Filters








6,427 Hits in 4.7 sec

Machine Learning Emulation of Urban Land Surface Processes [article]

David Meyer, Sue Grimmond, Peter Dueben, Robin Hogan, Maarten van Reeuwijk
2021 arXiv   pre-print
Can we improve the modeling of urban land surface processes with machine learning (ML)?  ...  A prior comparison of urban land surface models (ULSMs) found that no single model is 'best' at predicting all common surface fluxes.  ...  We would also like to thank Andrew Coutts and Jason Beringer for supplying the observation data used in evaluations, as well as all those who contributed to the urban model  ... 
arXiv:2112.11429v2 fatcat:5wnfi5xporem7k6bc7uuzrzcqi

Machine Learning Emulation of Urban Land Surface Processes

David Meyer, Sue Grimmond, Peter Dueben, Robin Hogan, Maarten Reeuwijk
2022 Journal of Advances in Modeling Earth Systems  
In recent years, machine learning (ML) techniques have shown potential in several areas of meteorology (e.g.,  ...  Land surface models (LSM) parameterize energy exchanges between the surface and the atmosphere, providing the lower boundary conditions (e.g., radiative and turbulent heat fluxes) to atmospheric models  ...  The authors would also like to thank Andrew Coutts and Jason Beringer for supplying the observation data used in evaluations and those who contributed to the urban model comparison project.  ... 
doi:10.1029/2021ms002744 fatcat:ovryn6y7ijeglcmliwiul36ppe

Large model structural uncertainty in global projections of urban heat waves

Zhonghua Zheng, Lei Zhao, Keith W. Oleson
2021 Nature Communications  
Here, we use an urban climate emulator combined with large ensemble global climate simulations to show that, at the urban scale a large proportion of the variability results from the model structural uncertainty  ...  Omission of this uncertainty would considerably underestimate the risk of UHW.  ...  L.Z. acknowledges the financial support from the Start-up Grant from University of Illinois, Urbana-Champaign.  ... 
doi:10.1038/s41467-021-24113-9 pmid:34145293 fatcat:qlfcugz32ncflnty5gucshjyq4

A Review of Machine Learning Applications in Land Surface Modeling

Sujan Pal, Prateek Sharma
2021 Earth  
Land Surface Models (LSMs) are important components of the climate models, which help to capture the water, energy, and momentum exchange between the land surface and the atmosphere, providing lower boundary  ...  Machine learning (ML), as an artificial intelligence tool, has acquired significant progress in data-driven research in Earth sciences.  ...  Acknowledgments: We would like to thank the Department of Atmospheric Science of University of Illinois at Urbana-Champaign for providing us with resources for the study.  ... 
doi:10.3390/earth2010011 fatcat:76upaooyjzaazgyt6jz4y5ueue

Investigating important urban characteristics in the formation of urban heat islands: a machine learning approach

Sanglim Yoo
2018 Journal of Big Data  
into planning practice and to apply machine learning approach to identify highly determinant variables in the formation of urban heat islands.  ...  Using a parcel as a unit of analysis, this study proposed to use a machine learning approach to identify important variables in the formation of urban heat islands in Indianapolis, Indiana.  ...  Acknowledgements The author would like to thank the anonymous reviewers for their valuable comments and suggestions to improve the quality of this manuscript. Funding Not applicable.  ... 
doi:10.1186/s40537-018-0113-z fatcat:4somauu4dree5dog5iibish7xy

Monitoring sustainable development by means of earth observation data and machine learning: a review

Bruno Ferreira, Muriel Iten, Rui G. Silva
2020 Environmental Sciences Europe  
strongly suggesting the use of new Machine Learning techniques.  ...  A review on the Sustainable Development concept and its goals is presented followed by Earth Observation approaches relevant to this field, giving special attention to the contribution of Machine Learning  ...  • There is an increased need for new methods and techniques to process an ever-growing amount of Earth Observation data. • Machine Learning techniques are crucial in handling Earth Observation data given  ... 
doi:10.1186/s12302-020-00397-4 fatcat:edydkdkeljfrvh3srqzicgvyqa

The potential of geospatial analysis and Bayesian networks to enable i-Tree Eco assessment of existing tree inventories

Zofie Cimburova, David N. Barton
2020 Urban Forestry & Urban Greening  
Furthermore, we illustrate how machine learning with Bayesian networks can be used to extrapolate i-Tree Eco outputs and infer the value of the entire municipal inventory.  ...  Using a tree inventory of Oslo, Norway, as an example, we demonstrate the potential of geospatial and machine learning methods to supplement missing and incomplete i-Tree Eco attributes in existing municipal  ...  Furthermore, we would like to thank Meta Berghauser Pont (Chalmers University of Technology, Sweden), Yngve Karl Frøyen (Norwegian University of Science and Technology, Norway) and two anonymous reviewers  ... 
doi:10.1016/j.ufug.2020.126801 fatcat:pmss4mzj7nfsboxm7wbn7obmvq

Emulation of the Saint Venant Equations enables rapid and accurate predictions of infiltration and overland flow velocity on spatially heterogeneous surfaces

