Accession Number : AD1048366


Title :   Machine-Learning Techniques for the Determination of Attrition of Forces Due to Atmospheric Conditions


Descriptive Note : Technical Report,01 Oct 2015,30 Sep 2017


Corporate Author : US Army Research Laboratory White Sands Missile Range United States


Personal Author(s) : Raby,Yasmina R


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/1048366.pdf


Report Date : 01 Feb 2018


Pagination or Media Count : 38


Abstract : This report documents the findings of an attempt to model the attrition of forces due to atmospheric conditions. Machine-learning techniques, primarily the random forest algorithm, were used to explore the possibility of a correlation between aircraft incidents in the National Transportation Safety Board database and meteorological conditions. If a strong correlation could be found, it could be used to derive a model to predict aircraft incidents and become part of a decision support tool for mission planning purposes. While the random forest algorithm was able to discover some consistent predictors across a variety of data sets while classifying aircraft incidents related to weather, there were some concerns regarding the error rate in the final result of the classification process. This report documents the efforts to define a model and provide lessons learned toward future attempts to refine the results and generate a model that addresses the attrition of forces due to atmospheric conditions using machine-learning techniques.


Descriptors :   algorithms , machine learning , attrition , aviation accidents , databases , METEOROLOGICAL DATA , predictions , DECISION SUPPORT SYSTEMS , lessons learned


Subject Categories : Military Aircraft Operations
      Meteorology


Distribution Statement : APPROVED FOR PUBLIC RELEASE