scholarly journals Operational Large-Area Land-Cover Mapping: An Ethiopia Case Study

2020 ◽  
Vol 12 (6) ◽  
pp. 954
Author(s):  
Reza Khatami ◽  
Jane Southworth ◽  
Carly Muir ◽  
Trevor Caughlin ◽  
Alemayehu N. Ayana ◽  
...  
Keyword(s):  
Land Cover ◽  
Classification Accuracy ◽  
Landsat 8 ◽  
Large Area ◽  
National Scale ◽  
Night Time ◽  
Explanatory Variables ◽  
Image Compositing ◽  
Elevation Data ◽  
Multi Temporal

Knowledge of land cover and land use nationally is a prerequisite of many studies on drivers of land change, impacts on climate, carbon storage and other ecosystem services, and allows for sufficient planning and management. Despite this, many regions globally do not have accurate and consistent coverage at the national scale. This is certainly true for Ethiopia. Large-area land-cover characterization (LALCC), at a national scale is thus an essential first step in many studies of land-cover change, and yet is itself problematic. Such LALCC based on remote-sensing image classification is associated with a spectrum of technical challenges such as data availability, radiometric inconsistencies within/between images, and big data processing. Radiometric inconsistencies could be exacerbated for areas, such as Ethiopia, with a high frequency of cloud cover, diverse ecosystem and climate patterns, and large variations in elevation and topography. Obtaining explanatory variables that are more robust can improve classification accuracy. To create a base map for the future study of large-scale agricultural land transactions, we produced a recent land-cover map of Ethiopia. Of key importance was the creation of a methodology that was accurate and repeatable and, as such, could be used to create earlier, comparable land-cover classifications in the future for the same region. We examined the effects of band normalization and different time-series image compositing methods on classification accuracy. Both top of atmosphere and surface reflectance products from the Landsat 8 Operational Land Imager (OLI) were tested for single-time classification independently, where the latter resulted in 1.1% greater classification overall accuracy. Substitution of the original spectral bands with normalized difference spectral indices resulted in an additional improvement of 1.0% in overall accuracy. Three approaches for multi-temporal image compositing, using Landsat 8 OLI and Moderate Resolution Imaging Spectroradiometer (MODIS) data, were tested including sequential compositing, i.e., per-pixel summary measures based on predefined periods, probability density function compositing, i.e., per-pixel characterization of distribution of spectral values, and per-pixel sinusoidal models. Multi-temporal composites improved classification overall accuracy up to 4.1%, with respect to single-time classification with an advantage of the Landsat OLI-driven composites over MODIS-driven composites. Additionally, night-time light and elevation data were used to improve the classification. The elevation data and its derivatives improved classification accuracy by 1.7%. The night-time light data improve producer’s accuracy of the Urban/Built class with the cost of decreasing its user’s accuracy. Results from this research can aid map producers with decisions related to operational large-area land-cover mapping, especially with selecting input explanatory variables and multi-temporal image compositing, to allow for the creation of accurate and repeatable national-level land-cover products in a timely fashion.

scholarly journals Seasonal variation of land cover classification accuracy of Landsat 8 images in Burkina Faso

2015 ◽  
Vol XL-7/W3 ◽  
pp. 455-460 ◽  
Author(s):  
J. Liu ◽  
J. Heiskanen ◽  
E. Aynekulu ◽  
P. K. E. Pellikka
Keyword(s):  
Land Cover ◽  
Burkina Faso ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Dry Season ◽  
Landsat 8 ◽  
Wet Season ◽  
Validation Data ◽  
Multi Temporal ◽  
Change Monitoring

In the seasonal tropics, vegetation shows large reflectance variation because of phenology, which complicates land cover change monitoring. Ideally, multi-temporal images for change monitoring should be from the same season, but availability of cloud-free images is limited in wet season in comparison to dry season. Our aim was to investigate how land cover classification accuracy depends on the season in southern Burkina Faso by analyzing 14 Landsat 8 OLI images from April 2013 to April 2014. Because all the images were acquired within one year, we assumed that most of the observed variation between the images was due to phenology. All the images were cloud masked and atmospherically corrected. Field data was collected from 160 field plots located within a 10 km × 10 km study area between December 2013 and February 2014. The plots were classified to closed forest, open forest and cropland, and used as training and validation data. Random forest classifier was employed for classifications. According to the results, there is a tendency for higher classification accuracy towards the dry season. The highest classification accuracy was provided by an image from December, which corresponds to the dry season and minimum NDVI period. In contrast, an image from October, which corresponds to the wet season and maximum NDVI period provided the lowest accuracy. Furthermore, the multi-temporal classification based on dry and wet season images had higher accuracy than single image classifications, but the improvement was small because seasonal changes affect similarly to the different land cover classes.

