scholarly journals The Potential of Open Geodata for Automated Large-Scale Land Use and Land Cover Classification

2019 ◽  
Vol 11 (19) ◽  
pp. 2249 ◽  
Author(s):  
Patrick Leinenkugel ◽  
Ramona Deck ◽  
Juliane Huth ◽  
Marco Ottinger ◽  
Benjamin Mack
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Large Scale ◽  
Natura 2000 ◽  
High Potential ◽  
Training Data ◽  
Data Generation ◽  
Data Set ◽  
Similar Accuracy ◽  
Landsat Satellite

This study examines the potential of open geodata sets and multitemporal Landsat satellite data as the basis for the automated generation of land use and land cover (LU/LC) information at large scales. In total, six openly available pan-European geodata sets, i.e., CORINE, Natura 2000, Riparian Zones, Urban Atlas, OpenStreetMap, and LUCAS in combination with about 1500 Landsat-7/8 scenes were used to generate land use and land cover information for three large-scale focus regions in Europe using the TimeTools processing framework. This fully automated preprocessing chain integrates data acquisition, radiometric, atmospheric and topographic correction, spectral–temporal feature extraction, as well as supervised classification based on a random forest classifier. In addition to the evaluation of the six different geodata sets and their combinations for automated training data generation, aspects such as spatial sampling strategies, inter and intraclass homogeneity of training data, as well as the effects of additional features, such as topography and texture metrics are evaluated. In particular, the CORINE data set showed, with up to 70% overall accuracy, high potential as a source for deriving dominant LU/LC information with minimal manual effort. The intraclass homogeneity within the training data set was of central relevance for improving the quality of the results. The high potential of the proposed approach was corroborated through a comparison with two similar LU/LC data sets, i.e., GlobeLand30 and the Copernicus High Resolution Layers. While similar accuracy levels could be observed for the latter, for the former, accuracy was considerable lower by about 12–24%.

scholarly journals Land Cover Change Dynamics and their Impacts on Thermal Environment of Dadri Block, Gautam Budh Nagar, India

2020 ◽  
Vol 13 (2) ◽  
pp. 1-13
Author(s):  
Sushma Shastri ◽  
Prafull Singh ◽  
Pradipika Verma ◽  
Praveen Kumar Rai ◽  
A. P. Singh
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Land Surface ◽  
Large Scale ◽  
Thermal Environment ◽  
Negative Impact ◽  
Information Source ◽  
Physical Parameters ◽  
Change Analysis ◽  
Landsat Satellite

AbstractLand use / land cover (LULC) has been considered as one of the important bio-physical parameters and have significant affect on local environmental change, particularly increasing anthropogenic temperature. Remote sensing images from Landsat series satellites are a major information source for LULC change analysis. In the present investigation, long term changes in LULC and its negative impact on land surface temperature (LST) were analyzed using multi-temporal Landsat satellite images between 2000 to 2016. firstly LULC of the study area has been classified and temporal changes in land use classes were quantify, and observed that in most of the land use classes such as vegetation (-1.28 %), water bodies (-1.65 %), agriculture (-3.52) and open land (-2.43 %) have shown negative change, however large scale positive changes in built-up area (+8.87 %) has been observed during the analysis, which is mainly due to continuous urbanization and growth of population in the area. The classified thermal images from the same period also show mean temperature of the area has increased by 1.60 °C since last 16 years. The observation from the present study reveals that due to the large-scale land use change practices in urban and peri-urban area witnessed for the rising temperature due to loss natural vegetation and other natural resources.

