Science has a critical role to play in guiding more sustainable development trajectories. Here, we present the Sustainable Amazon Network ( Rede Amazônia Sustentável , RAS): a multidisciplinary research initiative involving more than 30 partner organizations working to assess both social and ecological dimensions of land-use sustainability in eastern Brazilian Amazonia. The research approach adopted by RAS offers three advantages for addressing land-use sustainability problems: (i) the collection of synchronized and co-located ecological and socioeconomic data across broad gradients of past and present human use; (ii) a nested sampling design to aid comparison of ecological and socioeconomic conditions associated with different land uses across local, landscape and regional scales; and (iii) a strong engagement with a wide variety of actors and non-research institutions. Here, we elaborate on these key features, and identify the ways in which RAS can help in highlighting those problems in most urgent need of attention, and in guiding improvements in land-use sustainability in Amazonia and elsewhere in the tropics. We also discuss some of the practical lessons, limitations and realities faced during the development of the RAS initiative so far.

Selective logging is the most widespread driver of tropical forest disturbance. As such, it is critically important to identify at which spatial scale logging intensity should be measured and whether there are clear thresholds in the relationship between logging intensity and its impacts on biodiversity or ecological processes. We address this using a robust beforeand-after logging experimental design in the Brazilian Amazon, using a gradient of logging intensity measured at two different spatial scales. We assessed the impacts of selective logging using dung beetle communities and their ecological functions of dung removal and soil bioturbation. Our findings provide novel empirical evidence that biological consequences from Reduced Impact Logging (RIL) depend strongly on the scale at which logging intensity is measured: dung beetle local species richness and composition were strongly associated with logging intensity measured at a 10ha scale, while dung beetle-mediated soil bioturbation was more strongly associated with logging intensity measured across 90ha. Contrary to expectations, we found concave-shaped relationships between logging intensity and biodiversity and ecosystem functioning, demonstrating that sensitive dung beetle species and important processes may be lost following even low intensity anthropogenic forest disturbances. Taken together, these results suggest that production forests in the tropics need to reconsider the scale at which logging intensity is regulated, and put in place measures that further incentivise land sparing to enhance biodiversity conservation.

Passive acoustics provides a powerful tool for monitoring the endangered North Atlantic right whale (Eubalaena glacialis), but robust detection algorithms are needed to handle diverse and variable acoustic conditions and differences in recording techniques and equipment. Here, we investigate the potential of deep neural networks for addressing this need. ResNet, an architecture commonly used for image recognition, is trained to recognize the time-frequency representation of the characteristic North Atlantic right whale upcall. The network is trained on several thousand examples recorded at various locations in the Gulf of St. Lawrence in 2018 and 2019, using different equipment and deployment techniques. Used as a detection algorithm on fifty 30-minute recordings from the years 2015-2017 containing over one thousand upcalls, the network achieves recalls up to 80%, while maintaining a precision of 90%. Importantly, the performance of the network improves as more variance is introduced into the training dataset, whereas the opposite trend is observed using a conventional linear discriminant analysis approach. Our work demonstrates that deep neural networks can be trained to identify North Atlantic right whale upcalls under diverse and variable conditions with a performance that compares favorably to that of existing algorithms.

No abstract

In this paper, we adapt Recurrent Neural Networks with Stochastic Layers, which are the state-of-the-art for generating text, music and speech, to the problem of acoustic novelty detection. By integrating uncertainty into the hidden states, this type of network is able to learn the distribution of complex sequences. Because the learned distribution can be calculated explicitly in terms of probability, we can evaluate how likely an observation is then detect low-probability events as novel. The model is robust, highly unsupervised, end-toend and requires minimum preprocessing, feature engineering or hyperparameter tuning. An experiment on a benchmark dataset shows that our model outperforms the state-of-the-art acoustic novelty detectors.Index Termsacoustic modeling, novelty detection, variational recurrent neural network, stochastic recurrent neural network.