scholarly journals Improving 3-m Resolution Land Cover Mapping through Efficient Learning from an Imperfect 10-m Resolution Map

2020 ◽  
Vol 12 (9) ◽  
pp. 1418
Author(s):  
Runmin Dong ◽  
Cong Li ◽  
Haohuan Fu ◽  
Jie Wang ◽  
Weijia Li ◽  
...  
Keyword(s):  
Land Cover ◽  
Training Data ◽  
Training Dataset ◽  
Land Cover Mapping ◽  
Remotely Sensed Data ◽  
Large Area ◽  
National Scale ◽  
Substantial Progress ◽  
Efficient Learning ◽  
Land Cover Maps

Substantial progress has been made in the field of large-area land cover mapping as the spatial resolution of remotely sensed data increases. However, a significant amount of human power is still required to label images for training and testing purposes, especially in high-resolution (e.g., 3-m) land cover mapping. In this research, we propose a solution that can produce 3-m resolution land cover maps on a national scale without human efforts being involved. First, using the public 10-m resolution land cover maps as an imperfect training dataset, we propose a deep learning based approach that can effectively transfer the existing knowledge. Then, we improve the efficiency of our method through a network pruning process for national-scale land cover mapping. Our proposed method can take the state-of-the-art 10-m resolution land cover maps (with an accuracy of 81.24% for China) as the training data, enable a transferred learning process that can produce 3-m resolution land cover maps, and further improve the overall accuracy (OA) to 86.34% for China. We present detailed results obtained over three mega cities in China, to demonstrate the effectiveness of our proposed approach for 3-m resolution large-area land cover mapping.

Impact of a volcanic eruption on the sediment connectivity of a Chilean river basin: the Calbuco study case

2021 ◽  
Author(s):  
Marco Andreoli ◽  
Lorenzo Martini ◽  
Marco Cavalli ◽  
Andrés Iroumé ◽  
Lorenzo Picco
Keyword(s):  
Land Cover ◽  
River Basin ◽  
Volcanic Eruption ◽  
Overland Flow ◽  
Volcanic Eruptions ◽  
Landsat 8 ◽  
Strong Impact ◽  
Low Resolution ◽  
Multi Temporal ◽  
Sediment Connectivity

<p>Volcanic eruptions are natural disturbances capable of introducing large quantities of sediment into river systems as to upset the transport regime for several years. Such a disturbance can have a strong impact on the water and sediment flows and consequently on the transport capacity. Moreover, changes in morphological settings and land cover lead to an alteration of the sediment connectivity within the catchment. This study aims to investigate the changes of sediment connectivity in a catchment affected by an explosive volcanic eruption using the Index of Connectivity (IC) with a multi-temporal approach. Potential variations were analyzed at the catchment scale over a period of 6 years, before and after the eruption. The study area, located in southern Chile, is the Blanco Este River basin (39,6 km²), affected by the eruption of the Calbuco volcano (April 2015, total volume of sediment expelled of about 0,28 km³) which profoundly changed its vegetation cover, geomorphology and hydrology. IC analyses were based on low-resolution and freely available data (i.e., GDEM, Landsat 8 satellite images). Through supervised image classification and field data survey, a Manning's n coefficient for overland flow is derived as weighting factor (W) due to its suitability to represent the impedance to sediment flows in catchments characterized by land cover variations. Following the eruption, bare soil cover on the basin doubled (from 5% to 10% of total basin area). Consequently, the multi-temporal analysis results in an overall increase of IC with the median value ranges from -3,58 to -3,26 in pre-eruptive (2015) and first post-eruptive scenario (2016), respectively. The connectivity maps show that the higher IC values (i.e. range from -1,23 to 1,66) are persistently located in three areas: at the base of the volcanic dome, on the steepest slopes near the main channel and in a sub-basin on the right side of the catchment. Moreover, the Difference of IC (DoIC) among different scenarios highlighted the major variations. Such changes are found along the volcano slopes, in a flat area located in the upper part of the basin and along the lower valley of the Rio Blanco Este. The study proposes a useful methodology to evaluate the sediment connectivity, and its evolutionary trends, in environments affected volcanic eruptions starting from low-resolution data and field survey. These results may help to better define types, location and typologies of interventions to improve the river management approaches, considering the ongoing cascading processes. This research is funded by the Fondecyt 1200079 project.</p>

scholarly journals Isolation Forests to Evaluate Class Separability and the Representativeness of Training and Validation Areas in Land Cover Classification