Quantifying Uncertainty in Land-Use/Land-Cover Classification Accuracy: A Stochastic Simulation Approach

2021 ◽  
Vol 9 ◽  
Author(s):  
Ke-Sheng Cheng ◽  
Jia-Yi Ling ◽  
Teng-Wei Lin ◽  
Yin-Ting Liu ◽  
You-Chen Shen ◽  
...  
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Stochastic Simulation ◽  
Classification Accuracy ◽  
Stochastic Simulations ◽  
Training Data ◽  
Land Use Land Cover ◽  
Simulation Approach ◽  
Data Set ◽  
Sample Data

In numerous applications of land-use/land-cover (LULC) classification, the classification rules are determined using a set of training data; thus, the results are inherently affected by uncertainty in the selection of those data. Few studies have assessed the accuracy of LULC classification with this consideration. In this article, we provide a general expression of various measures of classification accuracy with regard to the sample data set for classifier training and the sample data set for the evaluation of the classification results. We conducted stochastic simulations for LULC classification of a two-feature two-class case and a three-feature four-class case to show the uncertainties in the training sample and reference sample confusion matrices. A bootstrap simulation approach for establishing the 95% confidence interval of the classifier global accuracy was proposed and validated through rigorous stochastic simulation. Moreover, theoretical relationships among the producer accuracy, user accuracy, and overall accuracy were derived. The results demonstrate that the sample size of class-specific training data and the a priori probabilities of individual LULC classes must be jointly considered to ensure the correct determination of LULC classification accuracy.

scholarly journals Classification of Very-High-Spatial-Resolution Aerial Images Based on Multiscale Features with Limited Semantic Information

2021 ◽  
Vol 13 (3) ◽  
pp. 364
Author(s):  
Han Gao ◽  
Jinhui Guo ◽  
Peng Guo ◽  
Xiuwan Chen
Keyword(s):  
Deep Learning ◽  
Land Cover ◽  
Spatial Resolution ◽  
Large Scale ◽  
High Spatial Resolution ◽  
Training Data ◽  
Aerial Images ◽  
Rural Landscapes ◽  
Feature Representations ◽  
Object Based

Recently, deep learning has become the most innovative trend for a variety of high-spatial-resolution remote sensing imaging applications. However, large-scale land cover classification via traditional convolutional neural networks (CNNs) with sliding windows is computationally expensive and produces coarse results. Additionally, although such supervised learning approaches have performed well, collecting and annotating datasets for every task are extremely laborious, especially for those fully supervised cases where the pixel-level ground-truth labels are dense. In this work, we propose a new object-oriented deep learning framework that leverages residual networks with different depths to learn adjacent feature representations by embedding a multibranch architecture in the deep learning pipeline. The idea is to exploit limited training data at different neighboring scales to make a tradeoff between weak semantics and strong feature representations for operational land cover mapping tasks. We draw from established geographic object-based image analysis (GEOBIA) as an auxiliary module to reduce the computational burden of spatial reasoning and optimize the classification boundaries. We evaluated the proposed approach on two subdecimeter-resolution datasets involving both urban and rural landscapes. It presented better classification accuracy (88.9%) compared to traditional object-based deep learning methods and achieves an excellent inference time (11.3 s/ha).

scholarly journals Land Use Land Cover map segmentation using Remote Sensing: A Case study of Ajoy river watershed, India

2020 ◽  
Vol 30 (1) ◽  
pp. 273-286
Author(s):  
Kalyan Mahata ◽  
Rajib Das ◽  
Subhasish Das ◽  
Anasua Sarkar
Keyword(s):  
Land Use ◽  
Image Segmentation ◽  
Cellular Automata ◽  
Land Cover ◽  
Satellite Imagery ◽  
Current Model ◽  
Discrete Dynamical System ◽  
Land Use Land Cover ◽  
Data Set ◽  
Validity Indices

