Listing 1 - 10 of 24 | << page >> |
Sort by
|
Choose an application
Gully erosion is the removal of soil by surface runoff, typically on hillsides. This process creates what we called a gully, which is represented by a ravine with a head-cut and high slope variations. Gully erosion has negative impacts on people's activities but also on the infrastructures. Some regions, such as Africa, suffer more from these impacts. Several researches were made to understand Gully erosion and build models to detect gullies in order to potentially reduce its impacts. However, current models do not work at a country-wide or continent-wide scale. The purpose of this master thesis is to determine if neural networks can be used as models to predict gullies with the help of freely worldwide available satellite data. The first step was to create a database composed of satellite images representing gully and no-gully points. To perform the predictions, three different models were used: a baseline, a CNN, and a ResNet. These models were tested on different data sets i.e., Ethiopia and Africa data sets. The data sets are based on the satellite images database from which different features are extracted. Results obtained with baseline model are closed to a random classifier for any data set configuration. The CNN and ResNet perform better on the configuration of some data sets, in particular on the data sets that do not separate sites between train and test sets. This non-distinct separation between sites implies models are good at predicting similar images than those seen during the training. When data set configuration forced a distinction in sites used to train and test the models, which is the configuration required to have models able to predict gullies on a totally new site, results obtained are also close to a random classifier. These results point out some limitations of the current database i.e. data points similarity, the quantity of labeled data, and the resolution of satellite images. However, these limitations could be reduced and future work ideas, with preliminary results, are proposed in this work. These perspectives show some improvements with an accuracy close to 0.6. The work achieved in this master thesis is a first step for the development of deep learning architectures to predict gully headcuts at a large scale. This brings some guidance to improve results and possibly to have powerful model.
Choose an application
L’impact causé par le ravinement est une réalité, mais c’est une question qui reste peu quantifiée pour la majorité des villes affectées en RD Congo. De toutes les villes frappées par ce phénomène du ravinement, seule la ville de Kinshasa et, dans une moindre mesure Butembo, sont documentées en termes d’analyse d’inventaires. En raison de ce manque d’étude, il y a actuellement très peu d'informations sur le dommage total causé par les ravins urbains en RD Congo. Le but de cette étude est de faire une première quantification de l’impact de ces processus sur les bâtis et sur le nombre des personnes affectées dans les villes concernées. Partant d’une cartographie à l’aide de l’imagerie Google Earth, et basés sur une analyse exploratoire antérieure, nous avons identifié 20 villes touchées par le ravinement et dont la plupart s’étendent sur les sables tertiaires du Kalahari, dans le plateau du Kasaï. Un total de 998 ravins a été cartographié, dont 86% actives. En analysant l’évolution de ces ravins, nous avons répertorié 1463 maisons qui ont été détruites. Une forte corrélation entre le taux d’expansion des ravins et le nombre des maisons détruites a été observée. 386 ravins affectent des routes. Les densités de ces ravins urbains varient de 0.12% à 4.66%. En les combinant avec des estimations de la population vivant dans chaque ville, une première quantification du nombre total de personnes affectées par les ravins urbains a été réalisée. Ce nombre s’élève à 212 242 personnes. Les villes de Kinshasa, Mbujimayi, Tshikapa, Kananga, Kabinda, Kikwit sont les plus touchées. Dans l’hypothèse où ces ravins, comme montré à Kinshasa, sont liés à la croissance urbaine, on peut supposer que la très grande majorité d’entre eux ont moins de 30 ans. Si un taux d’expansion linéaire des ravins est supposé (ce qui n’est pas encore analysé), on peut dire que plus de 7000 personnes sont nouvellement affectées par an. Cela sous-entend que leurs maisons ont été probablement détruites, sans compter d’autres dommages indirects. A noter qu’il s’agit d’une estimation qui devra certainement être revue à la hausse, étant donné que la résolution spatiale, spectrale (et temporelle) des images Google Earth n’est pas toujours optimale et qu’il y a certainement d’autres villes affectées qui n’ont pas été considérées par cette étude. Cette première estimation montre que le ravinement urbain constitue un grave problème en RD Congo, et qu’il est nécessaire de poursuivre les recherches pour mieux comprendre les processus qui y sont associés et aussi, à terme, prévenir et atténuer ses impacts. Les résultats et ainsi que la base de données de cette étude constituent une première étape importante. The impact caused by the gullying is a reality, but it is an issue that remains little quantified for the majority of affected cities in DR Congo. Of all the cities hit by this phenomenon of gullying, only the city of Kinshasa and, to a lesser extent, Butembo, are documented in terms of inventory analysis. Due to this lack of study, there is currently very little information on the total damage caused by urban Gullies in DR Congo. The purpose of this study is to make a first quantification of the impact of these processes on the buildings and the number of people affected in the cities concerned. Based on mapping using Google Earth imagery, and based on previous exploratory analysis, we have identified 20 cities affected by gullying, most of which extend over the Kalahari tertiary sands in the plateau of Kasai. 