Effects of Different Methods of Radiometric Calibration on the Use of Training Data for Supervised Classification of Landsat5/TM Images from other Dates

The Bago Mountain Range in Myanmar is known as the “home of teak” (Tectona grandis L. f.) because of its bountiful, naturally growing teak-bearing forests. Accelerating forest loss and degradation are threatening the sustainable production of teak in the region. Changes in land cover between 2000 and 2017 in four reserved forests of the Bago Mountain Range were mapped using supervised classification of Landsat imagery and training data collected in the field. A stratified random sample was used to collect reference data to assess accuracy of the maps and estimate area. Based on the reference sample, it was estimated that the forest area declined from 71 240 ha (standard error (SE) = 1524 ha) in 2000 to 40 891 ha (SE = 4404 ha) in 2017, whereas the area of degraded forests increased from 88 797 ha (SE = 1694 ha) to 97 013 ha (SE = 5395 ha). The annualized rates of gross forest loss and gross forest degradation were 1.03% and 0.97%, respectively, indicating that forest degradation paralleled forest loss. In many degraded areas, there is an opportunity to ameliorate the situation through silviculture. The 2017 map identifies bamboo-dominated degraded forests where enrichment planting or reforestation is recommended.

Download Full-text

Automated image classification of outlet glaciers in Greenland using deep learning

10.5194/egusphere-egu2020-19996 ◽

2020 ◽

Author(s):

Melanie Marochov ◽

Patrice Carbonneau ◽

Chris Stokes

Keyword(s):

Neural Network ◽

Deep Learning ◽

Image Classification ◽

Supervised Classification ◽

Greenland Ice Sheet ◽

Training Data ◽

Glacier Change ◽

Outlet Glacier ◽

Glacial Environments

<p>In recent decades, a wealth of research has focused on elucidating the key controls on the mass loss of the Greenland Ice Sheet and its response to climate forcing, specifically in relation to the drivers of spatio-temporally variable outlet glacier change. Despite the increasing availability of high-resolution satellite data, the time-consuming nature of the manual methods traditionally used to analyse satellite imagery has resulted in a significant bottleneck in the monitoring of outlet glacier change. Recent advances in deep learning applied to image processing have opened up a new frontier in the area of automated delineation of glacier termini. However, at this stage, there remains a paucity of research on the use of deep learning for image classification of outlet glacier landscapes. In this contribution, we apply a deep learning approach based on transfer learning to automatically classify satellite images of Helheim glacier, the fastest flowing outlet glacier in eastern Greenland. The method uses the well-established VGG16 convolutional neural network (CNN), and is trained on 224x224 pixel tiles derived from Sentinel-2 RGB bands, which have a spatial resolution of 10 metres. Based on features learned from ImageNet and limited training data, our deep learning model can classify glacial environments with >85% accuracy. In future stages of this research, we will use a new method originally developed for fluvial settings, dubbed &#8216;CNN-Supervised Classification&#8217; (CSC). CSC uses a pre-trained CNN (in this case our VGG16 model) to replace the human operator&#8217;s role in traditional supervised classification by automatically producing new label data to train a pixel-level neural network classifier for any new image. This transferable approach to image classification of outlet glacier landscapes permits not only automated terminus delineation, but also facilitates the efficient analysis of numerous processes controlling outlet glacier behaviour, such as fjord geometry, subglacial plumes, and supra-glacial lakes.</p>

Download Full-text

Technical Note: Semi-automated classification of time-lapse RGB imagery for a remote Greenlandic river

Hydrology and Earth System Sciences Discussions ◽

10.5194/hessd-12-1311-2015 ◽

2015 ◽

Vol 12 (1) ◽

pp. 1311-1327

Author(s):

C. J. Gleason ◽

L. C. Smith ◽

D. C. Finnegan ◽

A. L. LeWinter ◽

L. H. Pitcher ◽

...

