Search

What role does traditional ecological knowledge play in the lives of smallholder farmers in post-conflict communities as they cope with the destructive impacts of war? In many cases, military weapons, such as unexploded bombs, are left behind in the surrounding landscape, forcing farmers to adapt their livelihood practices to the increased risk of death and injury. We analyze trends in the local production of knowledge in Ratanak Kiri province, Cambodia, an area heavily bombarded by the US Air Force during the Vietnam War. We argue that the system of traditional ecological knowledge has adapted to include basic information on bomb identification, location, and management strategies. This factual approach gives individuals the flexibility to generate their own views on whether they perceive unexploded ordnance as a violent hazard and/or an economic commodity. In a relatively short 50-year time period, the body of knowledge has been quickly accumulated and culturally transmitted to family and neighbors. Our findings suggest that traditional ecological knowledge should not be reduced to a static and ancient form of collective memory. We call for the expansion of the concept of traditional ecological knowledge to include short-term and dynamic processes of knowledge generation. [ABSTRACT FROM AUTHOR]

Unexploded ordnance (UXO) pose a significant threat to post-conflict communities, and current efforts to locate bombs rely on time-intensive and dangerous in-person enumeration. Very high resolution (VHR) sub-meter satellite images may offer a low-cost and high-efficiency approach to automatically detect craters and estimate UXO density. Machine-learning methods from the meteor crater literature are ill-suited to find bomb craters, which are smaller than meteor craters and have high appearance variation, particularly in spectral reflectance and shape, due to the complex terrain environment. A two-stage learning-based framework is created to address these challenges. First, a simple and loose statistical classifier based on histogram of oriented gradient (HOG) and spectral information is used for a first pass of crater recognition. In a second stage, a patch-dependent novel spatial feature is developed through dynamic mean-shift segmentation and SIFT descriptors. We apply the model to a multispectral WorldView-2 image of a Cambodian village, which was heavily bombed during the Vietnam War. The proposed method increased true bomb crater detection by over 160 percent. Comparative analysis demonstrates that our method significantly outperforms typical object-recognition algorithms and can be used for wide-area bomb crater detection. Our model, combined with declassified records and demining reports, suggests that 44 to 50 percent of the bombs in the vicinity of this particular Cambodian village may remain unexploded., Competing Interests: The authors have declared that no competing interests exist.