Using machine learning to produce a very high resolution land-cover map for Ireland

Abstract. Land-cover classifications in the form of maps are required for numerical modelling of weather and climate. Such maps are often of coarse resolution and are infrequently updated. Here we propose a novel approach for land-cover classification using a Convolutional Neural Network machine learning algorithm to segment satellite images into various land-cover classes. Sentinel-2 satellite imagery, the CORINE land-cover database and the BigEarthNet dataset are used. A 10 m resolution map, called the Ulmas-Walsh map, has been created for Ireland that outperforms ECO-SG in terms of accuracy, as well as demonstrating a capacity for identifying features not labelled correctly in CORINE. The map can be updated on demand for any time of the year, subject to cloud cover. This is particularly useful for regions with large seasonal variation in land classifications such as Turloughs – seasonal lakes, flood plains and rotational crops.

[1]  D. Chalikov,et al.  New Approach to Calculation of Atmospheric Model Physics: Accurate and Fast Neural Network Emulation of Longwave Radiation in a Climate Model , 2005 .

[2]  Limin Yang,et al.  Development of a global land cover characteristics database and IGBP DISCover from 1 km AVHRR data , 2000 .

[3]  Begüm Demir,et al.  Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding , 2019, IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium.

[4]  R. Lacaze,et al.  A Global Database of Land Surface Parameters at 1-km Resolution in Meteorological and Climate Models , 2003 .

[5]  Vladimir M. Krasnopolsky,et al.  A Neural Network Nonlinear Multimodel Ensemble to Improve Precipitation Forecasts over Continental US , 2012 .

[6]  Innar Liiv,et al.  Segmentation of Satellite Imagery using U-Net Models for Land Cover Classification , 2020, ArXiv.

[7]  X. X. Zhu,et al.  A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks , 2020, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[8]  Jeremy Howard,et al.  fastai: A Layered API for Deep Learning , 2020, Inf..

[9]  P. Earnshaw,et al.  The Met Office Unified Model Global Atmosphere 7.0/7.1 and JULES Global Land 7.0 configurations , 2011, Geoscientific Model Development.

[10]  Yong Wang,et al.  The ALADIN System and its canonical model configurations AROME CY41T1 and ALARO CY40T1 , 2017 .

[11]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[12]  Jean-Louis Roujean,et al.  ECOCLIMAP-II/Europe: a twofold database of ecosystems and surface parameters at 1 km resolution based on satellite information for use in land surface, meteorological and climate models , 2012 .

[13]  S. E. Haupt,et al.  Using Artificial Intelligence to Improve Real-Time Decision-Making for High-Impact Weather , 2017 .

[14]  Marvin N. Wright,et al.  SoilGrids250m: Global gridded soil information based on machine learning , 2017, PloS one.

[15]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[16]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  A. Overeem,et al.  Quality Control for Crowdsourced Personal Weather Stations to Enable Operational Rainfall Monitoring , 2019, Geophysical Research Letters.

[18]  Driss Bari,et al.  Machine-learning regression applied to diagnose horizontal visibility from mesoscale NWP model forecasts , 2020, SN Applied Sciences.

[19]  C. Ballabio,et al.  Mapping topsoil physical properties at European scale using the LUCAS database , 2016 .

[20]  Vladimir M. Krasnopolsky,et al.  Using Ensemble of Neural Networks to Learn Stochastic Convection Parameterizations for Climate and Numerical Weather Prediction Models from Data Simulated by a Cloud Resolving Model , 2013, Adv. Artif. Neural Syst..

[21]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[22]  A. Belward,et al.  GLC2000: a new approach to global land cover mapping from Earth observation data , 2005 .

[23]  Nicola Jones,et al.  How machine learning could help to improve climate forecasts , 2017, Nature.

[24]  John Connolly,et al.  Mapping land use on Irish peatlands using medium resolution satellite imagery , 2019 .

[25]  Brian W. Barrett,et al.  Temporal optimisation of image acquisition for land cover classification with Random Forest and MODIS time-series , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[26]  Lisa Bengtsson,et al.  The HARMONIE-AROME Model Configuration in the ALADIN-HIRLAM NWP System , 2017 .

[27]  A. Baccini,et al.  Mapping forest canopy height globally with spaceborne lidar , 2011 .

[28]  Fred Meier,et al.  Development and Application of a Statistically-Based Quality Control for Crowdsourced Air Temperature Data , 2018, Front. Earth Sci..

[29]  Stephan Rasp,et al.  Neural networks for post-processing ensemble weather forecasts , 2018, Monthly Weather Review.

[30]  Kristin M. Calhoun,et al.  Evaluation of a Probabilistic Forecasting Methodology for Severe Convective Weather in the 2014 Hazardous Weather Testbed , 2015 .

[31]  Line Båserud,et al.  TITAN automatic spatial quality control of meteorological in-situ observations , 2020 .

[32]  V. Masson,et al.  The AROME-France Convective-Scale Operational Model , 2011 .

[33]  Peter Bauer,et al.  Challenges and design choices for global weather and climate models based on machine learning , 2018, Geoscientific Model Development.

[34]  E. Ruprecht,et al.  Determination of cloud liquid water path over the oceans from Special Sensor Microwave/Imager (SSM/I) data using neural networks , 1998 .

[35]  A. Belward,et al.  GLC 2000 : a new approach to global land cover mapping from Earth observation data , 2005 .

[36]  Vladimir M. Krasnopolsky,et al.  A neural network technique to improve computational efficiency of numerical oceanic models , 2002 .

[37]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[38]  Jessica Lowell.  Neural Network , 2001 .

[39]  Hanyue Chen,et al.  High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data , 2020, Int. J. Appl. Earth Obs. Geoinformation.

[40]  Vladimir M. Krasnopolsky,et al.  Neural network approximations for nonlinear interactions in wind wave spectra: direct mapping for wind seas in deep water , 2005 .

[41]  Torsten Hoefler,et al.  Deep learning for post-processing ensemble weather forecasts , 2021, Philosophical Transactions of the Royal Society A.

[42]  Frédéric Chevallier,et al.  Use of a neural‐network‐based long‐wave radiative‐transfer scheme in the ECMWF atmospheric model , 2000 .

[43]  Lin Lin,et al.  Improving surface roughness lengths estimation using machine learning algorithms , 2020, Agricultural and Forest Meteorology.

[44]  David B. Lobell,et al.  Weakly Supervised Deep Learning for Segmentation of Remote Sensing Imagery , 2020, Remote. Sens..

[45]  B. Barrett,et al.  TaLAM: Mapping Land Cover in Lowlands and Uplands with Satellite Imagery , 2018 .