Estimation of missing weather variables using different data mining techniques for avalanche forecasting

The availability of continuous weather data is essential in many applications such as the study of hydrology, glaciology, and modelling of extreme catastrophic events such as landslides, heavy precipitation, cloud burst and snow avalanches. Weather data are collected either manually or automatically, and due to variety of reasons, it becomes difficult to maintain continuous records of these data. In the present study, different data mining techniques like multivariate imputation by chained equations and nearest neighbour have been used to address the missing data problem for avalanche forecasting over the Himalayas. Six weather variables, maximum temperature, minimum temperature, wind speed, pressure, fresh snow and relative humidity used in all avalanche and weather forecasting models, have been made available from 1996 to 2019. Missing data are generated randomly to create 10, 15, 20 and 30% in order to study the algorithms. Scatter plots, root-mean-square error and coefficient of determination (R²) of the generated missing data have been computed. Case analysis of imputed major snow events is done from 2017 to 2019, demonstrating proficient imputation. The performance of artificial neural network-based avalanche forecasting models has been compared with and without data imputation. Results of the study are promising as HSS and accuracy for avalanche forecasting models accelerates to 0.36 from 0.31 and 0.74 from 0.71, respectively, for Station-1 and HSS to 0.3 from 0.24 and accuracy to 0.72 from 0.68 for Station-2 after missing data imputation.