Browse Articles

The authors looked at how soil temperature changes with fire to develop a sensor system that could aid in earlier detection of fires.

The authors looked at beach nourishment (a way to combat erosion on coasts) and resulting grain size distribution. Their work is important to understand the dynamics of erosion and it's relation to wave action and the implications this has for efforts to mitigate coastal erosion.

One-third of the world's people do not have access to clean drinking water. Nadella and Nadella tackle this issue by testing a low-cost filtration system for removing heavy metal and bacteria from water.

The authors looked at renewable energy generators and the ability to utilize green roofs as a solution to climate change.

Using machine learning to predict the risk of algae bloom

The authors test the effect of caffeine on the behavior of the Siamese fighting fish Betta splendens.

In this study, the authors engineer a cost-effective and bio-friendly water purification system using limestone, denitrifying bacteria, and sulfate-reducing bacteria. They evaluated its efficacy with samples from Eastern PA industrial sites.

In this study, the authors test whether excess copper exposure has neurobehavioral effects on Hirudo verbana leeches.

The energy conservation in a system of objects in collision depends on the elasticity of the objects and environmental factors such as air resistance. One system that relies heavily on elasticity is the Newton’s Cradle. We aimed to determine the extent to which these adhesives serve to mitigate or worsen the chaotic movements and elastic collisions.

The mountain chain of the Western Ghats on the Indian peninsula, a UNESCO World Heritage site, is home to about 200 frog species, 89 of which are endemic. Distinctive to each frog species, their vocalizations can be used for species recognition. Manually surveying frogs at night during the rain in elephant and big cat forests is difficult, so being able to autonomously record ambient soundscapes and identify species is essential. An effective machine learning (ML) species classifier requires substantial training data from this area. The goal of this study was to assess data augmentation techniques on a dataset of frog vocalizations from this region, which has a minimal number of audio recordings per species. Consequently, enhancing an ML model’s performance with limited data is necessary. We analyzed the effects of four data augmentation techniques (Time Shifting, Noise Injection, Spectral Augmentation, and Test-Time Augmentation) individually and their combined effect on the frog vocalization data and the public environmental sounds dataset (ESC-50). The effect of combined data augmentation techniques improved the model's relative accuracy as the size of the dataset decreased. The combination of all four techniques improved the ML model’s classification accuracy on the frog calls dataset by 94%. This study established a data augmentation approach to maximize the classification accuracy with sparse data of frog call recordings, thereby creating a possibility to build a real-world automated field frog species identifier system. Such a system can significantly help in the conservation of frog species in this vital biodiversity hotspot.