scholarly journals The t-SNE Algorithm as a Tool to Improve the Quality of Reference Data Used in Accurate Mapping of Heterogeneous Non-Forest Vegetation

2019 ◽  
Vol 12 (1) ◽  
pp. 39 ◽  
Author(s):  
Anna Halladin-Dąbrowska ◽  
Adam Kania ◽  
Dominik Kopeć
Keyword(s):  
Remote Sensing ◽  
Reference Data ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Forest Vegetation ◽  
Visual Interpretation ◽  
Reference Dataset ◽  
Visual Evaluation ◽  
Sensing Data

Supervised classification methods, used for many applications, including vegetation mapping require accurate “ground truth” to be effective. Nevertheless, it is common for the quality of this data to be poorly verified prior to it being used for the training and validation of classification models. The fact that noisy or erroneous parts of the reference dataset are not removed is usually explained by the relatively high resistance of some algorithms to errors. The objective of this study was to demonstrate the rationale for cleaning the reference dataset used for the classification of heterogeneous non-forest vegetation, and to present a workflow based on the t-distributed stochastic neighbor embedding (t-SNE) algorithm for the better integration of reference data with remote sensing data in order to improve outcomes. The proposed analysis is a new application of the t-SNE algorithm. The effectiveness of this workflow was tested by classifying three heterogeneous non-forest Natura 2000 habitats: Molinia meadows (Molinion caeruleae; code 6410), species-rich Nardus grassland (code 6230) and dry heaths (code 4030), employing two commonly used algorithms: random forest (RF) and AdaBoost (AB), which, according to the literature, differ in their resistance to errors in reference datasets. Polygons collected in the field (on-ground reference data) in 2016 and 2017, containing no intentional errors, were used as the on-ground reference dataset. The remote sensing data used in the classification were obtained in 2017 during the peak growing season by a HySpex sensor consisting of two imaging spectrometers covering spectral ranges of 0.4–0.9 μm (VNIR-1800) and 0.9–2.5 μm (SWIR-384). The on-ground reference dataset was gradually cleaned by verifying candidate polygons selected by visual interpretation of t-SNE plots. Around 40–50% of candidate polygons were ultimately found to contain errors. Altogether, 15% of reference polygons were removed. As a result, the quality of the final map, as assessed by the Kappa and F1 accuracy measures as well as by visual evaluation, was significantly improved. The global map accuracy increased by about 6% (in Kappa coefficient), relative to the baseline classification obtained using random removal of the same number of reference polygons.

scholarly journals Groundwater Potential Zones in Relation to Catchment Condition in Orenburg, Russia

2019 ◽  
pp. 60-65
Author(s):  
K Choudhary ◽  
M S Boori ◽  
A Kupriyanov
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Groundwater Potential ◽  
Groundwater Potential Zone ◽  
Potential Zone ◽  
Ground Truth Data ◽  
Groundwater Availability ◽  
Sensing Data

The main objective of this study was to detect groundwater availability for agriculture in the Orenburg, Russia. Remote sensing data (RS) and geographic information system (GIS) were used to locate potential zones for groundwater in Orenburg. Diverse maps such as a base map, geomorphological, geological structural, lithology, drainage, slope, land use/cover and groundwater potential zone were prepared using the satellite remote sensing data, ground truth data, and secondary data. ArcGIS software was utilized to manipulate these data sets. The groundwater availability of the study was classified into different classes such as very high, high, moderate, low and very low based on its hydro-geomorphological conditions. The land use/cover map was prepared using a digital classification technique with the limited ground truth for mapping irrigated areas in the Orenburg, Russia.

Valuing Radiometric Quality of Remote Sensing Data for Decisions

2021 ◽  
Author(s):  
Afreen Siddiqi ◽  
Sheila Baber ◽  
Olivier De Weck
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Sensing Data

The Evaluation and Application Study of Remote Sensing Data Quality of Environment and Disaster Monitoring

2012 ◽  
Vol 573-574 ◽  
pp. 271-276
Author(s):  
Ping Ren ◽  
Jie Ming Zhou
Keyword(s):  
Remote Sensing ◽  
Data Quality ◽  
Remote Sensing Data ◽  
Resolution Time ◽  
Application Study ◽  
Space Resolution ◽  
Sensing Data ◽  
The Earth ◽  
Disaster Monitoring

The existing Fengyun (FY) satellites, resource satellites and ocean satellites all can observe the earth muti-funtionally and work well in monitoring environment and disasters. However, all these satellites are insufficient for space resolution, time resolution, spectral resolution and all-weather requirements when facing complicated environmental problems and natural disasters. This paper evaluates the multi-spectral remote sensing data quality of the Environment and Disasters Monitoring Micro-satellite Constellation (HJ-1A/B)A/B satellite and extracts data characteristics to offer references for promotion and application this data.

scholarly journals Damage Assessment of a Salt Dome in Jizan, Southwestern Saudi Arabia, Using High Spatial Resolution Remote Sensing Data