Octavia Crompton, Anneliese Sytsma, Sally Thompson
2019 Water Resources Research  
The emulation model predicts infiltration and peak flow velocities for every location on a hillslope with an arbitrary spatial pattern of impermeable and permeable surfaces but fixed soil, slope, and storm  ...  way forward for applications in dryland and urban settings and in supporting the development of potential connectivity indices.  ...  Introduction The partitioning of rainfall between infiltration and runoff at the land surface (Horton, 1933) strongly determines the hydrological behavior of the urban, montane, agricultural, and desert  ... 
doi:10.1029/2019wr025146 fatcat:rcyuev5vj5depgxgbsdmzs7tha

Monitoring sustainable development by means of earth observation data and machine learning: a review

Bruno Ferreira, Muriel Iten, Rui Silva
2021 Zenodo  
strongly suggesting the use of new Machine Learning techniques.  ...  A review on the Sustainable Development concept and its goals is presented followed by Earth Observation approaches relevant to this field, giving special attention to the contribution of Machine Learning  ...  • There is an increased need for new methods and techniques to process an ever-growing amount of Earth Observation data. • Machine Learning techniques are crucial in handling Earth Observation data given  ... 
doi:10.5281/zenodo.4436989 fatcat:pbzcgzdqcbh2ddrkfhl74kzoky

Global Sensitivity Analysis of Leaf-Canopy-Atmosphere RTMs: Implications for Biophysical Variables Retrieval from Top-of-Atmosphere Radiance Data

Jochem Verrelst, Jorge Vicent, Juan Pablo Rivera-Caicedo, Maria Lumbierres, Pablo Morcillo-Pallarés, José Moreno
2019 Remote Sensing  
a machine learning algorithm with low computation time.  ...  A Gaussian process regression (GPR) emulator was used to reproduce lookup tables of TOA radiance as a function of 12 input variables with relative errors of 2.4%.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs11161923 fatcat:qfwlp62nr5e43dd6fsvfyegdoi

Statistical Emulation of Winter Ambient Fine Particulate Matter Concentrations From Emission Changes in China

Luke Conibear, Carly L. Reddington, Ben J. Silver, Ying Chen, Christoph Knote, Stephen R. Arnold, Dominick V. Spracklen
2021 GeoHealth  
Machine learning models can emulate chemical transport models to provide computationally efficient predictions of outputs based on statistical associations with inputs.  ...  The emulators were optimized based on Gaussian process regressors with Matern kernels.  ...  Emulator Machine learning models can predict outputs based on statistical associations with inputs. We refer to the machine learning model developed here as the emulator.  ... 
doi:10.1029/2021gh000391 pmid:33977182 pmcid:PMC8095364 fatcat:xa6x74cvhbcuhdlgt56ftiuc3i

Adaptive hybrid architecture for enhancement of the complex hydroclimatic system and assessment of freshwater security

Venkatesh Budamala, Amit Baburao Mahindrakar
2021 Journal of Hydroinformatics  
Here, the framework compiles both physical and machine learning concepts with adaptive technology for the replication of real-world scenarios.  ...  The proposed study focused on the parallel computing of emulator modeling-based spatial optimization to enhance the HC systems with the perspective of future freshwater security in the Upper Chattahoochee  ...  In this study, Extreme Learning Machines (ELM) adopted as an emulator model to fit and enhance the hydrological response of SWAT.  ... 
doi:10.2166/hydro.2021.182 fatcat:6kabr7ohjnflhnqxkgxkh4gw7q

Assessing the representational accuracy of data-driven models: The case of the effect of urban green infrastructure on temperature

Marius Zumwald, Christoph Baumberger, David N. Bresch, Reto Knutti
2021 Environmental Modelling & Software  
Methods that aim at understanding the learned relationships of a supervised machine learning algorithm are called interpretable machine learning 1 (IML) (Murdoch et al., 2019) .  ...  In climate science, methods have recently been developed that can physically constrain the machine learning of evapotranspiration and achieve conservation of energy when using neural network emulators  ... 
doi:10.1016/j.envsoft.2021.105048 fatcat:yx7ppi47ljdmxepgrsezh5npju

Modelling transitions in sealed surface cover fraction with Quantitative State Cellular Automata

Frederik Priem, Frank Canters
2021 Landscape and Urban Planning  
Yet discrete land-use maps are not suitable for every application, particularly if the target is to model more continuous processes of urban change.  ...  We furthermore acknowledge that the machine learning methodology proposed here is just one of many possible setups.  ...  An independent random sample of 5000 cells was used to perform this accuracy assessment. FA = False Alarms, CR = Correct Refusals, FPR = False Positive Rate, TPR = True Positive Rate.  ... 
doi:10.1016/j.landurbplan.2021.104081 fatcat:mfsrzoczgjd6tlmsdm5zrxwt4u

Deep Learning Techniques for Geospatial Data Analysis [chapter]

Arvind W. Kiwelekar, Geetanjali S. Mahamunkar, Laxman D. Netak, Valmik B Nikam
2020 Learning and Analytics in Intelligent Systems  
Typically such applications are leveraged upon non-hierarchical machine learning techniques such as Naive-Bayes Classifiers, Support Vector Machines, and decision trees.  ...  The chapter presents a survey on the current state of the applications of deep learning techniques for analyzing geospatial data.  ...  Acknowledgement: The authors acknowledge the funding provided by Ministry of Human Resource Development (MHRD), Government of India, under the Pandit Madan Mohan National Mission on Teachers Training (  ... 
doi:10.1007/978-3-030-49724-8_3 fatcat:yv6stldjcjbclbfcx3d6i3s2um
« Previous Showing results 1 — 15 out of 6,427 results