998 Gullies have been mapped, of which 86% are active. By analyzing the evolution of these Gullies, we have listed 1463 houses that have been destroyed. A strong correlation between the rate of gully expansion and the number of houses destroyed was observed. 386 gullies affect roads. The densities of these urban Gullies range from 0.12% to 4.66%. Combining them with estimates of the population living in each city, a first quantification of the total number of people affected by the urban Gullies was carried out. This number stands at 212 242 people. The cities of Kinshasa, Mbujimayi, Tshikapa, Kananga, Kabinda, Kikwit are the most affected. In the hypothesis that these Gullies, as shown in Kinshasa, are linked to urban growth, we can assume that the vast majority of them are under 30 years old. If a rate of linear expansion of the Gullies is assumed (which is not yet analyzed), it can be said that more than 7000 people are newly affected per year. This implies that their homes were probably destroyed, not to mention other indirect damages. Note that this is an estimate that will certainly have to be revised upwards, given that the spatial, spectral (and temporal) resolution of Google Earth images is not always optimal and that there is certainly other affected cities that were not considered by this study. This first estimate shows that urban gullying is a serious problem in DR Congo, and that further research is needed to better understand the associated processes and, ultimately, to prevent and mitigate its impacts. The results and the database of this study is an important first step.
ravinement urbain --- RD Congo --- impact --- maisons --- population --- urban --- gully --- DR Congo --- impact --- houses --- population --- Physique, chimie, mathématiques & sciences de la terre > Sciences de la terre & géographie physique
Choose an application
The purpose of this book is to provide novel results related to soil water erosion that could help landowners and land-users, farmers, politicians, and other representatives of our global society to protect and, if possible, improve the quality and quantity of our precious soil resources. Published papers on the topics are related to new ways of mapping, maps with more detailed input data, maps about areas that have never been mapped before, sediment yield estimations, modelling sheets and gully erosion, USLE models, RUSLE models, dams which stop sediment runoff, sediment influx, solute transport, soil detachment capacities, badland morphology, freeze-thaw cycles, armed conflicts, use of rainfall simulators, rainfall erosivity, soil erodibility, etc.
Technology: general issues --- History of engineering & technology --- gully head-cuts --- machine learning modeling --- soil erosion --- Iran --- R-factor --- USLE --- rainfall intensity --- modeling --- radar climatology --- RADKLIM --- rain gauge --- sediment flux --- total soil loss --- watershed characteristics --- PCA analysis --- RUSLE (Revised Universal Soil Loss Equation) --- WaTEM/SEDEM --- Czech Republic --- residential areas --- loess --- meltwater flow --- runoff and sediment yield --- hydraulic parameter --- comparability --- infiltration --- rainfall simulation --- runoff --- RUSLE --- land cover change --- armed conflict --- Northern Al-Kabeer river Syria --- freeze-thaw cycles --- loamy soil --- soil property --- soil detachment capacity --- Loess Plateau --- badlands --- morphological changes --- land use change --- Emilia Apennines (Northern Italy) --- multiple-tracer experiments --- precipitation amounts --- preferential flow --- solute transport --- protection forest --- irrigation --- sediment --- overland flow --- soil loss --- watershed --- sediment connectivity --- connection mode --- connection degree --- land management --- gully geometry --- dynamic erosion model --- stable gully --- area–slope approach --- field measurement --- water erosion model --- event scale --- sediment yield --- Chenab river --- remote sensing --- GIS --- n/a --- area-slope approach
Choose an application
The purpose of this book is to provide novel results related to soil water erosion that could help landowners and land-users, farmers, politicians, and other representatives of our global society to protect and, if possible, improve the quality and quantity of our precious soil resources. Published papers on the topics are related to new ways of mapping, maps with more detailed input data, maps about areas that have never been mapped before, sediment yield estimations, modelling sheets and gully erosion, USLE models, RUSLE models, dams which stop sediment runoff, sediment influx, solute transport, soil detachment capacities, badland morphology, freeze-thaw cycles, armed conflicts, use of rainfall simulators, rainfall erosivity, soil erodibility, etc.
