Search for: All records

Ecologists interested in monitoring the effects caused by climate change are increasingly turning to passive acoustic monitoring, the practice of placing autonomous audio recording units in ecosystems to monitor species richness and occupancy via species calls. However, identifying species calls in large datasets by hand is an expensive task, leading to a reliance on machine learning models. Due to a lack of annotated datasets of soundscape recordings, these models are often trained on large databases of community created focal recordings. A challenge of training on such data is that clips are given a "weak label," a single label that represents the whole clip. This includes segments that only have background noise but are labeled as calls in the training data, reducing model performance. Heuristic methods exist to convert clip-level labels to "strong" call-specific labels, where the label tightly bounds the temporal length of the call and better identifies bird vocalizations. Our work improves on the current weakly to strongly labeled method used on the training data for BirdNET, the current most popular model for audio species classification. We utilize an existing RNN-CNN hybrid, resulting in a precision improvement of 12% (going to 90% precision) against our new strongly hand-labeled dataset of Peruvian bird species.Jacob Ayers (Engineers for Exploration at UCSD); Sean Perry (University of California San Diego); Samantha Prestrelski (UC San Diego); Tianqi Zhang (Engineers for Exploration); Ludwig von Schoenfeldt (University of California San Diego); Mugen Blue (UC Merced); Gabriel Steinberg (Demining Research Community); Mathias Tobler (San Diego Zoo Wildlife Alliance); Ian Ingram (San Diego Zoo Wildlife Alliance); Curt Schurgers (UC San Diego); Ryan Kastner (University of California San Diego) 

Humanitarian mine action (HMA) is a critically under-researched field when compared to other hazards fields of similar societal impact. A potential solution to this problem is early exposure to and engagement in the HMA field in undergraduate education. Early undergraduate education emphasizing technical and social aspects of HMA can help protect lives by building a robust pipeline of passionate researchers who will find new solutions to the global explosive ordnance (EO) crisis. Early engagement of the next generation of HMA researchers and policy makers can occur through various classroom experiences, undergraduate research projects, and public outreach events. These include but are not limited to course-based undergraduate research experiences (CUREs); presenting research results at local, national, and international conferences; dissemination in edited and peer-reviewed publications; local community events; and through social media outreach. Early engagement, active guidance, and mentorship of such students by mid-career and experienced HMA scholars and practitioners could dramatically reduce the learning curve associated with entry into the HMA sector and allow for more fruitful long-term collaboration between academic institutions, private industry, and leading nongovernmental organizations (NGOs) operating across different facets of HMA.