scholarly journals Application of machine learning techniques for regional bias correction of snow water equivalent estimates in Ontario, Canada

2020 ◽  
Vol 24 (10) ◽  
pp. 4887-4902
Author(s):  
Fraser King ◽  
Andre R. Erler ◽  
Steven K. Frey ◽  
Christopher G. Fletcher
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Water Resource Management ◽  
Snow Water Equivalent ◽  
Bias Reduction ◽  
Machine Learning Techniques ◽  
Spatial Coverage ◽  
Snow Water ◽  
In Situ Observations

Abstract. Snow is a critical contributor to Ontario's water-energy budget, with impacts on water resource management and flood forecasting. Snow water equivalent (SWE) describes the amount of water stored in a snowpack and is important in deriving estimates of snowmelt. However, only a limited number of sparsely distributed snow survey sites (n=383) exist throughout Ontario. The SNOw Data Assimilation System (SNODAS) is a daily, 1 km gridded SWE product that provides uniform spatial coverage across this region; however, we show here that SWE estimates from SNODAS display a strong positive mean bias of 50 % (16 mm SWE) when compared to in situ observations from 2011 to 2018. This study evaluates multiple statistical techniques of varying complexity, including simple subtraction, linear regression and machine learning methods to bias-correct SNODAS SWE estimates using absolute mean bias and RMSE as evaluation criteria. Results show that the random forest (RF) algorithm is most effective at reducing bias in SNODAS SWE, with an absolute mean bias of 0.2 mm and RMSE of 3.64 mm when compared with in situ observations. Other methods, such as mean bias subtraction and linear regression, are somewhat effective at bias reduction; however, only the RF method captures the nonlinearity in the bias and its interannual variability. Applying the RF model to the full spatio-temporal domain shows that the SWE bias is largest before 2015, during the spring melt period, north of 44.5∘ N and east (downwind) of the Great Lakes. As an independent validation, we also compare estimated snowmelt volumes with observed hydrographs and demonstrate that uncorrected SNODAS SWE is associated with unrealistically large volumes at the time of the spring freshet, while bias-corrected SWE values are highly consistent with observed discharge volumes.

scholarly journals Application of machine learning techniques for regional bias correction of SWE estimates in Ontario, Canada

2020 ◽  
Author(s):  
Fraser King ◽  
Andre R. Erler ◽  
Steven K. Frey ◽  
Christopher G. Fletcher
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Water Resource Management ◽  
Snow Water Equivalent ◽  
Evaluation Criteria ◽  
Bias Reduction ◽  
Machine Learning Techniques ◽  
Spatial Coverage ◽  
In Situ Observations

Abstract. Snow is a critical contributor to Ontario's water-energy budget with impacts on water resource management and flood forecasting. Snow water equivalent (SWE) describes the amount of water stored in a snowpack and is important in deriving estimates of snowmelt. However, only a limited number of sparsely distributed snow survey sites (n = 383) exist throughout Ontario. The SNOw Data Assimilation System (SNODAS) is a daily, 1 km gridded SWE product that provides uniform spatial coverage across this region; however, we show here that SWE estimates from SNODAS display a strong positive mean bias of 50 % (16 mm SWE) when compared to in situ observations from 2011 to 2018. This study evaluates multiple statistical techniques of varying complexity, including simple subtraction, linear regression and machine learning methods to bias-correct SNODAS SWE estimates using absolute mean bias and RMSE as evaluation criteria. Results show that the random forest (RF) algorithm is most effective at reducing bias in SNODAS SWE, with an absolute mean bias of 0.2 mm and RMSE of 3.64 mm when compared with in situ observations. Other methods, such as mean bias subtraction and linear regression, are somewhat effective at bias reduction however, only the RF method captures the nonlinearity in the bias, and its interannual variability. Applying the RF model to the full spatio-temporal domain shows that the SWE bias is largest before 2015, during the spring melt period, north of 44.5° N and East (downwind) of the Great Lakes. As an independent validation, we also compare estimated snowmelt volumes with observed hydrographs, and demonstrate that uncorrected SNODAS SWE is associated with unrealistically large volumes at the time of the spring freshet, while bias-corrected SWE values are highly consistent with observed discharge volumes.

