An Automated Snow Mapper Powered by Machine Learning

Snow preserves fresh water and impacts regional climate and the environment. Enabled by modern satellite Earth observations, fast and accurate automated snow mapping is now possible. In this study, we developed the Automated Snow Mapper Powered by Machine Learning (AutoSMILE), which is the first machine learning-based open-source system for snow mapping. It is built in a Python environment based on object-based analysis. AutoSMILE was first applied in a mountainous area of 1002 km2 in Bome County, eastern Tibetan Plateau. A multispectral image from Sentinel-2B, a digital elevation model, and machine learning algorithms such as random forest and convolutional neural network, were utilized. Taking only 5% of the study area as the training zone, AutoSMILE yielded an extraordinarily satisfactory result over the rest of the study area: the producer’s accuracy, user’s accuracy, intersection over union and overall accuracy reached 99.42%, 98.78%, 98.21% and 98.76%, respectively, at object level, corresponding to 98.84%, 98.35%, 97.23% and 98.07%, respectively, at pixel level. The model trained in Bome County was subsequently used to map snow at the Qimantag Mountain region in the northern Tibetan Plateau, and a high overall accuracy of 97.22% was achieved. AutoSMILE outperformed threshold-based methods at both sites and exhibited superior performance especially in handling complex land covers. The outstanding performance and robustness of AutoSMILE in the case studies suggest that AutoSMILE is a fast and reliable tool for large-scale high-accuracy snow mapping and monitoring.

[1]  Fan Zhang,et al.  Ground-based evaluation of MODIS snow cover product V6 across China: Implications for the selection of NDSI threshold. , 2019, The Science of the total environment.

[2]  W. Bloh,et al.  Importance of snow and glacier meltwater for agriculture on the Indo-Gangetic Plain , 2019, Nature Sustainability.

[3]  Hanqiu Xu.  Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery , 2006 .

[4]  Ahmad Kalhor,et al.  A data-driven fuzzy model for prediction of rockburst , 2020 .

[5]  D. Hall,et al.  Accuracy assessment of the MODIS snow products , 2007 .

[6]  Natascha Oppelt,et al.  Wet and Dry Snow Detection Using Sentinel-1 SAR Data for Mountainous Areas with a Machine Learning Technique , 2019, Remote. Sens..

[7]  Xiaoyan Zhang,et al.  An Automated Method for Surface Ice/Snow Mapping Based on Objects and Pixels from Landsat Imagery in a Mountainous Region , 2020, Remote. Sens..

[8]  Lei Wang,et al.  Object-Based Convolutional Neural Networks for Cloud and Snow Detection in High-Resolution Multispectral Imagers , 2018, Water.

[9]  Changyu Liu,et al.  MODIS Fractional Snow Cover Mapping Using Machine Learning Technology in a Mountainous Area , 2020, Remote. Sens..

[10]  Jean-Pierre Dedieu,et al.  On the Importance of High-Resolution Time Series of Optical Imagery for Quantifying the Effects of Snow Cover Duration on Alpine Plant Habitat , 2016, Remote. Sens..

[11]  S. F. F. Mojtahedi,et al.  Optimisation of deep mixing technique by artificial neural network based on laboratory and field experiments , 2020, Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards.

[12]  Lan-hai Li,et al.  Snow cover estimation from MODIS and Sentinel-1 SAR data using machine learning algorithms in the western part of the Tianshan Mountains , 2020, Journal of Mountain Science.

[13]  K. Schulz,et al.  On the need for a time- and location-dependent estimation of the NDSI threshold value for reducing existing uncertainties in snow cover maps at different scales , 2017 .

[14]  Haojie Wang,et al.  Landslide identification using machine learning , 2021, Geoscience Frontiers.

[15]  Jian He,et al.  AI-powered landslide susceptibility assessment in Hong Kong , 2021, Engineering Geology.

[16]  André Stumpf,et al.  Object-oriented mapping of landslides using Random Forests , 2011 .

[17]  P. Mercogliano,et al.  The Snow Load in Europe and the Climate Change , 2018 .

[18]  Jiewen Fu,et al.  Uncertainties of snow cover extraction caused by the nature of topography and underlying surface , 2015, Journal of Arid Land.

[19]  Te Xiao,et al.  A novel physically-based model for updating landslide susceptibility , 2019, Engineering Geology.

[20]  Bicheron Patrice,et al.  The Most Detailed Portrait of Earth , 2008 .

[21]  Omid Ghorbanzadeh,et al.  Spatial Modeling of Snow Avalanche Using Machine Learning Models and Geo-Environmental Factors: Comparison of Effectiveness in Two Mountain Regions , 2019, Remote. Sens..

[22]  I. Moore,et al.  Digital terrain modelling: A review of hydrological, geomorphological, and biological applications , 1991 .

[23]  Thomas Oommen,et al.  A comparative analysis of pixel- and object-based detection of landslides from very high-resolution images , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[24]  N. Cristea,et al.  High-resolution CubeSat imagery and machine learning for detailed snow-covered area , 2021 .

[25]  Thomas Blaschke,et al.  Evaluation of Different Machine Learning Methods and Deep-Learning Convolutional Neural Networks for Landslide Detection , 2019, Remote. Sens..

[26]  Olivier Hagolle,et al.  Theia Snow collection: high-resolution operational snow cover maps from Sentinel-2 and Landsat-8 data , 2019, Earth System Science Data.