Ensemble of artificial neural network based land cover classifiers using satellite data

Bi-scale analysis of multitemporal land cover fractions for wetland vegetation mapping

Estimation of surface upward longwave radiation from MODIS and VIIRS clear-sky data in the Tibetan Plateau

Validation of water vapor retrieval from Moderate Resolution Imaging Spectro-radiometer (MODIS) in near infrared channels using GPS data over IAO-Hanle, in the trans-Himalayan region

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

The pace of change in land use and cover in Ethiopia depends on three main factors that cause pressure on agriculture land: resettlement programmes, population growth and increasing agricultural investments. Gambella is one of the regions of Ethiopia that attracts large-scale agricultural investments that extensively drive land use and cover changes in the region. The aim of this study is to examine the rate, extent and distribution of various land use and cover changes in Gambella Regional State, Ethiopia, from 1987 to 2017. The analysis is mainly based on Landsat 5 and Sentinel 2A satellite images and fieldwork. Two Landsat Thematic Mapper and a Sentinel 2A image were used for determining the maximum likelihood of land use/cover classification. The results show that farmland decreased by 26 km2 from 1987 to 2000; however, during the last two decades, agricultural land area increased by 599 km2, mainly at the cost of tropical grasslands and forests. We found that areas cultivated by smallholder farmers increased by 9.17% from 1987 to 2000. However, small-scale farm activities decreased by 7% from 2000 to 2017. Areas cultivated by large-scale state farms totalled 202 km2 in 1987; but by 2000, this large-scale state farming had been completely abandoned by the state, and as a result, its land use has decreased to zero. Despite this, in 2017 large-scale farming increased to 746 km2. In addition, Gambella National Park, which is the nation's largest national park and ecosystem, was also largely affected by Land Use and Land Cover changes. The conversion of savannah/tropical grasslands to agricultural farmland has caused varied and extensive environmental degradation to the park. The Land Use and Land Cover changes in the Gambella region are discussed on the basis of underlying socioeconomic factors.

The moderate resolution imaging spectroradiometer (MODIS) is one of the widely used sensors to address environmental and climate change subjects with a daily global coverage. MODIS Collection 6 aerosol products at 10-km resolution are used in this study to monitor aerosol variability and assess its uncertainty using ground-based measurements. The aerosol optical depth (AOD) is retrieved by different algorithms based on the pixel surface, determining between land and ocean. Using data collected from Sidi Salem Aerosol Robotic Network (AERONET) station, we computed the accuracy for aerosol optical depth (AOD) retrieved from MODIS aboard the AQUA satellite using two validation methods. The results show a good agreement between MODIS and AERONET data for the study period using both the algorithms. We obtained high values of the correlation coefficient. These findings indicate that MODIS data perform well over Ben Salem AERONET station and are recommended for air quality monitoring over Tunisia. The conducted validation throughout the AERONET leads to a degree of confidence that allows a deep investigation of the AOD spatial variability over Tunisia. Then, MODIS data shows high performance with good certainty to identify the principal dust sources and typical transport paths occurring on the study region.

The authors provide a method based on ensembles of artificial neural networks (ANNs) that, fed with supervised training data, are able to estimate rotational speed of the machine under investigation. Ensembles of various ANNs trained using different algorithms provide reliability of the method and protection from unfortunate initial weights distribution. The method is validated on the basis of data gathered in large amount of experiments performed in epicyclic gearbox test bed

As one of the last agricultural frontiers of the humid tropics, Amazonia is the largest area of the world currently undergoing frontier settlement. Although the earliest intrusions of foreign populations into Amazonia date from pre-Hispanic times, the large-scale entrance of peasant colonists into the vast region is a recent phenomenon. Much of this movement represents the spontaneous migration of peoples, but governments in the region have also become increasingly interested in opening up and integrating Amazonia to national and international economies. These actions are frequently seen as potential solutions to a number of national problems, including the need to increase agricultural production, correct spatial imbalances in the distribution of population, exploit frontier lands for reasons of national security, and defuse potentially serious political problems resulting from the existing agrarian structure, landlessness, and unemployment. The upper basin of the Amazon in Ecuador, bordering on the eastern slopes of the Andes, is one such area of frontier settlement. Recent decades have witnessed the rapid conversion of these Amazonian forests to agricultural uses through a series of schemes bearing such labels as land development and colonization. Most forest intervention in the region has come at the hands of colonist farmers attempting to establish land claims along transport routes originally constructed to aid in petroleum exploration and exploitation. These are farmers who formerly have made a living in long-established farmlands and who, for various reasons (population pressures, pervasive poverty, maldistribution of farmland, lack of inputs for intensive cultivation, lack of nonagrarian livelihood opportunities, and generally inadequate rural development) have been increasingly squeezed out of their homelands. A marginal person by virtue of his low socioeconomic and political status, the farmer often perceives

