Bio-logging technologies allow scientists to remotely monitor animal behaviourand the environment. In this study, we used the combination of natural abilitiesof African white-backed vultures Gyps africanus and state-of-the-art bio-loggingtechnology for detecting and locating carcasses in a vast landscape. We used data from two captive and 27 wild vultures to create a reference data setfor the training of a support vector machine to distinguish between six behaviourclasses based on acceleration data. Next, we combined the classified behaviour ofthe initial 27 and 7 additional vultures with GPS data and used the 'Density-BasedSpatial Clustering of Applications with Noise' algorithm to cluster all GPS data toget a position of potential feeding locations. Finally, we used the clustered dataset to train a Random Forest algorithm to distinguish between clusters with andwithout a carcass.3. The behaviour classifier was trained on 14,682 samples for all behaviour classes,which were classified with a high performance (overall precision: 0.95, recall:0.89). This enabled a ground team to examine 1900 clusters between May 2022and March 2023 in the field, 580 linked to a carcass and 1320 without a carcass.The cluster classifier trained on this data set was able to correctly distinguish be-tween carcass and no carcass clusters with high performance (overall precision:0.92, recall: 0.89).4. Synthesis and applications. We showed that a carcass detection system using vultures, loggers and artificial intelligence (AI) can be used to monitor the mortalityof numerous species in a vast landscape. This method has broad applications,such as studying the feeding ecology of vultures, detecting and monitoring ofdisease outbreaks, environmental poisoning or illegal killing of wildlife. Similar tovultures and carcasses, our methodological framework can be applied to otherspecies to locate their respective food resources. It could also be applied to othertypes of resources like temporary water sources, roosting sites and to other be-haviours such as marking to locate marking sites. Keywords: Saccelerometry, behaviour classification, carcass detection, feeding sites, gyps africanus,machine learning, random forest, support vector machine.