Continuous Change Detection of Forest/Grassland and Cropland in the Loess Plateau of China Using All Available Landsat Data

Wang, Zhihui; Yao, Wei; Tang, Qiuhong; Liu, Liangyun; Xiao, Peiqing; Kong, Xianwen; Zhang, Pan; Shi, Fangxin; Wang, Yuanjian

doi:10.3390/rs10111775

Cited by 24 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the values of NDVI and in the interpretation of Google Earth images to identify and to quantify the vegetation change during the analysis period (1987-2017), we applied an NDVI thresholding [45,46] to classify NDVI into three classes: (1) NDVI values below to 0.2 were considered as low-density vegetation (2) NDVI values between 0.2 and 0.5 were considered as moderate-density vegetation and (3) NDVI values higher than 0.5 were considered as high-density vegetation. This classification depends on the soil type and, in this case, is based on the knowledge of the study area characteristics.…”

Section: Ndvi Classificationmentioning

confidence: 99%

Land Use/Land Cover (LULC) Using Landsat Data Series (MSS, TM, ETM+ and OLI) in Azrou Forest, in the Central Middle Atlas of Morocco

et al. 2018

View full text Add to dashboard Cite

The study of land use/land cover (LULC) has become an increasingly important stage in the development of forest ecosystems strategies. Hence, the main goal of this study was to describe the vegetation change of Azrou Forest in the Middle Atlas, Morocco, between 1987 and 2017. To achieve this, a set of Landsat images, including one Multispectral Scanner (MSS) scene from 1987; one Enhanced Thematic Mapper Plus (ETM+) scene from 2000; two Thematic Mapper (TM) scenes from 1995 and 2011; and one Landsat 8 Operational Land Imager (OLI) scene from 2017; were acquired and processed. Ground-based survey data and the normalized difference vegetation index (NDVI) were used to identify and to improve the discrimination between LULC categories. Then, the maximum likelihood (ML) classification method was applied was applied, in order to produce land cover maps for each year. Three classes were considered by the classification of NDVI value: low-density vegetation; moderate-density vegetation, and high-density vegetation. Our study achieved classification accuracies of 66.8% (1987), 99.9% (1995), 99.8% (2000), 99.9% (2011), and 99.9% (2017). The results from the Landsat-based image analysis show that the area of low-density vegetation was decreased from 27.4% to 2.1% over the past 30 years. While, in 2017, the class of high-density vegetation was increased to 64.6% of the total area of study area. The results of this study show that the total forest cover remained stable. The present study highlights the importance of the image classification algorithms combined with NDVI index for better understanding the changes that have occurred in this forest. Therefore, the findings of this study could assist planners and decision-makers to guide, in a good manner, the sustainable land development of areas with similar backgrounds.

show abstract

Section: Ndvi Classificationmentioning

confidence: 99%

Land Use/Land Cover (LULC) Using Landsat Data Series (MSS, TM, ETM+ and OLI) in Azrou Forest, in the Central Middle Atlas of Morocco

et al. 2018

View full text Add to dashboard Cite

show abstract

“…To solve this problem, the riparian vegetation degradation in the river terrace was used to represent the building construction in the river terrace, and NDVI was employed to discriminate the river channel-built-up area interface in this study. In addition, a multi-year criterion in the detection rules [40] is helpful to guarantee that the rules are not satisfied by an accidental vegetation change caused by rainfall or anthropogenic factors, thus improving the detection accuracy. Note that, due to local farmers growing crops in the river terrace, the land-cover type of the river terrace is always vegetation, which can be easily monitored using NDVI time-series.…”

Section: Application Of Detection Methods For River Channel Occupationmentioning

confidence: 99%

“…The pixels with an NDVI value above 0.21 were assigned as non-built-up. For each pixel, the NDVI time-series of the pixels within the built-up area interpreted by GF-2 high-resolution images were assessed by referencing the detection rules of the previous study of Wang et al [40], as follows.…”

