An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

This research proposed an improved transfer-learning bird classification framework to achieve a more precise classification of Protected Indonesia Birds(PIB)which have been identified as the endangered bird species.The framework takes advantage of using the proposed sequence of Batch Normalization Dropout Fully-Connected(BNDFC)layers to enhance the baseline model of transfer learning.The main contribution of this work is the proposed sequence of BNDFC that can be applied to any Convolutional Neural Network(CNN)based model to improve the classification accuracy,especially for image-based species classification problems.The experiment results show that the proposed sequence of BNDFC layers outperform other combination of BNDFC.The addition of BNDFC can improve the model’s performance across ten different CNN-based models.On average,BNDFC can improve by approximately 19.88%in Accuracy,24.43%in F-measure,17.93%in G-mean,23.41%in Sensitivity,and 18.76%in Precision.Moreover,applying fine-tuning(FT)is able to enhance the accuracy by 0.85%with a smaller validation loss of 18.33%improvement.In addition,MobileNetV2 was observed to be the best baseline model with the lightest size of 35.9 MB and the highest accuracy of 88.07%in the validation set.

Projected impacts of climate change on protected birds and nature reserves in China

Knowledge about climate change impacts on species distribution at national scale is critical to biodi- versity conservation and design of management programs. Although China is a biodiversity hot spot in the world, potential influence of climate change on Chinese protected birds is rarely studied. Here, we assess the impact of climate change on 108 protected bird species and nature reserves using species distribution modeling at a relatively fine spatial resolution （1 km） for the first time. We found that a large proportion of protected species would have potential suitable habitat shrink and northward range shift by 77-90 km in response to projected future climate change in 2080. Southeastern China would suffer from losing climate suitability, whereas the climate conditions in Qinghai-Tibet Plateau and northeastern China were projected to become suitable for more protected species. On average, each protected area in decline of suitable climate for China would experience a 3-4 species by 2080. Cli- mate change will modify which species each protected area will be suitable for. Our results showed that the risk of extinction for Chinese protected birds would be high, even in the moderate climate change scenario. These findings indicate that the management and design of nature reserves in China must take climate change into consideration.