Search results for "work"

Convolutional Neural Networks for Cloud Screening: Transfer Learning from Landsat-8 to Proba-V

2018

Cloud detection is a key issue for exploiting the information from Earth observation satellites multispectral sensors. For Proba-V, cloud detection is challenging due to the limited number of spectral bands. Advanced machine learning methods, such as convolutional neural networks (CNN), have shown to work well on this problem provided enough labeled data. However, simultaneous collocated information about the presence of clouds is usually not available or requires a great amount of manual labor. In this work, we propose to learn from the available Landsat −8 cloud masks datasets and transfer this learning to solve the Proba-V cloud detection problem. CNN are trained with Landsat images adap…

Tree Species Classification of Drone Hyperspectral and RGB Imagery with Deep Learning Convolutional Neural Networks

2020

Interest in drone solutions in forestry applications is growing. Using drones, datasets can be captured flexibly and at high spatial and temporal resolutions when needed. In forestry applications, fundamental tasks include the detection of individual trees, tree species classification, biomass estimation, etc. Deep neural networks (DNN) have shown superior results when comparing with conventional machine learning methods such as multi-layer perceptron (MLP) in cases of huge input data. The objective of this research is to investigate 3D convolutional neural networks (3D-CNN) to classify three major tree species in a boreal forest: pine, spruce, and birch. The proposed 3D-CNN models were emp…

Estimating Missing Information by Cluster Analysis and Normalized Convolution

2018

International audience; Smart city deals with the improvement of their citizens' quality of life. Numerous ad-hoc sensors need to be deployed to know humans' activities as well as the conditions in which these actions take place. Even if these sensors are cheaper and cheaper, their installation and maintenance cost increases rapidly with their number. We propose a methodology to limit the number of sensors to deploy by using a standard clustering technique and the normalized convolution to estimate environmental information whereas sensors are actually missing. In spite of its simplicity, our methodology lets us provide accurate assesses.

Supporting group decision makers to locate temporary relief distribution centres after sudden-onset disasters

2020

International audience; In the humanitarian response, multiple decision-makers (DMs) need to collaborate in various problems, such as locating temporary relief distribution centres (RDCs). Several studies have argued that maximising demand coverage, reducing logistics costs and minimising response time are among the critical objectives when locating RDCs after a sudden-onset disaster. However, these objectives are often conflicting and the trade-offs can considerably complicate the situation for finding a consensus.To address the challenge and support the DMs, we suggest investigating the stability of non-dominated alternatives derived from a multi-objective model based on Monte Carlo Simul…

Trends in global research in deforestation. A bibliometric analysis

2018

The main aim of this study was to analyse topics of research, scientific production, collaboration among countries, and most cited papers on deforestation through a bibliometric and social network study of articles found in the Web of Science database. The most productive subject areas corresponded to Environmental Sciences, Ecology and Environmental Studies. The articles were published in 458 different journals. A total of 2051 research articles were obtained. The main challenges identified for deforestation include “land use change” “conservation” “climate change” “rain forest” and “reducing emissions from deforestation and degradation”. Social and economic topics are understudied. An imp…

Modelling the Effects of Climate Change on the Supply of Inorganic Nitrogen

2009

Human-induced changes in the nitrogen cycle due to the increased use of artificial fertilisers, the cultivation of nitrogen-fixing crops and atmospheric deposition have made nitrogen pollution to surface waters a long-standing cause for concern. In Europe, legislation has been introduced to minimise the risk of water quality degradation from excessive nitrogen inputs e.g., the European Union Nitrates Directive (EU, 1991), Drinking Water Directive (EU, 1998) and Water Framework Directive (EU, 2000). Coastal regions in particular have been an important focus, since coastal eutrophication has been attributed to increased fluxes of nitrogen from the landscape (Howarth et al., 1996; Boesch et al…

Exploring Effective Ecosystems in Disaster Management: Case studies of Japan and Nepal

2017

Transferring deep learning models for cloud detection between Landsat-8 and Proba-V

2020

Abstract Accurate cloud detection algorithms are mandatory to analyze the large streams of data coming from the different optical Earth observation satellites. Deep learning (DL) based cloud detection schemes provide very accurate cloud detection models. However, training these models for a given sensor requires large datasets of manually labeled samples, which are very costly or even impossible to create when the satellite has not been launched yet. In this work, we present an approach that exploits manually labeled datasets from one satellite to train deep learning models for cloud detection that can be applied (or transferred) to other satellites. We take into account the physical proper…

Recreational noise pollution of traditional festivals reduces the juvenile productivity of an avian urban bioindicator.

2021

Noise is a pollutant of emergent concern for ecologists and conservation biologists. Recreational noise pollution, especially unpredictable and intermittent sounds, and its effects on wildlife and biodiversity have been poorly studied. Researchers have paid very little attention to the effect of noisy traditional festivals (fireworks and powder-guns). This study aimed to explore the effect of these recreational activities on the juvenile productivity of an urban avian bioindicator: the house sparrow. We studied five pairs of localities in the Valencia Region (E Spain) with noisy traditional festivals. Each pair was composed of one locality with festivals during the breeding season and the c…

Planktic foraminiferal changes in the western Mediterranean Anthropocene

2021

The increase in anthropogenic induced warming over the last two centuries is impacting marine environment. Planktic foraminifera are a globally distributed calcifying marine zooplankton responding sensitively to changes in sea surface temperatures and interacting with the food web structure. Here, we study two high resolution multicore records from two western Mediterranean Sea regions (Alboran and Balearic basins), areas highly affected by both natural climate change and anthropogenic warming. Cores cover the time interval from the Medieval Climate Anomaly to present. Reconstructed sea surface temperatures are in good agreement with other results, tracing temperature changes through the Co…