Miombo woodlands (MW) are increasingly experiencing widespread land use and land cover change (LULCC). This study explores the influence of fire, agriculture, and slope variability on LULCC in the miombo of the Beira Corridor. Land use and land cover data were derived from three Landsat images for 2001, 2008, and 2018. Slope attributes were derived from the Shuttle Radar Topography Mission (SRTM). Monthly burned data of Moderate-Resolution Imaging Spectroradiometer (MODIS) were used to map fire frequency. The derived data were then used to investigate the relationship between LULCC and fire, agriculture, and slope, based on geographically weighted regression (GWR). In addition, the relationship between LULCC and slope was assessed. Our findings indicate that fire frequency, agriculture, and slope were significantly spatially non-stationary. We found that LULCC was negatively correlated with agriculture in open miombo, but positively correlated in dense miombo. A positive relationship between LULCC and fire was found for dense and open miombo. Changes in agriculture, dense miombo, and open miombo increased towards high slopes. The study improves the understanding of the spatial effect of LULCC drivers. The development and implementation of effective fire management actions is required to promote sustainable forest management and preservation of critical ecosystem services.

The objective of this research is into detecting sea ice by using PALSAR (Phased-Array type L-band SAR) polarimetric data. It is generally difficult to detect thin sea ice area by using the methods based on the backscattering coefficient. We propose a new method utilizing scattering entropy to detect sea ice. This paper shows the results of extracting sea ice area from PALSAR fully polarimetric data acquired from 2009 to 2010. The MODIS (Moderate Resolution Imaging Spectroradiometer) data are used as sea ice reference. The threshold of PALSAR scattering entropy to discriminate sea ice from open water is determined from the distribution of scattering entropy for both sea ice and open water. We compared PALSAR derived sea ice area with MODIS derived area. Since most of PALSAR detected sea ice area is also detected by MODIS data, we can conclude that our proposed method is reliable to detect thin sea ice area in the Sea of Okhotsk. The high resolution backscattering and scattering entropy images give us an idea that there are some difficulties in detecting thin sea ice only by backscattering coefficient.

ABSTRACTIn Brazil, the main biofuel crop is sugarcane, and with its rapid expansion, there is much debate about what land uses and land covers it is replacing, and what are the associated environmental and social impacts. Some argue sugarcane is mainly replacing cattle pasture, thus having minimal impacts on native vegetation and small-scale family farming. In contrast, others claim sugarcane is replacing cropland traditionally under soybeans, rice, beans, and corn. Thus, food security is negatively affected and small-scale family farming livelihoods and culture are threatened. This is a proof-of-concept paper illustrating methods contributing toward the resolution of such debates. First we map land use and cover change in areas undergoing sugarcane expansion using satellite data from MODIS (Moderate Resolution Imaging Spectroradiometer); second, we test the hypothesis that sugarcane is replacing traditional annual crops using intensity analysis, via a case study of land change in the municipality of Pedro Afonso, Tocantins in northern Brazil between the 2008–2013 crop years. Maps matched reference data with overall agreements between 87–91%. Intensity analysis confirmed sugarcane is replacing annual crops much more than cattle pasture and other land uses and covers, pointing to particular economic and social processes driving land change.

Development of the GLASS 250-m leaf area index product (version 6) from MODIS data using the bidirectional LSTM deep learning model

Dinocysts as proxy of primary productivity in mid–high latitudes of the Northern Hemisphere

A surface reflectance correction model to improve the retrieval of MISR aerosol optical depth supported by MODIS data

PhotoVoltaic (PV) plants can provide important economic and environmental benefits to electric systems. On the other hand, the variability of the solar source leads to technical challenges in grid management as PV penetration rates increase continuously. For this reason, PV power forecasting represents a crucial tool for uncertainty management to ensure system stability. In this paper, a novel hybrid methodology for the PV forecasting is presented. The proposed approach can exploit clear-sky models or an ensemble of artificial neural networks, according to day-ahead weather forecast. In particular, the selection among these techniques is performed through a decision tree approach, which is designed to choose the best method among those aforementioned. The presented methodology has been validated on a real PV plant with very promising results.