2021 ◽  
Vol 9 ◽  
Author(s):  
Habes Ghrefat ◽  
Ahmed Hakami ◽  
Elkhedr Ibrahim ◽  
Saad Mogren ◽  
Saleh Qaysi ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Saudi Arabia ◽  
Spatial Resolution ◽  
Damage Assessment ◽  
High Spatial Resolution ◽  
Remote Sensing Data ◽  
Salt Dome ◽  
Visual Interpretation ◽  
Sensing Data ◽  
Residential Neighborhood

The salt dome in Jizan, southwestern Saudi Arabia, has caused several problems related to underground dissolution, particularly in the old part of the city. Examples of these problems include surface collapse, building failure, fracturing, tilting, and road cracking. Analysis of the salt dome using X-ray diffraction (XRD) revealed the dominance of gypsum, anhydrite, and halite. This study evaluates the damage assessment using multitemporal high spatial resolution data of the GeoEye-1, and QuickBird-2 sensors. Change detection technique, textural analysis, and visual interpretation were applied to these data. Analysis of the data recorded before and after a particular damage event revealed that three neighborhoods located above the Jizan salt dome—Al-Ashaima, Shamiya, and Aljabal—were affected to the greatest extent. The entire residential neighborhood of Al-Ashaima was evacuated, and the buildings located in it were demolished. Several buildings in the Shamiya and Aljabal neighborhoods were also demolished. Therefore, high spatial remote sensing data are effective in assessing building damage and for anticipating future damage, thus benefiting decision making for the affected cities.

scholarly journals Evaluating the quality of remote sensing products for agricultural index insurance

PLoS ONE ◽  
2021 ◽  
Vol 16 (10) ◽  
pp. e0258215
Author(s):  
Benson K. Kenduiywo ◽  
Michael R. Carter ◽  
Aniruddha Ghosh ◽  
Robert J. Hijmans
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Well Being ◽  
Insurance Contract ◽  
Index Insurance ◽  
Sensing Data ◽  
Insurance Contracts ◽  
The Impact ◽  
Economic Well Being

Agricultural index insurance contracts increasingly use remote sensing data to estimate losses and determine indemnity payouts. Index insurance contracts inevitably make errors, failing to detect losses that occur and issuing payments when no losses occur. The quality of these contracts and the indices on which they are based, need to be evaluated to assess their fitness as insurance, and to provide a guide to choosing the index that best protects the insured. In the remote sensing literature, indices are often evaluated with generic model evaluation statistics such as R2 or Root Mean Square Error that do not directly consider the effect of errors on the quality of the insurance contract. Economic analysis suggests using measures that capture the impact of insurance on the expected economic well-being of the insured. To bridge the gap between the remote sensing and economic perspectives, we adopt a standard economic measure of expected well-being and transform it into a Relative Insurance Benefit (RIB) metric. RIB expresses the welfare benefits derived from an index insurance contract relative to a hypothetical contract that perfectly measures losses. RIB takes on its maximal value of one when the index contract offers the same economic benefits as the perfect contract. When it achieves none of the benefits of insurance it takes on a value of zero, and becomes negative if the contract leaves the insured worse off than having no insurance. Part of our contribution is to decompose this economic well-being measure into an asymmetric loss function. We also argue that the expected well-being measure we use has advantages over other economic measures for the normative purpose of insurance quality ascertainment. Finally, we illustrate the use of the RIB measure with a case study of potential livestock insurance contracts in Northern Kenya. We compared 24 indices that were made with 4 different statistical models and 3 remote sensing data sources. RIB for these indices ranged from 0.09 to 0.5, and R2 ranged from 0.2 to 0.51. While RIB and R2 were correlated, the model with the highest RIB did not have the highest R2. Our findings suggest that, when designing and evaluating an index insurance program, it is useful to separately consider the quality of a remote sensing-based index with a metric like the RIB instead of a generic goodness-of-fit metric.

scholarly journals Visual characteristics of landscapes and methods for their assessment on GIS (Belogradchik rocks (Bulgaria) as an example)

2021 ◽  
Vol 27 (2) ◽  
pp. 191-204
Author(s):  
Elina Sheremet ◽  
Natalia Kalutskova ◽  
Vladimir Dekhnich
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Visual Quality ◽  
Aerial Photographs ◽  
Main Task ◽  
Field Observations ◽  
North West ◽  
Sensing Data ◽  
Visual Characteristics

Visual characteristics of landscapes are important factors for the assessment of tourist and recreational potential of territories. At present, a number of methodological approaches are applied to assess the visual characteristics of landscapes. They can be divided into traditional, associated exclusively with field research, and innovative, which is based on remote sensing data (RSD) of high spatial resolution and GIS technologies. Field assessment of the visual quality of landscapes utilizes a system of numerous elementary indicators to minimize subjectivity of assessment. They are conducted within separate areas or touristic routes. In its turn, modern GIS and high quality of remote sensing data allow assessing of most indicators of the visual quality of landscapes for any observation point on the entire territory. The main task of our research is to verify the results of automated processing of ultra-high resolution aerial photographs obtained from unmanned aerial vehicles (UAV) by field observations on a touristic route. The research was carried out on the territory of the “Belogradchik Rocks” Geopark (North-West Bulgaria). In our study, we estimated 4 out of 28 aesthetic indicators—the amount of mountain peaks visible from a site, the amount of mountain peaks on the skyline, the percentage of the forest-covered area, and the amount of open spaces in the wooded landscape. The obtained results confirmed that our approach allows calculating these aesthetic indicators at an accuracy level comparable to field observations.