scholarly journals Snow water equivalent measurement in the Arctic based on cosmic ray neutron attenuation

2021 ◽  
Vol 15 (11) ◽  
pp. 5227-5239
Author(s):  
Anton Jitnikovitch ◽  
Philip Marsh ◽  
Branden Walker ◽  
Darin Desilets
Keyword(s):  
Water Resource Management ◽  
Snow Water Equivalent ◽  
Cosmic Ray ◽  
The Arctic ◽  
Sensing Applications ◽  
Neutron Attenuation ◽  
Snow Water ◽  
Remote Sites ◽  
Neutron Sensors

Abstract. Grounded in situ, or invasive, cosmic ray neutron sensors (CRNSs) may allow for continuous, unattended measurements of snow water equivalent (SWE) over complete winter seasons and allow for measurements that are representative of spatially variable Arctic snow covers, but few studies have tested these types of sensors or considered their applicability at remote sites in the Arctic. During the winters of 2016/2017 and 2017/2018 we tested a grounded in situ CRNS system at two locations in Canada: a cold, low- to high-SWE environment in the Canadian Arctic and at a warm, low-SWE landscape in southern Ontario that allowed easier access for validation purposes. Five CRNS units were applied in a transect to obtain continuous data for a single significant snow feature; CRNS-moderated neutron counts were compared to manual snow survey SWE values obtained during both winter seasons. The data indicate that grounded in situ CRNS instruments appear able to continuously measure SWE with sufficient accuracy utilizing both a linear regression and nonlinear formulation. These sensors can provide important SWE data for testing snow and hydrological models, water resource management applications, and the validation of remote sensing applications.

scholarly journals In situ snow water equivalent observations in the US Arctic

2012 ◽  
Vol 44 (1) ◽  
pp. 21-34 ◽  
Author(s):  
Svetlana Stuefer ◽  
Douglas L. Kane ◽  
Glen E. Liston
Keyword(s):  
Snow Water Equivalent ◽  
Winter Precipitation ◽  
Local Scale ◽  
Arctic Alaska ◽  
The Us ◽  
Snow Water ◽  
In Situ Observations ◽  
Best Fit ◽  
Collection Methods

This paper summarizes 12 years of snow water equivalent (SWE) observations collected in the data-sparse region of Arctic Alaska, United States. The in situ observations are distributed across a 200 × 300 km domain that includes the Kuparuk River watershed from the Brooks Range to the Beaufort Sea coast. Data collection methods and analyses were classified to distinguish between snow observation sites representing regional- and local-scale variability. Average SWE for the entire domain ranges from 92 mm in 2008 to 148 mm in 2011. Regional end-of-winter SWE indicates that both the extreme high SWE in 2009 and 2011 and the extreme low SWE in 2008 occurred during recent and alternating years, suggesting the limitations of 12 years of data for detecting SWE trends. By assimilating the observational datasets into SnowModel, hourly 100 m gridded SWE distributions for the central Alaska Arctic were created to provide a best-fit to the observations where and when they occur. The model simulations highlight how observed SWE data can be used as a surrogate for the more problematic winter precipitation measurements. The resulting SWE distributions are readily available to support ecological and hydrologic studies in this region.

scholarly journals Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan

2017 ◽  
Author(s):  
Edward H. Bair ◽  
Andre Abreu Calfa ◽  
Karl Rittger ◽  
Jeff Dozier
Keyword(s):  
Machine Learning ◽  
Snow Water Equivalent ◽  
Remotely Sensed ◽  
Machine Learning Techniques ◽  
Microwave Brightness Temperature ◽  
Time Estimates ◽  
Covered Area ◽  
Spatially Distributed ◽  
Snow Water ◽  
Feed Forward Neural Networks