Keyword(s):

Supervised Classification ◽

Field Measurements ◽

Time Lapse ◽

Technical Note ◽

Training Data ◽

Hydraulic Parameters ◽

Automated Classification ◽

Braided Rivers ◽

Highly Correlated

Abstract. River systems in remote environments are often challenging to monitor and understand where traditional gauging apparatus are difficult to install or where safety concerns prohibit field measurements. In such cases, remote sensing, especially terrestrial time lapse imaging platforms, offer a means to better understand these fluvial systems. One such environment is found at the proglacial Isortoq River in southwest Greenland, a river with a constantly shifting floodplain and remote Arctic location that make gauging and in situ measurements all but impossible. In order to derive relevant hydraulic parameters for this river, two RGB cameras were installed in July of 2011, and these cameras collected over 10 000 half hourly time-lapse images of the river by September of 2012. Existing approaches for extracting hydraulic parameters from RGB imagery require manual or supervised classification of images into water and non-water areas, a task that was impractical for the volume of data in this study. As such, automated image filters were developed that removed images with environmental obstacles (e.g. shadows, sun glint, snow) from the processing stream. Further image filtering was accomplished via a novel automated histogram similarity filtering process. This similarity filtering allowed successful (mean accuracy 79.6%) supervised classification of filtered images from training data collected from just 10% of those images. Effective width, a hydraulic parameter highly correlated with discharge in braided rivers, was extracted from these classified images, producing a hydrograph proxy for the Isortoq River between 2011 and 2012. This hydrograph proxy shows agreement with historic flooding observed in other parts of Greenland in July 2012 and offers promise that the imaging platform and processing methodology presented here will be useful for future monitoring studies of remote rivers.

Download Full-text

Predictive Modeling of Future Forest Cover Change Patterns in Southern Belize

Remote Sensing ◽

10.3390/rs11070823 ◽

2019 ◽

Vol 11 (7) ◽

pp. 823 ◽

Cited By ~ 11

Author(s):

Carly Voight ◽

Karla Hernandez-Aguilar ◽

Christina Garcia ◽

Said Gutierrez

Keyword(s):

Supervised Classification ◽

Forest Cover ◽

Agricultural Practices ◽

Google Earth ◽

Training Data ◽

Forest Loss ◽

Landsat 8 ◽

Forest Cover Change ◽

Change Analysis

Tropical forests and the biodiversity they contain are declining at an alarming rate throughout the world. Although southern Belize is generally recognized as a highly forested landscape, it is becoming increasingly threatened by unsustainable agricultural practices. Deforestation data allow forest managers to efficiently allocate resources and inform decisions for proper conservation and management. This study utilized satellite imagery to analyze recent forest cover and deforestation in southern Belize to model vulnerability and identify the areas that are the most susceptible to future forest loss. A forest cover change analysis was conducted in Google Earth Engine using a supervised classification of Landsat 8 imagery with ground-truthed land cover points as training data. A multi-layer perceptron neural network model was performed to predict the potential spatial patterns and magnitude of forest loss based on the regional drivers of deforestation. The assessment indicates that the agricultural frontier will continue to expand into recently untouched forests, predicting a decrease from 75.0% mature forest cover in 2016 to 71.9% in 2026. This study represents the most up-to-date assessment of forest cover and the first vulnerability and prediction assessment in southern Belize with immediate applications in conservation planning, monitoring, and management.

Download Full-text

On Supervised Classification of Feature Vectors with Independent and Non-Identically Distributed Elements

Entropy ◽

10.3390/e23081045 ◽

2021 ◽

Vol 23 (8) ◽

pp. 1045

Author(s):

Farzad Shahrivari ◽

Nikola Zlatanov

Keyword(s):

Error Probability ◽

Supervised Classification ◽

Feature Vector ◽

Training Data ◽

Finite Alphabet ◽

Feature Vectors ◽

Optimal Classifier ◽

Mutually Independent ◽

Distributed Elements

In this paper, we investigate the problem of classifying feature vectors with mutually independent but non-identically distributed elements that take values from a finite alphabet set. First, we show the importance of this problem. Next, we propose a classifier and derive an analytical upper bound on its error probability. We show that the error probability moves to zero as the length of the feature vectors grows, even when there is only one training feature vector per label available. Thereby, we show that for this important problem at least one asymptotically optimal classifier exists. Finally, we provide numerical examples where we show that the performance of the proposed classifier outperforms conventional classification algorithms when the number of training data is small and the length of the feature vectors is sufficiently high.