Abstract Image segmentation in land cover regions which are overlapping in satellite imagery, is one crucial challenge. To detect true belonging of one pixel becomes a challenging problem while classifying mixed pixels in overlapping regions. In current work, we propose one new approach for image segmentation using a hybrid algorithm of K-Means and Cellular Automata algorithms. This newly implemented unsupervised model can detect cluster groups using hybrid 2-Dimensional Cellular-Automata model based on K-Means segmentation approach. This approach detects different land use land cover areas in satellite imagery by existing K-Means algorithm. Since it is a discrete dynamical system, cellular automaton realizes uniform interconnecting cells containing states. In the second stage of current model, we experiment with a 2-dimensional cellular automata to rank allocations of pixels among different land-cover regions. The method is experimented on the watershed area of Ajoy river (India) and Salinas (California) data set with true class labels using two internal and four external validity indices. The segmented areas are then compared with existing FCM, DBSCAN and K-Means methods and verified with the ground truth. The statistical analysis results also show the superiority of the new method.

scholarly journals Application of remote sensing and GIS in land use/land cover mapping and change detection in Shasha forest reserve, Nigeria

2014 ◽  
Vol XL-8 ◽  
pp. 613-616 ◽  
Author(s):  
O. S. Olokeogun ◽  
K. Iyiola ◽  
O. F. Iyiola
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Change Detection ◽  
Sustainable Forest Management ◽  
Cost Effective ◽  
Remote Sensing And Gis ◽  
Clear Understanding ◽  
Forest Reserve ◽  
Landsat Satellite

Mapping of LULC and change detection using remote sensing and GIS techniques is a cost effective method of obtaining a clear understanding of the land cover alteration processes due to land use change and their consequences. This research focused on assessing landscape transformation in Shasha Forest Reserve, over an 18 year period. LANDSAT Satellite imageries (of 30 m resolution) covering the area at two epochs were characterized into five classes (Water Body, Forest Reserve, Built up Area, Vegetation, and Farmland) and classification performs with maximum likelihood algorithm, which resulted in the classes of each land use. <br><br> The result of the comparison of the two classified images showed that vegetation (degraded forest) has increased by 30.96 %, farmland cover increased by 22.82 % and built up area by 3.09 %. Forest reserve however, has decreased significantly by 46.12 % during the period. <br><br> This research highlights the increasing rate of modification of forest ecosystem by anthropogebic activities and the need to apprehend the situation to ensure sustainable forest management.

scholarly journals Change Detection Analysis Using Surveying and Geoinformatics Techniques

2018 ◽  
Vol 2 (1) ◽  
pp. 28-38
Author(s):  
I. C. Onuigbo ◽  
J. Y. Jwat
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Change Detection ◽  
Research Work ◽  
Temporal Data ◽  
Landsat Images ◽  
Detection Analysis ◽  
Ground Truthing ◽  
Landsat Satellite ◽  
Geoinformatics Techniques

The study was on change detection using Surveying and Geoinformatics techniques. For effective research study, Landsat satellite images and Quickbird imagery of Minna were acquired for three periods, 2000, 2005 and 2012. The research work demonstrated the possibility of using Surveying and Geoinformatics in capturing spatial-temporal data. The result of the research work shows a rapid growth in built-up land between 2000 and 2005, while the periods between 2005 and 2012 witnessed a reduction in this class. It was also observed that change by 2020 may likely follow the trend in 2005 – 2012 all things being equal. Built up area may increase to 11026.456 hectares, which represent 11% change. The study has shown clearly the extent to which MSS imagery and Landsat images together with extensive ground- truthing can provide information necessary for land use and land cover mapping. Attempt was made to capture as accurate as possible four land use and land cover classes as they change through time.

scholarly journals Land Cover/ Land Use Change and Climate Change in Dhofar Governorate, Oman

2021 ◽  
pp. 41-47
Author(s):  
E. Ramadan ◽  
T. Al-Awadhi ◽  
Y. Charabi
Keyword(s):  
Climate Change ◽  
Land Use ◽  
Land Cover ◽  
Land Cover Change ◽  
Land Use Changes ◽  
Spatial Differentiation ◽  
Study Results ◽  
Vegetation Activity ◽  
The Status ◽  
Landsat Satellite

