Landmine probability maps

Estimating the Probability of Landmine Contamination. LTC Stephen R. Riese, Donald E. Brown and Yacov Y. Haimes. Military Operations Research 11:3, 2006. This paper creates landmine probability maps almost precisely in the way that I have wanted to create lost person behavior probability maps. (I'll add some more notes on it later. NOTE: now shows the image. Text slightly revised to suit.)

Abstract

This paper introduces a new approach to forecasting landmine contamination in war-torn areas. The Probability of Mine (PoM) forecast incorporates information not used in traditional predictive pattern analysis, and provides more accurate estimates to support decision-making in the allocation of scarce demining resources, relocation of refugees, or planning of peacekeeping operations. That new information is spatial feature data that helps drive human behavior, in this case the choice of where to place landmines. Data gathered by the U.S. Army in Bosnia in 1995 and 1996 provides real world data to test and evaluate the model. The PoM forecast is built upon an empirical Bayesian prediction model that uses examples of areas known to be mined, examples of areas known to be free of mines, feature data (e.g., location of roads, vegetation, fighting lines), and an initial estimate of the overall mine density within the region. Results demonstrate that the PoM model is able to make accurate probabilistic forecasts on the presence of landmines, as well as provide measures of forecast quality that address both the model’s ability to account for uncertainty and the model’s predictive power.