Section: River Channel Dynamic Detection Using Ndvi Time-series and Hmentioning

confidence: 99%

The Influence of River Channel Occupation on Urban Inundation and Sedimentation Induced by Floodwater in Mountainous Areas: A Case Study in the Loess Plateau, China

et al. 2019

Self Cite

View full text Add to dashboard Cite

River channel occupation has made cities in the mountainous areas more vulnerable to floodwater out of river channels during rapid global urbanization. A better understanding of the influence of river channel occupation on urban flood disasters can serve as a reference in planning effective urban flood control strategies. In this study, taking a flood event that occurred on July 26th, 2017 in a city on the Loess Plateau as an example, field surveys, dynamics detection of the river channel using remote sensing technology, and scenario simulations with a two-dimensional flow and sediment model were utilized to quantitatively analyze the impacts of river channel occupation on urban inundation and sedimentation. The results show that river channel dynamics reduced by construction can be successfully detected using the combination of high-resolution images and Landsat time-series images. The variation of the water level–discharge relationship caused by the narrowing of the river channel and the increase of the flood-water level caused by water-blocking bridges/houses result in a significant reduction of the flood discharge capacity. The contribution of the narrowing of the river channel was 72.3% for the total area inundated by floodwater, whereas 57.2% of urban sedimentation was caused by the construction of bridges/houses within the river channel. Sustainable flood mitigation measures were also recommended according to the investigations and research findings in this study in order to reduce the social, environmental and economic damages caused by floods.

show abstract

“…Specifically, it has been established that there is no statistical difference (p = 0.303) between changes in coral habitat areas as observed by the Coral Reef Evaluation and Monitoring Project (CREMP) and change detection analysis conducted using a combination of Landsat missions [41]. Additional validation studies demonstrated that change analysis conducted based on Landsat 5, Landsat 7, and Landsat 8 was accurate with an overall accuracy of 88.9% ± 1.0% and a kappa coefficient of 0.86 [46]. This study expands upon the previous limited scope analyses by applying a classifier to two new sites [47][48][49][50][51].…”

Section: Introductionmentioning

confidence: 96%

Coral Reef Change Detection in Remote Pacific Islands Using Support Vector Machine Classifiers

2019

View full text Add to dashboard Cite

Despite the abundance of research on coral reef change detection, few studies have been conducted to assess the spatial generalization principles of a live coral cover classifier trained using remote sensing data from multiple locations. The aim of this study is to develop a machine learning classifier for coral dominated benthic cover-type class (CDBCTC) based on ground truth observations and Landsat images, evaluate the performance of this classifier when tested against new data, then deploy the classifier to perform CDBCTC change analysis of multiple locations. The proposed framework includes image calibration, support vector machine (SVM) training and tuning, statistical assessment of model accuracy, and temporal pixel-based image differencing. Validation of the methodology was performed by cross-validation and train/test split using ground truth observations of benthic cover from four different reefs. These four locations (Palmyra Atoll, Kingman Reef, Baker Island Atoll, and Howland Island) as well as two additional locations (Kiritimati Island and Tabuaeran Island) were then evaluated for CDBCTC change detection. The in-situ training accuracy against ground truth observations for Palmyra Atoll, Kingman Reef, Baker Island Atoll, and Howland Island were 87.9%, 85.7%, 69.2%, and 82.1% respectively. The classifier attained generalized accuracy scores of 78.8%, 81.0%, 65.4%, and 67.9% for the respective locations when trained using ground truth observations from neighboring reefs and tested against the local ground truth observations of each reef. The classifier was trained using the consolidated ground truth data of all four sites and attained a cross-validated accuracy of 75.3%. The CDBCTC change detection analysis showed a decrease in CDBCTC of 32% at Palmyra Atoll, 25% at Kingman Reef, 40% at Baker Island Atoll, 25% at Howland Island, 35% at Tabuaeran Island, and 43% at Kiritimati Island. This research establishes a methodology for developing a robust classifier and the associated Controlled Parameter Cross-Validation (CPCV) process for evaluating how well the model will generalize to new data. It is an important step for improving the scientific understanding of temporal change within coral reefs around the globe.

show abstract

Continuous Change Detection of Forest/Grassland and Cropland in the Loess Plateau of China Using All Available Landsat Data

Cited by 24 publications

References 41 publications

Land Use/Land Cover (LULC) Using Landsat Data Series (MSS, TM, ETM+ and OLI) in Azrou Forest, in the Central Middle Atlas of Morocco

Land Use/Land Cover (LULC) Using Landsat Data Series (MSS, TM, ETM+ and OLI) in Azrou Forest, in the Central Middle Atlas of Morocco

The Influence of River Channel Occupation on Urban Inundation and Sedimentation Induced by Floodwater in Mountainous Areas: A Case Study in the Loess Plateau, China

Coral Reef Change Detection in Remote Pacific Islands Using Support Vector Machine Classifiers

Contact Info

Product

Resources

About