scholarly journals Remote sensing data retouching based on image inpainting algorithms in the forgery generation problem

2020 ◽  
Vol 44 (5) ◽  
pp. 763-771
Author(s):  
A.V. Kuznetsov ◽  
M.V. Gashnikov
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
Image Inpainting ◽  
Remote Sensing Data ◽  
Earth Remote Sensing ◽  
Sensing Data ◽  
Natural Data ◽  
Generation Problem

We investigate image retouching algorithms for generating forgery Earth remote sensing data. We provide an overview of existing neural network solutions in the field of generation and inpainting of remote sensing images. To retouch Earth remote sensing data, we use imageinpainting algorithms based on convolutional neural networks and generative-adversarial neural networks. We pay special attention to a generative neural network with a separate contour prediction block that includes two series-connected generative-adversarial subnets. The first subnet inpaints contours of the image within the retouched area. The second subnet uses the inpainted contours to generate the resulting retouch area. As a basis for comparison, we use exemplar-based algorithms of image inpainting. We carry out computational experiments to study the effectiveness of these algorithms when retouching natural data of remote sensing of various types. We perform a comparative analysis of the quality of the algorithms considered, depending on the type, shape and size of the retouched objects and areas. We give qualitative and quantitative characteristics of the efficiency of the studied image inpainting algorithms when retouching Earth remote sensing data. We experimentally prove the advantage of generative-competitive neural networks in the construction of forgery remote sensing data.

Taking the pulse of the Amazon rainforest by fusing multitemporal Sentinel 1 and 2 data for advanced deep-learning

2021 ◽  
Author(s):  
Melanie Brandmeier ◽  
Eya Cherif
Keyword(s):  
Remote Sensing ◽  
Deep Learning ◽  
Land Cover ◽  
Supervised Learning ◽  
Large Scale ◽  
Remote Sensing Data ◽  
Ground Truth ◽  
Brazilian Amazon ◽  
Sensing Data ◽  
Weakly Supervised

<p>Degradation of large forest areas such as the Brazilian Amazon due to logging and fires can increase the human footprint way beyond deforestation. Monitoring and quantifying such changes on a large scale has been addressed by several research groups (e.g. Souza et al. 2013) by making use of freely available remote sensing data such as the Landsat archive. However, fully automatic large-scale land cover/land use mapping is still one of the great challenges in remote sensing. One problem is the availability of reliable “ground truth” labels for training supervised learning algorithms. For the Amazon area, several landcover maps with 22 classes are available from the MapBiomas project that were derived by semi-automatic classification and verified by extensive fieldwork (Project MapBiomas). These labels cannot be considered real ground-truth as they were derived from Landsat data themselves but can still be used for weakly supervised training of deep-learning models that have a potential to improve predictions on higher resolution data nowadays available. The term weakly supervised learning was originally coined by (Zhou 2017) and refers to the attempt of constructing predictive models from incomplete, inexact and/or inaccurate labels as is often the case in remote sensing. To this end, we investigate advanced deep-learning strategies on Sentinel-1 timeseries and Sentinel-2 optical data to improve large-scale automatic mapping and monitoring of landcover changes in the Amazon area. Sentinel-1 data has the advantage to be resistant to cloud cover that often hinders optical remote sensing in the tropics.</p><p>We propose new architectures that are adapted to the particularities of remote sensing data (S1 timeseries and multispectral S2 data) and compare the performance to state-of-the-art models.  Results using only spectral data were very promising with overall test accuracies of 77.9% for Unet and 74.7% for a DeepLab implementation with ResNet50 backbone and F1 measures of 43.2% and 44.2% respectively.  On the other hand, preliminary results for new architectures leveraging the multi-temporal aspect of  SAR data have improved the quality of mapping, particularly for agricultural classes. For instance, our new designed network AtrousDeepForestM2 has a similar quantitative performances as DeepLab  (F1 of 58.1% vs 62.1%), however it produces better qualitative land cover maps.</p><p>To make our approach scalable and feasible for others, we integrate the trained models in a geoprocessing tool in ArcGIS that can also be deployed in a cloud environment and offers a variety of post-processing options to the user.</p><p>Souza, J., Carlos M., et al. (2013). "Ten-Year Landsat Classification of Deforestation and Forest Degradation in the Brazilian Amazon." Remote Sensing 5(11): 5493-5513.   </p><p>Zhou, Z.-H. (2017). "A brief introduction to weakly supervised learning." National Science Review 5(1): 44-53.</p><p>"Project MapBiomas - Collection  4.1 of Brazilian Land Cover & Use Map Series, accessed on January 2020 through the link: https://mapbiomas.org/colecoes-mapbiomas?cama_set_language=en"</p>

Sign in / Sign up

Export Citation Format

Share Document