Habitat loss for black flying foxes and implications for Hendra virus.

Context: Environmental change impacts natural ecosystems and wildlife populations. In Australia, native forests have been heavily cleared and the local emergence of Hendra virus (HeV) has been linked to land-use change, winter habitat loss, and changing bat behavior. Objectives: We quantified changes in landscape factors for black flying foxes (Pteropus alecto), a reservoir host of HeV, in sub-tropical Queensland, Australia from 2000-2020. We hypothesized that native winter habitat loss and native remnant forest loss were greatest in areas with the most human population growth. Methods: We measured the spatiotemporal change in human population size and native 'remnant' woody vegetation extent. We assessed changes in the observed P. alecto population and native winter habitats in bioregions where P. alecto are observed roosting in winter. We assessed changes in the amount of remnant vegetation across bioregions and within 50 km foraging buffers around roosts. Results: Human populations in these bioregions grew by 1.18 M people, mostly within 50 km foraging areas around roosts. Remnant forest extent decreased overall, but regrowth was observed when policy restricted vegetation clearing. Winter habitats were continuously lost across all spatial scales. Observed roost counts of P. alecto declined. Conclusion: Native remnant forest loss and winter habitat loss were not directly linked to spatial human population growth. Rather, most remnant vegetation was cleared for indirect human use. We observed forest loss and regrowth in response to state land clearing policies. Expanded flying fox population surveys will help better understand how land-use change has impacted P. alecto distribution and Hendra virus spillover. Supplementary Information: The online version contains supplementary material available at 10.1007/s10980-023-01642-w.

A Mobile-Based Deep Learning Model for Cassava Disease Diagnosis.

Convolutional neural network (CNN) models have the potential to improve plant disease phenotyping where the standard approach is visual diagnostics requiring specialized training. In scenarios where a CNN is deployed on mobile devices, models are presented with new challenges due to lighting and orientation. It is essential for model assessment to be conducted in real world conditions if such models are to be reliably integrated with computer vision products for plant disease phenotyping. We train a CNN object detection model to identify foliar symptoms of diseases in cassava (Manihot esculenta Crantz). We then deploy the model in a mobile app and test its performance on mobile images and video of 720 diseased leaflets in an agricultural field in Tanzania. Within each disease category we test two levels of severity of symptoms-mild and pronounced, to assess the model performance for early detection of symptoms. In both severities we see a decrease in performance for real world images and video as measured with the F-1 score. The F-1 score dropped by 32% for pronounced symptoms in real world images (the closest data to the training data) due to a decrease in model recall. If the potential of mobile CNN models are to be realized our data suggest it is crucial to consider tuning recall in order to achieve the desired performance in real world settings. In addition, the varied performance related to different input data (image or video) is an important consideration for design in real world applications.

Deep Learning for Image-Based Cassava Disease Detection.

Cassava is the third largest source of carbohydrates for human food in the world but is vulnerable to virus diseases, which threaten to destabilize food security in sub-Saharan Africa. Novel methods of cassava disease detection are needed to support improved control which will prevent this crisis. Image recognition offers both a cost effective and scalable technology for disease detection. New deep learning models offer an avenue for this technology to be easily deployed on mobile devices. Using a dataset of cassava disease images taken in the field in Tanzania, we applied transfer learning to train a deep convolutional neural network to identify three diseases and two types of pest damage (or lack thereof). The best trained model accuracies were 98% for brown leaf spot (BLS), 96% for red mite damage (RMD), 95% for green mite damage (GMD), 98% for cassava brown streak disease (CBSD), and 96% for cassava mosaic disease (CMD). The best model achieved an overall accuracy of 93% for data not used in the training process. Our results show that the transfer learning approach for image recognition of field images offers a fast, affordable, and easily deployable strategy for digital plant disease detection.