A Review on Unsupervised Band Selection Techniques : Land Cover Classification for Hyperspectral Earth Observation Data

In this paper, a novel feature selection algorithm for inference from high-dimensional data (FASTENER) is presented. With its multi-objective approach, the algorithm tries to maximize the accuracy of a machine learning algorithm with as few features as possible. The algorithm exploits entropy-based measures, such as mutual information in the crossover phase of the iterative genetic approach. FASTENER converges to a (near) optimal subset of features faster than other multi-objective wrapper methods, such as POSS, DT-forward and FS-SDS, and achieves better classification accuracy than similarity and information theory-based methods currently utilized in earth observation scenarios. The approach was primarily evaluated using the earth observation data set for land-cover classification from ESA’s Sentinel-2 mission, the digital elevation model and the ground truth data of the Land Parcel Identification System from Slovenia. For land cover classification, the algorithm gives state-of-the-art results. Additionally, FASTENER was tested on open feature selection data sets and compared to the state-of-the-art methods. With fewer model evaluations, the algorithm yields comparable results to DT-forward and is superior to FS-SDS. FASTENER can be used in any supervised machine learning scenario.

Download Full-text

Multisource Earth Observation Data for Land-Cover Classification Using Random Forest

IEEE Geoscience and Remote Sensing Letters ◽

10.1109/lgrs.2018.2806223 ◽

2018 ◽

Vol 15 (5) ◽

pp. 789-793 ◽

Cited By ~ 10

Author(s):

Zhigang Xu ◽

Jike Chen ◽

Junshi Xia ◽

Peijun Du ◽

Hongrui Zheng ◽

...

Keyword(s):

Random Forest ◽

Land Cover ◽

Land Cover Classification ◽

Earth Observation ◽

Observation Data ◽

Earth Observation Data

Download Full-text

Quantifying Tree Cover Loss in Urban Forests within Nairobi City Metropolitan Area from Earth Observation Data

Environmental Sciences Proceedings ◽

10.3390/iecf2020-07952 ◽

2020 ◽

Vol 3 (1) ◽

pp. 78

Author(s):

Francis Oloo ◽

Godwin Murithi ◽

Charlynne Jepkosgei

Keyword(s):

Land Cover ◽

Metropolitan Area ◽

Land Surface ◽

Urban Forest ◽

Urban Forests ◽

Earth Observation ◽

Tree Cover ◽

Observation Data ◽

Vegetation Health ◽

Earth Observation Data

Urban forests contribute significantly to the ecological integrity of urban areas and the quality of life of urban dwellers through air quality control, energy conservation, improving urban hydrology, and regulation of land surface temperatures (LST). However, urban forests are under threat due to human activities, natural calamities, and bioinvasion continually decimating forest cover. Few studies have used fine-scaled Earth observation data to understand the dynamics of tree cover loss in urban forests and the sustainability of such forests in the face of increasing urban population. The aim of this work was to quantify the spatial and temporal changes in urban forest characteristics and to assess the potential drivers of such changes. We used data on tree cover, normalized difference vegetation index (NDVI), and land cover change to quantify tree cover loss and changes in vegetation health in urban forests within the Nairobi metropolitan area in Kenya. We also used land cover data to visualize the potential link between tree cover loss and changes in land use characteristics. From approximately 6600 hectares (ha) of forest land, 720 ha have been lost between 2000 and 2019, representing about 11% loss in 20 years. In six of the urban forests, the trend of loss was positive, indicating a continuing disturbance of urban forests around Nairobi. Conversely, there was a negative trend in the annual mean NDVI values for each of the forests, indicating a potential deterioration of the vegetation health in the forests. A preliminary, visual inspection of high-resolution imagery in sample areas of tree cover loss showed that the main drivers of loss are the conversion of forest lands to residential areas and farmlands, implementation of big infrastructure projects that pass through the forests, and extraction of timber and other resources to support urban developments. The outcome of this study reveals the value of Earth observation data in monitoring urban forest resources.

Download Full-text

Space Observatory for carbon budget monitoring in Russian forests using Earth observations and modelling

10.5194/egusphere-egu2020-20567 ◽

2020 ◽

Author(s):

Sergey Bartalev

Keyword(s):

Land Cover ◽

Carbon Budget ◽

Earth Observation ◽

Forest Carbon ◽

Observation Data ◽

Space Observatory ◽

Russian Science ◽

Land Cover Types ◽

Russian Forests ◽

Earth Observation Data

Russian forest is a factor of global importance for implementation of international conventions on climate considering its potential for absorption and accumulation of the atmospheric carbon at an impressive scale. Considering recently adopted Paris agreement on climate the comprehensive and accurate estimation of Russian forests&#8217; carbon budget became a top priority research and development issue on national agenda. However existing quantitative estimates of Russian forests&#8217; carbon budget are of significant level of uncertainty. One of the most obvious reasons for such uncertainty is not sufficiently reliable and up-to-date information on characteristics of forests and their dynamics.The Russian Science Foundation has supported an ambitious research megaproject titled &#8220;Space Observatory for Forest Carbon&#8221; (SOFC) started in year 2019 and aimed at the development of a new concept and comprehensive methods for forest carbon budget monitoring using Earth observation data and forest growth and dynamics models. The main SOFC project objectives are as follows:- Development of a new concept and methodology for Russian forests and their carbon budget monitoring based on the integration of remote sensing and ground data along with improved models of forest structure and dynamics;- Development of new annually updated GIS databases on the characteristics and multi-annual dynamics of Russian forests;- Development of an informational system and technology for the continuous monitoring of Russian forests&#8217; carbon budget.Information necessary for carbon budget estimation includes data on various land cover types, forest characteristics (growing stock volume, species composition, age, site-index) and ecological parameters (Net Primary Production, heterotrophic respiration). Data on natural (fires, diseases and pests, windstorm, droughts) and anthropogenic (felling, pollution) forest disturbances causing deforestation, as well as information on subsequent reforestation processes are also vital.The existing remote sensing methods can provide significant part of missing country-wide information about the land cover types and forest characteristics for the national-scale carbon budget estimation and monitoring. Multi-year time series of this data since the beginning of the century allow modelling the forest dynamics and its biophysical characteristics. The Earth observation data derived information on forest fires&#8217; impact includes burnt area mapping over various land cover types as well as forest fire severity assessment allowing characterisation of fire induced carbon emissions. Furthermore, developed methods for processing and analysis of multi-year satellite data time series enable detection of forest cover changes caused by various destructive factors making it possible to substantially improve the accuracy of carbon budget estimation.Obtained information on forest ecosystems&#8217; parameters is used to improve existing and develop new approaches to forest carbon budget estimation, as well as to simulate various scenarios of Russian economy development depending on forest management practices and climate change trajectories.This work was supported by the Russian Science Foundation [grant number 19-77-30015].

Download Full-text