Abstract. In many mountains, snowmelt provides most of the runoff. In Afghanistan, few ground-based measurements of the snow resource exist. Operational estimates use imagery from optical and passive microwave sensors, but with their limitations. An accurate approach reconstructs spatially distributed snow water equivalent (SWE) by calculating snowmelt backward from a remotely sensed date of disappearance, but reconstructed SWE estimates are available only retrospectively; they do not provide a forecast. To estimate SWE early in the snowmelt season, we consider physiographic and remotely-sensed information as predictors and reconstructed SWE as the target. The period of analysis matches the AMSR-E radiometer's lifetime from 2003 to 2011, for the months of April through June. The spatial resolution of the predictions is 3.125 km, to match the resolution of a microwave brightness temperature product. Two machine learning techniques – bagged regression trees and feed-forward neural networks – produced similar mean results, with 0–14 % bias and 46–48 mm RMSE on average. Daily SWE climatology and fractional snow-covered area are the most important predictors. We conclude that the methods can accurately estimate SWE during the snow season in remote mountains.

scholarly journals Using machine learning for real-time estimates of snow water equivalent in the watersheds of Afghanistan

2018 ◽  
Vol 12 (5) ◽  
pp. 1579-1594 ◽  
Author(s):  
Edward H. Bair ◽  
Andre Abreu Calfa ◽  
Karl Rittger ◽  
Jeff Dozier
Keyword(s):  
Machine Learning ◽  
Sierra Nevada ◽  
Snow Water Equivalent ◽  
Remotely Sensed ◽  
Machine Learning Techniques ◽  
Microwave Brightness Temperature ◽  
Time Estimates ◽  
Covered Area ◽  
Spatially Distributed ◽  
Snow Water

Abstract. In the mountains, snowmelt often provides most of the runoff. Operational estimates use imagery from optical and passive microwave sensors, but each has its limitations. An accurate approach, which we validate in Afghanistan and the Sierra Nevada USA, reconstructs spatially distributed snow water equivalent (SWE) by calculating snowmelt backward from a remotely sensed date of disappearance. However, reconstructed SWE estimates are available only retrospectively; they do not provide a forecast. To estimate SWE throughout the snowmelt season, we consider physiographic and remotely sensed information as predictors and reconstructed SWE as the target. The period of analysis matches the AMSR-E radiometer's lifetime from 2003 to 2011, for the months of April through June. The spatial resolution of the predictions is 3.125 km, to match the resolution of a microwave brightness temperature product. Two machine learning techniques – bagged regression trees and feed-forward neural networks – produced similar mean results, with 0–14 % bias and 46–48 mm RMSE on average. Nash–Sutcliffe efficiencies averaged 0.68 for all years. Daily SWE climatology and fractional snow-covered area are the most important predictors. We conclude that these methods can accurately estimate SWE during the snow season in remote mountains, and thereby provide an independent estimate to forecast runoff and validate other methods to assess the snow resource.

scholarly journals Snow Depth Fusion Based on Machine Learning Methods for the Northern Hemisphere

2021 ◽  
Vol 13 (7) ◽  
pp. 1250
Author(s):  
Yanxing Hu ◽  
Tao Che ◽  
Liyun Dai ◽  
Lin Xiao
Keyword(s):  
Machine Learning ◽  
Northern Hemisphere ◽  
Snow Depth ◽  
Learning Algorithm ◽  
Random Forest Regression ◽  
Machine Learning Methods ◽  
Long Time ◽  
In Situ Observations ◽  
Input Variables