The study of land cover/land use dynamics under climate change conditions is of great significance for improving sustainable ecological management. Understanding the relationships between land cover and land use changes and climate change is thus very important. Understanding the interactive and cumulative effects of climate and land-use changes are a priority for urban planners and policy makers. The present investigation is based on Landsat satellite imagery to explore changes in vegetation spatial distribution between the years from 2000 to2018 The methodology is focused on vegetation indexes tracking and algebraic overlay calculation to analyzed vegetation and their spatial differentiation, land cover change pattern, and the relationships between vegetation dynamics and land cover change in Dhofar Governorate. The study results have revealed that the vegetation vigor is lower in all years compared to 2000. The scene of 2010 shows the minimum vegetation vigor, overall. Besides, the investigation shows a statistical relationship between rainfall and the status of the health of vegetation. Monsoon rainfall has an impact of the growth of vegetation. Between 2012 and 2013, the vegetation activity shows a decreasing trend. The analysis diagnoses an area affected by the worst degree of aridity situated in the southeastern of Dhofar Mountains. Climate change is the main driving factor resulted from both human activities and rainfall fluctuation.

Semantic Fusion of Image Annotation

2011 ◽  
Vol 268-270 ◽  
pp. 1386-1389
Author(s):  
Xiao Ying Wu ◽  
Yun Juan Liang ◽  
Li Li ◽  
Li Juan Ma
Keyword(s):  
Large Scale ◽  
Image Annotation ◽  
Semantic Annotation ◽  
Probability Model ◽  
Joint Probability ◽  
Training Data ◽  
Data Set ◽  
Other Information ◽  
Image Area ◽  
Representative Image

In this paper, improve the image annotation with semantic meaning, and name the new algorithm for semantic fusion of image annotation, that is a image is given to be labeled, use of training data set, the word set, and a collection of image area and other information to establish the probability model ,estimates the joint probability by word and given image areas.The probability value as the size, combined with keywords relevant table that integrates lexical semantics to extract keywords as the most representative image semantic annotation results. The algorithm can effectively use large-scale training data with rich annotation, so as to achieve better recall and precision than the existing automatic image annotation ,and validate the algorithm in the Corel data set.

scholarly journals Environmental Differences between Migratory and Resident Ungulates—Predicting Movement Strategies in Rocky Mountain Mule Deer (Odocoileus hemionus) with Remotely Sensed Plant Phenology, Snow, and Land Cover

2019 ◽  
Vol 11 (17) ◽  
pp. 1980
Author(s):  
Benjamin Robb ◽  
Qiongyu Huang ◽  
Joseph Sexton ◽  
David Stoner ◽  
Peter Leimgruber
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Snow Cover ◽  
Large Scale ◽  
Mule Deer ◽  
Life History Strategy ◽  
Odocoileus Hemionus ◽  
Remotely Sensed ◽  
Land Use Impacts ◽  
Human Land Use

Migration is a valuable life history strategy for many species because it enables individuals to exploit spatially and temporally variable resources. Globally, the prevalence of species’ migratory behavior is decreasing as individuals forgo migration to remain resident year-round, an effect hypothesized to result from anthropogenic changes to landscape dynamics. Efforts to conserve and restore migrations require an understanding of the ecological characteristics driving the behavioral tradeoff between migration and residence. We identified migratory and resident behaviors of 42 mule deer (Odocoileus hemionus) based on GPS locations and correlated their locations to remotely sensed indicators of forage quality, land cover, snow cover, and human land use. The model classified mule deer seasonal migratory and resident niches with an overall accuracy of 97.8% and cross-validated accuracy of 81.2%. The distance to development was the most important variable in discriminating in which environments these behaviors occur, with resident niche space most often closer to developed areas than migratory niches. Additionally, snow cover in December was important for discriminating summer migratory niches. This approach demonstrates the utility of niche analysis based on remotely sensed environmental datasets and provides empirical evidence of human land use impacts on large-scale wildlife migrations.

Sign in / Sign up

Export Citation Format

Share Document