetation restoration and biodiversity conservation in coastal wetlands was explored based on the landscape pattern index and the human disturbance index (HDI). The results showed that the vegetation displayed a zonal distribution pattern in which, perpendicular to the coastline early in the study period, the vegetation type changed from coastal wetland to bare mud flat with Spartina alterniflora, Suaeda glauca, and Phragmites australis as well as to constructed wetlands dominated by rice. Under the influence of human activities, the number of patches (NP) and mean nearest-neighbor distance (MNN) between patches gradually increased during the study period, while the mean patch size gradually decreased. The patch density increased from 179 (1987) to 296 patches per ha (2013). Additionally, human activity in the study area intensified. The HDI increased from 0.353 (1987) to 0.471 (1987) and showed positive correlations (R2 > 80%, p < 0.01) with NP and MNN. Human activity, such as changes in land use, resulted in more fragmented vegetation patterns, and the nonzonal (intrazonal) distribution of the vegetation became more obvious in coastal wetlands.

show abstract

Section: Image Interpretationmentioning

confidence: 99%

Section: Landscape Pattern Indicesmentioning

confidence: 99%

Analysis of the spatiotemporal correlation between vegetation pattern and human activity intensity in Yancheng coastal wetland, China

Zang

Zou

Song

et al. 2019

Anthropocene Coasts

Self Cite

View full text Add to dashboard Cite

show abstract

“…The tidal vegetation areas can be divided into four categories of the mud, salt living wormwood, prevailing lalang grass, and dominated reed belts. The ecological elements of sea, river, mud, catchment, shrub, and grassland mainly become the discriminative morphologic characteristics (L. Huang et al, ; Zang et al, ). Zoige wetland contains the largest high‐altitude peat‐substrate swamp area in the world. It is located at the upstream of the Yellow River in the northern Sichuan Province and extends into southern Gansu Province and southeastern Qinghai Province and the geographical coordinates are 33°25′–34°00′N; 102°28′–102°59′E; 3,422–3,704 m. With an area of 260,000 hectares, it lies between the west of the Min Mountains and the east of the Amne Machin mountain.…”

Section: Experimental Data and Devicesmentioning

confidence: 99%

Section: Characteristics Of Wetlandsmentioning

confidence: 99%

“…To deal with these challenges, we introduced a deep-level cascade discriminative model based on convolutional neural networks (CNN) architecture (Esteva et al, 2017;LeCun, Bengio, & Hinton, 2015;Wang, Peng, Ma, & Xu, 2016) for identifying the WVM in the Ramsar sites list. There were four different classes of wetlands in our investigation, including DongZhai Harbor (DZH) intertidal mangrove wetland (Tang et al, 2014;Xi, Li, Xia, & Qu, 2016), Lashi Lake (LSL) alpine peat wetland (Y. C. Huang, Tian, Yue, Liu, & Lai, 2012;Liao, Ye, Huang, & Peng, 2017), Yancheng (YC) coastal saline wetland (L. Huang et al, 2015;Zang et al, 2017), and Zoige plateau freshwater lake wetland (Jiang, Lv, Wang, Chen, & Liu, 2017;Li et al, 2014) in China. We followed deep-level AlexNet CNN network structures (Krizhevsky, Sutskever, & Hinton, 2012;Srivastava, Hinton, Krizhevsky, Sutskever, & Salakhutdinov, 2014) to construct the WVM identification model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence classification of wetland vegetation morphology based on deep convolutional neural network

Lin

et al. 2019

Natural Resource Modeling

View full text Add to dashboard Cite

In real-world wetland vegetation morphology (WVM) detection, large scene variations such as those due to landform, vegetation, sunlight, weather, and sky, as well as camera parameter settings such as focal length and shooting angle, require systematic and complicated artificial intelligence technology to accurately discriminate inter and intra-class wetland objections. To deal with these challenges, we introduced a deep-level discriminative model based on convolutional neural networks (CNN) for classifying the images of DongZhai Harbor intertidal, Lashi Lake alpine, Yancheng coastal and Zoige plateau wetlands in China. A 96-dimensional convolution operation with kernel sizes of 11 × 11 × 3 first applied to the resized 227 × 227 WVM input pictures to acquire the effective morphologic features. The perceptron layers of the rectified linear unit and the batch normalization were used in the middle layer to achieve the better gradient propagation property during the training process. The WVM features were down-sampled by the pooling networks to reduce the neuron dimensions. The fully connected layer linked to the output of the convolutional and pooling layers to obtain the high-level WVM species information for the final WVM classification purpose. The deep-level CNN-based method was compared with the traditional shallow-level feature-designed algorithms of conditional maximum entropy regression, multilayer perceptron and support vector machine. The deep-level algorithm showed the superior performance for detecting the WVM species, which provided a superior alternative routine for accurate artificial intelligence classification of WVM in the ecological engineering application. Recommendations for Resource Managers• This proposed artificial intelligence model can be used to effectively help people understand the macroscopic scene changes of ecological elements from the wetland vegetation morphology images. • The detection results show the robustness of the discriminative model, for it is not affected by the complex natural factors such as landform, vegetation, sunlight, weather, and sky, as well as human factors such as camera parameter settings of focal length and shooting angle to some extent. • The deep-level model based on the cascade convolution framework can be used to extract more distinguishing detailed ecological features from the original wetland vegetation morphology images compared with the shallow-level algorithms using a single convolutional layer. K E Y W O R D S classification, convolutional neural network, ecological engineering, vegetation morphology, wetland

show abstract

Variation of the floodplain forest ecosystem service value in the lower reaches of Tarim River, China

et al. 2017

View full text Add to dashboard Cite

Ecosystem service and human activity assessment are essential for effective natural resources allocation; however, these were seldom researched in arid region. This study used the theory proposed by Millennium Ecosystem Assessment to analyse ecosystem services provided by the floodplain forest in the lower reaches of the Tarim River. Results showed the following: (a) In the research area, the ecosystem service values of approximately US$216.78 × 108 occurring from 1972 to 2015 showed a decreasing trend; (b) the total ecosystem service values for floodplain forest and water area for all land use and land cover types accounted for 87.43% of the total value in the research area, and water supply, biodiversity protection, and waste treatment accounted for 55% of the total function values—these were the highest service values; (c) this research showed that the estimated ecosystem service values of research area were inelastic to value coefficients. This study showed that future work should allow land use and Ecological Water Conveyance Project to follow with rigorous environmental impact analyses. These analyses will be crucial to maintain the stability and sustainable development in the lower reaches of the Tarim River and also can provide references for research in the arid regions of Northwest China and Central Asia.

show abstract

Impact of landscape patterns on ecological vulnerability and ecosystem service values: An empirical analysis of Yancheng Nature Reserve in China

Cited by 126 publications

References 38 publications

Analysis of the spatiotemporal correlation between vegetation pattern and human activity intensity in Yancheng coastal wetland, China

Analysis of the spatiotemporal correlation between vegetation pattern and human activity intensity in Yancheng coastal wetland, China

Artificial intelligence classification of wetland vegetation morphology based on deep convolutional neural network

Variation of the floodplain forest ecosystem service value in the lower reaches of Tarim River, China

Contact Info

Product

Resources

About