gully head-cuts --- machine learning modeling --- soil erosion --- Iran --- R-factor --- USLE --- rainfall intensity --- modeling --- radar climatology --- RADKLIM --- rain gauge --- sediment flux --- total soil loss --- watershed characteristics --- PCA analysis --- RUSLE (Revised Universal Soil Loss Equation) --- WaTEM/SEDEM --- Czech Republic --- residential areas --- loess --- meltwater flow --- runoff and sediment yield --- hydraulic parameter --- comparability --- infiltration --- rainfall simulation --- runoff --- RUSLE --- land cover change --- armed conflict --- Northern Al-Kabeer river Syria --- freeze-thaw cycles --- loamy soil --- soil property --- soil detachment capacity --- Loess Plateau --- badlands --- morphological changes --- land use change --- Emilia Apennines (Northern Italy) --- multiple-tracer experiments --- precipitation amounts --- preferential flow --- solute transport --- protection forest --- irrigation --- sediment --- overland flow --- soil loss --- watershed --- sediment connectivity --- connection mode --- connection degree --- land management --- gully geometry --- dynamic erosion model --- stable gully --- area–slope approach --- field measurement --- water erosion model --- event scale --- sediment yield --- Chenab river --- remote sensing --- GIS --- n/a --- area-slope approach
Choose an application
The purpose of this book is to provide novel results related to soil water erosion that could help landowners and land-users, farmers, politicians, and other representatives of our global society to protect and, if possible, improve the quality and quantity of our precious soil resources. Published papers on the topics are related to new ways of mapping, maps with more detailed input data, maps about areas that have never been mapped before, sediment yield estimations, modelling sheets and gully erosion, USLE models, RUSLE models, dams which stop sediment runoff, sediment influx, solute transport, soil detachment capacities, badland morphology, freeze-thaw cycles, armed conflicts, use of rainfall simulators, rainfall erosivity, soil erodibility, etc.
Technology: general issues --- History of engineering & technology --- gully head-cuts --- machine learning modeling --- soil erosion --- Iran --- R-factor --- USLE --- rainfall intensity --- modeling --- radar climatology --- RADKLIM --- rain gauge --- sediment flux --- total soil loss --- watershed characteristics --- PCA analysis --- RUSLE (Revised Universal Soil Loss Equation) --- WaTEM/SEDEM --- Czech Republic --- residential areas --- loess --- meltwater flow --- runoff and sediment yield --- hydraulic parameter --- comparability --- infiltration --- rainfall simulation --- runoff --- RUSLE --- land cover change --- armed conflict --- Northern Al-Kabeer river Syria --- freeze-thaw cycles --- loamy soil --- soil property --- soil detachment capacity --- Loess Plateau --- badlands --- morphological changes --- land use change --- Emilia Apennines (Northern Italy) --- multiple-tracer experiments --- precipitation amounts --- preferential flow --- solute transport --- protection forest --- irrigation --- sediment --- overland flow --- soil loss --- watershed --- sediment connectivity --- connection mode --- connection degree --- land management --- gully geometry --- dynamic erosion model --- stable gully --- area-slope approach --- field measurement --- water erosion model --- event scale --- sediment yield --- Chenab river --- remote sensing --- GIS
Choose an application
This Special Issue includes manuscripts about soil erosion and degradation processes and the accelerated rates due to hydrological processes and climate change. The new research included in this issue focuses on measurements, modeling, and experiments in field or laboratory conditions developed at different scales (pedon, hillslope, and catchment). This Special Issue received investigations from different parts of the world such as Ethiopia, Morocco, China, Iran, Italy, Portugal, Greece, and Spain, among others. We are happy to see that all papers presented findings characterized as unconventional, provocative, innovative, and methodologically new. We hope that the readers of the journal Water can enjoy and learn about hydrology and soil erosion using the published material, and share the results with the scientific community, policymakers, and stakeholders to continue this amazing adventure, facing plenty of issues and challenges.