2019 ◽  
Vol 11 (24) ◽  
pp. 3000 ◽  
Author(s):  
Francisco Alonso-Sarria ◽  
Carmen Valdivieso-Ros ◽  
Francisco Gomariz-Castillo
Keyword(s):  
Remote Sensing ◽  
Random Forest ◽  
Land Cover ◽  
Classification Accuracy ◽  
Land Cover Classification ◽  
Landsat 8 ◽  
Commission Errors ◽  
Class Separability ◽  
Isolation Forest

Supervised land cover classification from remote sensing imagery is based on gathering a set of training areas to characterise each of the classes and to train a predictive model that is then used to predict land cover in the rest of the image. This procedure relies mainly on the assumptions of statistical separability of the classes and the representativeness of the training areas. This paper uses isolation forests, a type of random tree ensembles, to analyse both assumptions and to easily correct lack of representativeness by digitising new training areas where needed to improve the classification of a Landsat-8 set of images with Random Forest. The results show that the improved set of training areas after the isolation forest analysis is more representative of the whole image and increases classification accuracy. Besides, the distribution of isolation values can be useful to estimate class separability. A class separability parameter that summarises such distributions is proposed. This parameter is more correlated to omission and commission errors than other separability measures such as the Jeffries–Matusita distance.

scholarly journals SCS+C Topographic Correction to Enhance SVM Classification Accuracy

2020 ◽  
Vol 2 ◽  
pp. 32-37
Author(s):  
Jwan AL-Doski ◽  
Shattri B. Mansor ◽  
H'ng Paik San ◽  
Zailani Khuzaimah
Keyword(s):  
Land Cover ◽  
Classification Accuracy ◽  
Main Step ◽  
Support Vector ◽  
Landsat 8 ◽  
Mountainous Terrain ◽  
Topographic Correction ◽  
Corrected Image ◽  
Svm Algorithm ◽  
Land Cover Maps

The topographic impact may change the radiance values captured by the spacecraft sensors, resulting in distinct reflectance value for similar land cover classes and mischaracterization. The problem can be more clearly seen in rugged terrain landscapes than in flat terrains, such as the mountainous areas. In order to minimize topographic impacts, we suggested the implementation of Modified Sun-Canopy-Sensor Correction (SCS+C) technique to generate land cover maps in Gua Musang district which is located in a rugged mountainous terrain area in Kelantan state, Malaysia using an atmospherically corrected Landsat 8 imagery captured on 22 April 2014 by Support Vector Machine (SVM) algorithm. The results showed that the SCS+C method reduces the topographic effect particularly in such a steep and forested terrain with classification accuracy improvement about 4% which was statistically significantly with the McNemar test value Z and P measured 6.42 and 0.0001 on the corrected image classification90.1%accuracy compared to the uncorrected image86.2%for the test area. Thus, the topographic correction is suggested to be the main step of the data pre-processing stage in mountainous terrain before SVM image classification

scholarly journals Large-Area, High Spatial Resolution Land Cover Mapping Using Random Forests, GEOBIA, and NAIP Orthophotography: Findings and Recommendations

2019 ◽  
Vol 11 (12) ◽  
pp. 1409 ◽  
Author(s):  
Aaron E. Maxwell ◽  
Michael P. Strager ◽  
Timothy A. Warner ◽  
Christopher A. Ramezan ◽  
Alice N. Morgan ◽  
...  
Keyword(s):  
Land Cover ◽  
Spatial Resolution ◽  
Classification Accuracy ◽  
High Spatial Resolution ◽  
Kappa Statistic ◽  
Data Availability ◽  
Computational Time ◽  
Land Cover Mapping ◽  
Large Area ◽  
Ancillary Data