Download Full-text

Technical Note: Semi-automated effective width extraction from time-lapse RGB imagery of a remote, braided Greenlandic river

Hydrology and Earth System Sciences ◽

10.5194/hess-19-2963-2015 ◽

2015 ◽

Vol 19 (6) ◽

pp. 2963-2969 ◽

Cited By ~ 8

Author(s):

C. J. Gleason ◽

L. C. Smith ◽

D. C. Finnegan ◽

A. L. LeWinter ◽

L. H Pitcher ◽

...

Keyword(s):

Supervised Classification ◽

Field Measurements ◽

Time Lapse ◽

Technical Note ◽

Training Data ◽

Hydraulic Parameters ◽

Effective Width ◽

Braided Rivers ◽

Highly Correlated

Abstract. River systems in remote environments are often challenging to monitor and understand where traditional gauging apparatus are difficult to install or where safety concerns prohibit field measurements. In such cases, remote sensing, especially terrestrial time-lapse imaging platforms, offer a means to better understand these fluvial systems. One such environment is found at the proglacial Isortoq River in southwestern Greenland, a river with a constantly shifting floodplain and remote Arctic location that make gauging and in situ measurements all but impossible. In order to derive relevant hydraulic parameters for this river, two true color (RGB) cameras were installed in July 2011, and these cameras collected over 10 000 half hourly time-lapse images of the river by September of 2012. Existing approaches for extracting hydraulic parameters from RGB imagery require manual or supervised classification of images into water and non-water areas, a task that was impractical for the volume of data in this study. As such, automated image filters were developed that removed images with environmental obstacles (e.g., shadows, sun glint, snow) from the processing stream. Further image filtering was accomplished via a novel automated histogram similarity filtering process. This similarity filtering allowed successful (mean accuracy 79.6 %) supervised classification of filtered images from training data collected from just 10 % of those images. Effective width, a hydraulic parameter highly correlated with discharge in braided rivers, was extracted from these classified images, producing a hydrograph proxy for the Isortoq River between 2011 and 2012. This hydrograph proxy shows agreement with historic flooding observed in other parts of Greenland in July 2012 and offers promise that the imaging platform and processing methodology presented here will be useful for future monitoring studies of remote rivers.

Download Full-text

Selection of Suitable Supervised Classification Techniques for the Geographic Analysis of Land Using GIS Techniques

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i3.27.17661 ◽

2018 ◽

Vol 7 (3.27) ◽

pp. 82

Author(s):

S L. Senthil Lekha ◽

S S.Kumar

Keyword(s):

Land Use ◽

Land Cover ◽

Supervised Classification ◽

Kappa Coefficient ◽

Landsat Image ◽

Training Data ◽

Spectral Angle Mapper ◽

Gis Techniques ◽

Spectral Angle

Nation has realised the changes in the land surface and the influence of this in the whole ecosystem. The activities of human on land is directly deteriorating the environment quality. This paper mainly focuses on the analysis of the destruction of land cover with the development of land use. The performance of five different Supervised Classification algorithms, which are Parallelepiped, Mahalanobis, Neurel Net, Adaptive Coherence and Spectral Angle Mapper have been analysed in classifying the Landsat Image of kanyakumari district. Automatic classification of five classes using training data have been performed and the best suitable algorithm for the classification of each class have been analysed. Being a tourism centre with coastal areas on all three sides, the development and the deterioration of kanyakumari district have to be monitored constantly. The proposed system is an automatic approach which helps in the analysis of the patterns of land use and land cover which constantly changes and to map each class clearly and distinct from each other using GIS techniques. The system was evaluated using the performance measures like accuracy and kappa coefficient using the tools Envi, ArcGIS and QGIS. From the performance analysis, the Spectral Angle Mapper with an overall accuracy of 97% and kappa coefficient of 0.54 has been selected as the best suitable algorithm for the classification of landsat image of kanyakumari district.

Download Full-text