Research & information: general --- soil --- natural resources --- modeling --- hybrid model --- Bastam watershed --- splash erosion --- environmental assessment --- soil erosion --- rainfall simulation --- loess landslide --- agricultural irrigation --- field investigation --- static liquefaction --- RUSLE --- soil erodibility --- gravel content --- Chaohu Lake Basin --- vineyards --- soil management --- tractor traffic --- hydrological properties --- erosion --- runoff --- hydraulic conductivity --- soil water conservation --- argan --- South Morocco --- soil degradation --- tree --- intertree --- Ethiopian highlands --- eucalyptus --- gully --- soil loss --- soil and water conservation practices --- gully erosion susceptibility --- GIS --- robustness --- MARS algorithm --- rainfall-runoff processes --- hillslope morphology --- surface flow --- roughness --- land degradation --- soil conservation --- remote sensing --- urbanization --- land-use --- suspended sediment concentration --- spatiotemporal variation --- hydrological processes --- different scales --- models --- experiments
Choose an application
This Special Issue includes manuscripts about soil erosion and degradation processes and the accelerated rates due to hydrological processes and climate change. The new research included in this issue focuses on measurements, modeling, and experiments in field or laboratory conditions developed at different scales (pedon, hillslope, and catchment). This Special Issue received investigations from different parts of the world such as Ethiopia, Morocco, China, Iran, Italy, Portugal, Greece, and Spain, among others. We are happy to see that all papers presented findings characterized as unconventional, provocative, innovative, and methodologically new. We hope that the readers of the journal Water can enjoy and learn about hydrology and soil erosion using the published material, and share the results with the scientific community, policymakers, and stakeholders to continue this amazing adventure, facing plenty of issues and challenges.
soil --- natural resources --- modeling --- hybrid model --- Bastam watershed --- splash erosion --- environmental assessment --- soil erosion --- rainfall simulation --- loess landslide --- agricultural irrigation --- field investigation --- static liquefaction --- RUSLE --- soil erodibility --- gravel content --- Chaohu Lake Basin --- vineyards --- soil management --- tractor traffic --- hydrological properties --- erosion --- runoff --- hydraulic conductivity --- soil water conservation --- argan --- South Morocco --- soil degradation --- tree --- intertree --- Ethiopian highlands --- eucalyptus --- gully --- soil loss --- soil and water conservation practices --- gully erosion susceptibility --- GIS --- robustness --- MARS algorithm --- rainfall-runoff processes --- hillslope morphology --- surface flow --- roughness --- land degradation --- soil conservation --- remote sensing --- urbanization --- land-use --- suspended sediment concentration --- spatiotemporal variation --- hydrological processes --- different scales --- models --- experiments
Choose an application
This Special Issue includes manuscripts about soil erosion and degradation processes and the accelerated rates due to hydrological processes and climate change. The new research included in this issue focuses on measurements, modeling, and experiments in field or laboratory conditions developed at different scales (pedon, hillslope, and catchment). This Special Issue received investigations from different parts of the world such as Ethiopia, Morocco, China, Iran, Italy, Portugal, Greece, and Spain, among others. We are happy to see that all papers presented findings characterized as unconventional, provocative, innovative, and methodologically new. We hope that the readers of the journal Water can enjoy and learn about hydrology and soil erosion using the published material, and share the results with the scientific community, policymakers, and stakeholders to continue this amazing adventure, facing plenty of issues and challenges.
Research & information: general --- soil --- natural resources --- modeling --- hybrid model --- Bastam watershed --- splash erosion --- environmental assessment --- soil erosion --- rainfall simulation --- loess landslide --- agricultural irrigation --- field investigation --- static liquefaction --- RUSLE --- soil erodibility --- gravel content --- Chaohu Lake Basin --- vineyards --- soil management --- tractor traffic --- hydrological properties --- erosion --- runoff --- hydraulic conductivity --- soil water conservation --- argan --- South Morocco --- soil degradation --- tree --- intertree --- Ethiopian highlands --- eucalyptus --- gully --- soil loss --- soil and water conservation practices --- gully erosion susceptibility --- GIS --- robustness --- MARS algorithm --- rainfall-runoff processes --- hillslope morphology --- surface flow --- roughness --- land degradation --- soil conservation --- remote sensing --- urbanization --- land-use --- suspended sediment concentration --- spatiotemporal variation --- hydrological processes --- different scales --- models --- experiments
Choose an application
The predicted climate change is likely to cause extreme storm events and, subsequently, catastrophic disasters, including soil erosion, debris and landslide formation, loss of life, etc. In the decade from 1976, natural disasters affected less than a billion lives. These numbers have surged in the last decade alone. It is said that natural disasters have affected over 3 billion lives, killed on average 750,000 people, and cost more than 600 billion US dollars. Of these numbers, a greater proportion are due to sediment-related disasters, and these numbers are an indication of the amount of work still to be done in the field of soil erosion, conservation, and landslides. Scientists, engineers, and planners are all under immense pressure to develop and improve existing scientific tools to model erosion and landslides and, in the process, better conserve the soil. Therefore, the purpose of this Special Issue is to improve our knowledge on the processes and mechanics of soil erosion and landslides. In turn, these will be crucial in developing the right tools and models for soil and water conservation, disaster mitigation, and early warning systems.
