Multi-Level Classification Based on Trajectory Features of Time Series for Monitoring Impervious Surface Expansions

Wang, Beibei; Chen, Zhenjie; Zhu, A‐Xing; Hao, Yuzhu; Xu, Changqing

doi:10.3390/rs11060640

Cited by 18 publications

(12 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, crops and forests usually have higher vegetation indices than grass in early spring, the crops will have lower VI values after harvest, and similar variations are found in some regions between crops and grasslands. Trajectory features are identified as characteristics for different class types, and are thus often applied to classifications [37,40]. Similar methods have been used for spectral curve matching by calculating the linear correlation coefficient between a test spectrum and a reference spectrum.…”

Section: Sim Methodsmentioning

confidence: 99%

An Effective Method for Generating Spatiotemporally Continuous 30 m Vegetation Products

Liang

Jin

2021

Remote Sensing

View full text Add to dashboard Cite

Leaf area index (LAI) and normalized difference vegetation index (NDVI) are key parameters for various applications. However, due to sensor tradeoff and cloud contaminations, these data are often temporally intermittent and spatially discontinuous. To address the discontinuities, this study proposed a method based on spectral matching of 30 m discontinuous values from Landsat data and 500 m temporally continuous values from Moderate-resolution Imaging Spectroradiometer (MODIS) data. Experiments have proven that the proposed method can effectively yield spatiotemporally continuous vegetation products at 30 m spatial resolution. The results for three different study areas with NDVI and LAI showed that the method performs well in restoring the time series, fills in the missing data, and reasonably predicts the images. Remarkably, the proposed method could address the issue when no cloud-free data pairs are available close to the prediction date, because of the temporal information “borrowed” from coarser resolution data. Hence, the proposed method can make better use of partially obscured images. The reconstructed spatiotemporally continuous data have great potential for monitoring vegetation, agriculture, and environmental dynamics.

show abstract

Section: Sim Methodsmentioning

confidence: 99%

An Effective Method for Generating Spatiotemporally Continuous 30 m Vegetation Products

Liang

Jin

2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The image layers were set to one for all bands to avoid any bias [56][57][58][59]. Then, the segmentation parameter was selected and the shape parameters and compactness parameters were determined via trial-and-error [58,60,61]. The specific process included first setting the range of shape and compactness to 0.1-0.9 and the change step to 0.1.…”

Section: Multiresolution Segmentation Using Ts Imagesmentioning

confidence: 99%

“…The five land use types considered in this study were water area, woodland, paddy field, construction land, and dry land (Table 2). NDVI, NDBI, and MNDWI are commonly used indices for analyzing Landsat images [7,60]. NDVI can be used to separate land with dense vegetation cover from that with other uses.…”

Section: Construction Of Multivariate Tsmentioning

confidence: 99%

Bidirectional Segmented Detection of Land Use Change Based on Object-Level Multivariate Time Series

et al. 2020

Self Cite

View full text Add to dashboard Cite

High-precision information regarding the location, time, and type of land use change is integral to understanding global changes. Time series (TS) analysis of remote sensing images is a powerful method for land use change detection. To address the complexity of sample selection and the salt-and-pepper noise of pixels, we propose a bidirectional segmented detection (BSD) method based on object-level, multivariate TS, that detects the type and time of land use change from Landsat images. In the proposed method, based on the multiresolution segmentation of objects, three dimensions of object-level TS are constructed using the median of the following indices: the normalized difference vegetation index (NDVI), the normalized difference built index (NDBI), and the modified normalized difference water index (MNDWI). Then, BSD with forward and backward detection is performed on the segmented objects to identify the types and times of land use change. Experimental results indicate that the proposed BSD method effectively detects the type and time of land use change with an overall accuracy of 90.49% and a Kappa coefficient of 0.86. It was also observed that the median value of a segmented object is more representative than the commonly used mean value. In addition, compared with traditional methods such as LandTrendr, the proposed method is competitive in terms of time efficiency and accuracy. Thus, the BSD method can promote efficient and accurate land use change detection.

show abstract

“…Former rural areas are becoming a part of an ever increasing urban landscape. As residential developments, commercial properties, and industrial facilities increase, they cover the natural landscape with roads, buildings, parking lots, and other impervious surfaces (Wang et al, 2019). Stream health can be directly linked to urbanization, the effects of which simultaneously decrease bank stability and increase pollutant presence and transfer.…”

Section: Effects Of Urbanizationmentioning

confidence: 99%

Prioritizing riparian corridors for ecosystem restoration in urbanizing watersheds

Atkinson

Lake

2020

PeerJ

View full text Add to dashboard Cite

Background Riparian corridors can affect nutrient, organic matter, and sediment transport, all of which shape water quality in streams and connected downstream waters. When functioning riparian corridors remain intact, they provide highly valued water quality ecosystem services. However, in rapidly urbanizing watersheds, riparian corridors are susceptible to development modifications that adversely affect those ecosystem services. Protecting high quality riparian corridors or restoring low quality corridors are widely advocated as watershed level water quality management options for protecting those ecosystem services. The two approaches, protection or restoration, should be viewed as complementary by watershed managers and provide a foundation for targeting highly functioning riparian corridors for protection or for identifying poorly functioning corridors for restoration. Ascertaining which strategy to use is often motivated by a specific ecosystem service, for example water quality, upon which watershed management is focused. We have previously reported on a spatially explicit model that focused on identifying riparian corridors that have specific characteristics that make them well suited for purposes of preservation and protection focused on water quality. Here we hypothesize that focusing on restoration, rather than protection, can be the basis for developing a watershed level strategy for improving water quality in urbanizing watersheds. Methods The model described here represents a geographic information system (GIS) based approach that utilizes riparian characteristics extracted from 40-meter wide corridors centered on streams and rivers. The model focuses on drinking water reservoir watersheds that can be analyzed at the sub-watershed level. Sub-watershed riparian data (vegetation, soil erodibility and surface slope) are scaled and weighted based on watershed management theories for water quality, and riparian restoration scores are assigned. Those scores are used to rank order riparian zones –the lower the score the higher the priority for riparian restoration. Results The model was applied to 90 sub-watersheds in the watershed of an important drinking water reservoir in north central Texas, USA. Results from this study area suggest that corridor scores were found to be most correlated to the amount of: forested vegetation, residential land use, soils in the highest erodibility class, and highest surface slope (r2 = 0.92, p < 0.0001). Scores allow watershed managers to rapidly focus on riparian corridors most in need of restoration. A beneficial feature of the model is that it also allows investigation of multiple scenarios of restoration strategies (e.g., revegetation, soil stabilization, flood plain leveling), giving watershed managers a tool to compare and contrast watershed level management plans.

show abstract

Multi-Level Classification Based on Trajectory Features of Time Series for Monitoring Impervious Surface Expansions

Cited by 18 publications

References 49 publications

An Effective Method for Generating Spatiotemporally Continuous 30 m Vegetation Products

An Effective Method for Generating Spatiotemporally Continuous 30 m Vegetation Products

Bidirectional Segmented Detection of Land Use Change Based on Object-Level Multivariate Time Series

Prioritizing riparian corridors for ecosystem restoration in urbanizing watersheds

Contact Info

Product

Resources

About