scholarly journals Continental-scale streamflow modeling of basins with reservoirs: towards a coherent deep-learning-based strategy

2021 ◽  
pp. 126455
Author(s):  
Wenyu Ouyang ◽  
Kathryn Lawson ◽  
Dapeng Feng ◽  
Lei Ye ◽  
Chi Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Continental Scale ◽  
Streamflow Modeling

scholarly journals Configuration and intercomparison of deep learning neural models for statistical downscaling

2020 ◽  
Vol 13 (4) ◽  
pp. 2109-2124 ◽  
Author(s):  
Jorge Baño-Medina ◽  
Rodrigo Manzanas ◽  
José Manuel Gutiérrez
Keyword(s):  
Climate Change ◽  
Deep Learning ◽  
Statistical Downscaling ◽  
Linear Models ◽  
Regional Climate ◽  
Added Value ◽  
Climate Conditions ◽  
Continental Scale ◽  
Spatial Features ◽  
Learning Techniques

Abstract. Deep learning techniques (in particular convolutional neural networks, CNNs) have recently emerged as a promising approach for statistical downscaling due to their ability to learn spatial features from huge spatiotemporal datasets. However, existing studies are based on complex models, applied to particular case studies and using simple validation frameworks, which makes a proper assessment of the (possible) added value offered by these techniques difficult. As a result, these models are usually seen as black boxes, generating distrust among the climate community, particularly in climate change applications. In this paper we undertake a comprehensive assessment of deep learning techniques for continental-scale statistical downscaling, building on the VALUE validation framework. In particular, different CNN models of increasing complexity are applied to downscale temperature and precipitation over Europe, comparing them with a few standard benchmark methods from VALUE (linear and generalized linear models) which have been traditionally used for this purpose. Besides analyzing the adequacy of different components and topologies, we also focus on their extrapolation capability, a critical point for their potential application in climate change studies. To do this, we use a warm test period as a surrogate for possible future climate conditions. Our results show that, while the added value of CNNs is mostly limited to the reproduction of extremes for temperature, these techniques do outperform the classic ones in the case of precipitation for most aspects considered. This overall good performance, together with the fact that they can be suitably applied to large regions (e.g., continents) without worrying about the spatial features being considered as predictors, can foster the use of statistical approaches in international initiatives such as Coordinated Regional Climate Downscaling Experiment (CORDEX).

scholarly journals Configuration and Intercomparison of Deep Learning Neural Models for Statistical Downscaling

2019 ◽  
Author(s):  
Jorge Baño-Medina ◽  
Rodrigo Manzanas ◽  
José Manuel Gutiérrez
Keyword(s):  
Climate Change ◽  
Deep Learning ◽  
Statistical Downscaling ◽  
Linear Models ◽  
Added Value ◽  
Climate Conditions ◽  
Continental Scale ◽  
Temperature And Precipitation ◽  
Spatial Features ◽  
Learning Techniques

Abstract. Deep learning techniques (in particular convolutional neural networks, CNNs) have recently emerged as a promising approach for statistical downscaling due to their ability to learn spatial features from huge spatio-temporal datasets. However, existing studies are based on complex models, applied to particular case studies and using simple validation frameworks, which makes difficult a proper assessment of the (possible) added value offered by these techniques. As a result, these models are usually seen as black-boxes generating distrust among the climate community, particularly in climate change problems. In this paper we undertake a comprehensive assessment of deep learning techniques for continental-scale statistical downscaling, building on the VALUE validation framework. In particular, different CNN models of increasing complexity are applied for downscaling temperature and precipitation over Europe, comparing them with a few standard benchmark methods from VALUE (linear and generalized linear models) which have been traditionally used for this purpose. Besides analyzing the adequacy of different components and topologies, we also focus on their extrapolation capability, a critical point for their possible application in climate change studies. To do this, we use a warm test period as surrogate of possible future climate conditions. Our results show that, whilst the added value of CNNs is mostly limited to the reproduction of extremes for temperature, these techniques do outperform the classic ones for the case of precipitation for most aspects considered. This overall good performance, together with the fact that they can be suitably applied to large regions (e.g. continents) without worrying about the spatial features being considered as predictors, can foster the use of statistical approaches in international initiatives such as CORDEX.

scholarly journals A Continental-Scale Assessment of Density, Size, Distribution and Historical Trends of Farm Dams Using Deep Learning Convolutional Neural Networks

2021 ◽  
Vol 13 (2) ◽  
pp. 319
Author(s):  
Martino E. Malerba ◽  
Nicholas Wright ◽  
Peter I. Macreadie
Keyword(s):  
Deep Learning ◽  
Rhode Island ◽  
South Australia ◽  
Remote Sensing Data ◽  
Agricultural Landscapes ◽  
Ecological Impacts ◽  
High Definition ◽  
Historical Trends ◽  
Continental Scale ◽  
Scale Assessment

Farm dams are a ubiquitous limnological feature of agricultural landscapes worldwide. While their primary function is to capture and store water, they also have disproportionally large effects on biodiversity and biogeochemical cycling, with important relevance to several Sustainable Development Goals (SDGs). However, the abundance and distribution of farm dams is unknown in most parts of the world. Therefore, we used artificial intelligence and remote sensing data to address this critical global information gap. Specifically, we trained a deep learning convolutional neural network (CNN) on high-definition satellite images to detect farm dams and carry out the first continental-scale assessment on density, distribution and historical trends. We found that in Australia there are 1.765 million farm dams that occupy an area larger than Rhode Island (4678 km2) and store over 20 times more water than Sydney Harbour (10,990 GL). The State of New South Wales recorded the highest number of farm dams (654,983; 37% of the total) and Victoria the highest overall density (1.73 dams km−2). We also estimated that 202,119 farm dams (11.5%) remain omitted from any maps, especially in South Australia, Western Australia and the Northern Territory. Three decades of historical records revealed an ongoing decrease in the construction rate of farm dams, from >3% per annum before 2000, to ~1% after 2000, to <0.05% after 2010—except in the Australian Capital Territory where rates have remained relatively high. We also found systematic trends in construction design: farm dams built in 2015 are on average 50% larger in surface area and contain 66% more water than those built in 1989. To facilitate sharing information on sustainable farm dam management with authorities, scientists, managers and local communities, we developed AusDams.org—a free interactive portal to visualise and generate statistics on the physical, environmental and ecological impacts of farm dams.

From Hydrometeorology to River Water Quality: Can a Deep Learning Model Predict Dissolved Oxygen at the Continental Scale?

2021 ◽  
Vol 55 (4) ◽  
pp. 2357-2368
Author(s):  
Wei Zhi ◽  
Dapeng Feng ◽  
Wen-Ping Tsai ◽  
Gary Sterle ◽  
Adrian Harpold ◽  
...  
Keyword(s):  
Water Quality ◽  
Deep Learning ◽  
Dissolved Oxygen ◽  
River Water ◽  
Learning Model ◽  
River Water Quality ◽  
Continental Scale ◽  
Deep Learning Model

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document