Technology: general issues --- Environmental science, engineering & technology --- landslide --- image classification --- spectrum similarity analysis --- extreme rainfall-induced landslide susceptibility model --- landslide ratio-based logistic regression --- landslide evolution --- Typhoon Morakot --- Taiwan --- vegetation community --- vegetation importance value --- root system --- soil erosion --- grey correlation analysis --- sediment yield --- RUSLE --- Lancang–Mekong River basin --- rainfall threshold --- landslide probability model --- debris flow --- Zechawa Gully --- mitigation countermeasures --- Jiuzhaigou Valley --- water erosion --- susceptibility --- Gaussian process --- climate change --- radial basis function kernel --- weighted subspace random forest --- extreme events --- extreme weather --- naive Bayes --- feature selection --- machine learning --- hydrologic model --- simulated annealing --- earth system science --- PSED Model --- loess --- ICU --- static liquefaction --- mechanical behavior --- pore structure --- alpine swamp meadow --- alpine meadow --- degradation of riparian vegetation --- root distribution --- tensile strength --- tensile crack --- soil management --- land cover changes --- Syria --- hillslopes --- gully erosion --- vegetation restoration --- soil erodibility --- land use --- bridge pier --- overfall --- scour --- landform change impact on pier --- shallow water equations --- wet-dry front --- outburst flood --- TVD-scheme --- MUSCL-Hancock method --- laboratory model test --- extreme rainfall --- rill erosion --- shallow landslides --- deep lip surface --- safety factor --- rainfall erosivity factor --- USLE R --- Deep Neural Network --- tree ring --- dendrogeomorphology --- landslide activity --- deciduous broadleaved tree --- Shirakami Mountains --- spatiotemporal cluster analysis --- landslide hotspots --- dam breach --- seepage --- overtopping --- seismic signal --- flume test --- breach model --- n/a --- Lancang-Mekong River basin
Choose an application
The predicted climate change is likely to cause extreme storm events and, subsequently, catastrophic disasters, including soil erosion, debris and landslide formation, loss of life, etc. In the decade from 1976, natural disasters affected less than a billion lives. These numbers have surged in the last decade alone. It is said that natural disasters have affected over 3 billion lives, killed on average 750,000 people, and cost more than 600 billion US dollars. Of these numbers, a greater proportion are due to sediment-related disasters, and these numbers are an indication of the amount of work still to be done in the field of soil erosion, conservation, and landslides. Scientists, engineers, and planners are all under immense pressure to develop and improve existing scientific tools to model erosion and landslides and, in the process, better conserve the soil. Therefore, the purpose of this Special Issue is to improve our knowledge on the processes and mechanics of soil erosion and landslides. In turn, these will be crucial in developing the right tools and models for soil and water conservation, disaster mitigation, and early warning systems.
landslide --- image classification --- spectrum similarity analysis --- extreme rainfall-induced landslide susceptibility model --- landslide ratio-based logistic regression --- landslide evolution --- Typhoon Morakot --- Taiwan --- vegetation community --- vegetation importance value --- root system --- soil erosion --- grey correlation analysis --- sediment yield --- RUSLE --- Lancang–Mekong River basin --- rainfall threshold --- landslide probability model --- debris flow --- Zechawa Gully --- mitigation countermeasures --- Jiuzhaigou Valley --- water erosion --- susceptibility --- Gaussian process --- climate change --- radial basis function kernel --- weighted subspace random forest --- extreme events --- extreme weather --- naive Bayes --- feature selection --- machine learning --- hydrologic model --- simulated annealing --- earth system science --- PSED Model --- loess --- ICU --- static liquefaction --- mechanical behavior --- pore structure --- alpine swamp meadow --- alpine meadow --- degradation of riparian vegetation --- root distribution --- tensile strength --- tensile crack --- soil management --- land cover changes --- Syria --- hillslopes --- gully erosion --- vegetation restoration --- soil erodibility --- land use --- bridge pier --- overfall --- scour --- landform change impact on pier --- shallow water equations --- wet-dry front --- outburst flood --- TVD-scheme --- MUSCL-Hancock method --- laboratory model test --- extreme rainfall --- rill erosion --- shallow landslides --- deep lip surface --- safety factor --- rainfall erosivity factor --- USLE R --- Deep Neural Network --- tree ring --- dendrogeomorphology --- landslide activity --- deciduous broadleaved tree --- Shirakami Mountains --- spatiotemporal cluster analysis --- landslide hotspots --- dam breach --- seepage --- overtopping --- seismic signal --- flume test --- breach model --- n/a --- Lancang-Mekong River basin
Listing 1 - 10 of 24 | << page >> |
Sort by
|