Despite the need for quality land cover information, large-area, high spatial resolution land cover mapping has proven to be a difficult task for a variety of reasons including large data volumes, complexity of developing training and validation datasets, data availability, and heterogeneity in data and landscape conditions. We investigate the use of geographic object-based image analysis (GEOBIA), random forest (RF) machine learning, and National Agriculture Imagery Program (NAIP) orthophotography for mapping general land cover across the entire state of West Virginia, USA, an area of roughly 62,000 km2. We obtained an overall accuracy of 96.7% and a Kappa statistic of 0.886 using a combination of NAIP orthophotography and ancillary data. Despite the high overall classification accuracy, some classes were difficult to differentiate, as highlight by the low user’s and producer’s accuracies for the barren, impervious, and mixed developed classes. In contrast, forest, low vegetation, and water were generally mapped with accuracy. The inclusion of ancillary data and first- and second-order textural measures generally improved classification accuracy whereas band indices and object geometric measures were less valuable. Including super-object attributes improved the classification slightly; however, this increased the computational time and complexity. From the findings of this research and previous studies, recommendations are provided for mapping large spatial extents.

scholarly journals Land use Land Cover Mapping using Modified Ant Colony Optimization Technique

2020 ◽  
Vol 9 (4) ◽  
pp. 100-106
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Ant Colony Optimization ◽  
Classification Accuracy ◽  
Environmental Changes ◽  
Optimization Technique ◽  
Unsupervised Classification ◽  
Ant Colony ◽  
Landsat 8 ◽  
Land Use Land Cover

Land use Land cover classification is an important aspect for managing natural resources and monitoring environmental changes. Urban expansion becomes one of the major challenges for the administrator. The LANDSAT 8 images are processed using the open source GRASS (Geographic Resource Analysis Support System). Unsupervised classification technique based on Ant Colony Optimization (ACO) algorithm has been modified and proposed as Modified Ant Colony Optimization (MACO) for LULC classification. In order to improve the classification accuracy of the proposed algorithm, we have combined spatial, spectral and texture features to extract more information of homogeneous land surface. The classification accuracy of the proposed algorithm has been compared with other unsupervised classification methods such as k-means, ISODATA and ACO algorithms. The overall classification accuracy of proposed unsupervised MACO algorithm has been increased by 11.24 %, 8.24% for open space and water bodies class, respectively as compared to ACO algorithm.

scholarly journals Impact of the Spatial Resolution of Satellite’s Data for Mapping Land use Land Cover in Karmala Tehsil, Solapur, India

2021 ◽  
pp. 66-75
Author(s):  
Sanket Kolambe ◽  
Jeet Raj ◽  
Krishna Loahkare ◽  
Shital Mane ◽  
Vikrant Nikam
Keyword(s):  
Land Use ◽  
Land Cover ◽  
Spatial Resolution ◽  
Classification Accuracy ◽  
Kappa Coefficient ◽  
Landsat 8 ◽  
Wide Field ◽  
Barren Land ◽  
Liss Iii ◽  
Sentinel 2A

Land use and land cover (LULC) classification mapping is important for evaluating, monitoring, protecting and planning for land resources. A key factor in extracting desired information from satellite images is choosing the right the spatial resolution. The scale of a pixel on the ground is known as spatial resolution. A pixel is the smallest ‘dot' that makes up an optical satellite image which defines the level of detail as in image. In this paper estimation of the areal extent of water, built up, barren land, vegetation land and fallow land classes with its classification accuracy were reviewed particularly for January 2013 and November 2016 in Karmala tehsil of Solapur district, India. LULC is implied by different spatial resolution images of Advanced Wide Field Sensor (AWiFS), Linear Imaging Self Scanning Sensor (LISS-III), Landsat-8 Operational Land Imager (OLI) and Sentinel-2A imageries in QGIS environment while the classification was carried out using the maximum likelihood algorithm (MLA). The classified maps obtained from AWiFS and LISS-III sensors, as well as Sentinel-2A and Landsat-8 OLI data sets, were compared separately.  Spatial analysis depicts that the Kappa coefficient of Sentinal-2A, Landsat-8, LISS III and AWiFS was found 96.96%, 91.64%, 87.30% and 89.36%. Furthermore, overall accuracy of was found to be 99.07%, 94.49%, 89.84% and 94.08% respectively. The accuracy of the classified image with higher spatial resolution (Sentinal-2A) proved more informative than that of lower resolution (AWiFS) sensor. On the response, the finer spatial resolution of Sentinal-2A (10 m) delivered more precise details and enhanced LULC classification accuracy most reliably than the coarser spatial resolution of Landsat-8 (30m), LISS III (23m) and AWiFS (56m) image. A perusal of data revealed that the overall accuracy and Kappa coefficient was found proportionate to spatial resolution of satellite imageries. The higher resolution spatial data also greatly reduces the mixed-pixel problem. The study revealed that the spatial resolution plays an important role and affects classification details and accuracy of LULC level.

Sign in / Sign up

Export Citation Format

Share Document