Remote Sensing in Ecology and Conservation · 2022 · 71 citations · 55 references
Natural ResourcesEcologyPlant SciencesComputer VisionInvasive Species ManagementPlant EcologyInvasive Plant MonitoringRemote Sensing Change DetectionVegetation Change DetectionVegetation MonitoringConvolutional Neural NetworksInvasive Plant MappingInvasive SpeciesRemote Sensing For DetectionRemote Sensing Of PhenologySatellite Imagery AnalysisSatellite PhenologySatellite-based Vegetation Monitoring
Abstract Effective management of invasive species requires rapid detection and dynamic monitoring. Remote sensing offers an efficient alternative to field surveys for invasive plants; however, distinguishing individual plant species can be challenging especially over geographic scales. Satellite imagery is the most practical source of data for developing predictive models over landscapes, but spatial resolution and spectral information can be limiting. We used two types of satellite imagery to detect the invasive plant, leafy spurge ( Euphorbia virgata ), across a heterogeneous landscape in Minnesota, USA. We developed convolutional neural networks (CNNs) with imagery from Worldview‐2 and Planetscope satellites. Worldview‐2 imagery has high spatial and spectral resolution, but images are not routinely taken in space or time. By contrast, Planetscope imagery has lower spatial and spectral resolution, but images are taken daily across Earth. The former had 96.1% accuracy in detecting leafy spurge, whereas the latter had 89.9% accuracy. Second, we modified the CNN for Planetscope with a long short‐term memory (LSTM) layer that leverages information on phenology from a time series of images. The detection accuracy of the Planetscope LSTM model was 96.3%, on par with the high resolution, Worldview‐2 model. Across models, most false‐positive errors occurred near true populations, indicating that these errors are not consequential for management. We identified that early and mid‐season phenological periods in the Planetscope time series were key to predicting leafy spurge. Additionally, green, red‐edge and near‐infrared spectral bands were important for differentiating leafy spurge from other vegetation. These findings suggest that deep learning models can accurately identify individual species over complex landscapes even with satellite imagery of modest spatial and spectral resolution if a temporal series of images is incorporated. Our results will help inform future management efforts using remote sensing to identify invasive plants, especially across large‐scale, remote and data‐sparse areas.
55
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Sepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 98.1K citations
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Squeeze-and-Excitation Networks
Jie Hu, Li Shen, Samuel Albanie et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2019 · 12.5K citations
A survey on Image Data Augmentation for Deep Learning
Connor Shorten, Taghi M. Khoshgoftaar · Journal Of Big Data · 2019 · 12.4K citations · Full text