Forewarning model of Glacial Lake Outburst Disaster in Southeast Tibet

The southeast region of Tibet was a frequent area of glacial lake outburst disasters, and disaster warning was an important means of disaster prevention and reduction. Based on remote sensing images and historical data, 21 Glacial Lakes in southeast Tibet were selected as samples for risk analysis. The probability model of glacial Lake Outburst in southeast Tibet is established by using the method of logistic regression for 8 selected prediction indexes. By calculating the sensitivity and specificity of the model, the probability of identifying the galcial Lake outburst event is 60% , and the identification degree of the galcial lake outburst is 86% . The AUC index area is obviously larger than 0.5, which indicates that logistic regression prediction plays a certain role in southeast Tibet. The probability equation of the model shows that the area of the Glacial Lake, the distance of the Glacial Lake from the glacier, the slope of the glacier, the slope of the glacier tongue and the slope of the water behind the dam are in direct proportion to the probability of the Glacial Lake Bursting, the more likely it is that the glacical lake will outburst, which is consistent with the observed facts.