In this study, a machine learning algorithm was introduced to fuse gridded snow depth datasets. The input variables of the machine learning method included geolocation (latitude and longitude), topographic data (elevation), gridded snow depth datasets and in situ observations. A total of 29,565 in situ observations were used to train and optimize the machine learning algorithm. A total of five gridded snow depth datasets—Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) snow depth, Global Snow Monitoring for Climate Research (GlobSnow) snow depth, Long time series of daily snow depth over the Northern Hemisphere (NHSD) snow depth, ERA-Interim snow depth and Modern-Era Retrospective Analysis for Research and Applications, version 2 (MERRA-2) snow depth—were used as input variables. The first three snow depth datasets are retrieved from passive microwave brightness temperature or assimilation with in situ observations, while the last two are snow depth datasets obtained from meteorological reanalysis data with a land surface model and data assimilation system. Then, three machine learning methods, i.e., Artificial Neural Networks (ANN), Support Vector Regression (SVR), and Random Forest Regression (RFR), were used to produce a fused snow depth dataset from 2002 to 2004. The RFR model performed best and was thus used to produce a new snow depth product from the fusion of the five snow depth datasets and auxiliary data over the Northern Hemisphere from 2002 to 2011. The fused snow-depth product was verified at five well-known snow observation sites. The R2 of Sodankylä, Old Aspen, and Reynolds Mountains East were 0.88, 0.69, and 0.63, respectively. At the Swamp Angel Study Plot and Weissfluhjoch observation sites, which have an average snow depth exceeding 200 cm, the fused snow depth did not perform well. The spatial patterns of the average snow depth were analyzed seasonally, and the average snow depths of autumn, winter, and spring were 5.7, 25.8, and 21.5 cm, respectively. In the future, random forest regression will be used to produce a long time series of a fused snow depth dataset over the Northern Hemisphere or other specific regions.

scholarly journals Evaluating Machine Learning and Geostatistical Methods for Spatial Gap-filling of Monthly ESA CCI Soil Moisture in China

2021 ◽  
Vol 13 (14) ◽  
pp. 2848
Author(s):  
Hao Sun ◽  
Qian Xu
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Water Resource Management ◽  
Large Scale ◽  
Gap Filling ◽  
Spatial Continuity ◽  
Study Results ◽  
Data Gaps

Obtaining large-scale, long-term, and spatial continuous soil moisture (SM) data is crucial for climate change, hydrology, and water resource management, etc. ESA CCI SM is such a large-scale and long-term SM (longer than 40 years until now). However, there exist data gaps, especially for the area of China, due to the limitations in remote sensing of SM such as complex topography, human-induced radio frequency interference (RFI), and vegetation disturbances, etc. The data gaps make the CCI SM data cannot achieve spatial continuity, which entails the study of gap-filling methods. In order to develop suitable methods to fill the gaps of CCI SM in the whole area of China, we compared typical Machine Learning (ML) methods, including Random Forest method (RF), Feedforward Neural Network method (FNN), and Generalized Linear Model (GLM) with a geostatistical method, i.e., Ordinary Kriging (OK) in this study. More than 30 years of passive–active combined CCI SM from 1982 to 2018 and other biophysical variables such as Normalized Difference Vegetation Index (NDVI), precipitation, air temperature, Digital Elevation Model (DEM), soil type, and in situ SM from International Soil Moisture Network (ISMN) were utilized in this study. Results indicated that: 1) the data gap of CCI SM is frequent in China, which is found not only in cold seasons and areas but also in warm seasons and areas. The ratio of gap pixel numbers to the whole pixel numbers can be greater than 80%, and its average is around 40%. 2) ML methods can fill the gaps of CCI SM all up. Among the ML methods, RF had the best performance in fitting the relationship between CCI SM and biophysical variables. 3) Over simulated gap areas, RF had a comparable performance with OK, and they outperformed the FNN and GLM methods greatly. 4) Over in situ SM networks, RF achieved better performance than the OK method. 5) We also explored various strategies for gap-filling CCI SM. Results demonstrated that the strategy of constructing a monthly model with one RF for simulating monthly average SM and another RF for simulating monthly SM disturbance achieved the best performance. Such strategy combining with the ML method such as the RF is suggested in this study for filling the gaps of CCI SM in China.

Sign in / Sign up

Export Citation Format

Share Document