Marsh ecosystems are some of our most important, serving many crucial ecological functions. They are also rapidly changing, and it is vital for scientists to track these changes. This includes monitoring the health of marshes via estimating ground coverage by various grass species, a task that requires human labor to look at marsh images and manually estimate the coverage. Clearly, this task can be quite formidable. To automate this standard yet laborsome process, we developa web-based system, called MarshCover, that automates the process of estimating vegetation density in marsh images using convolutional neural networks (CNNs). MarshCover, to the best of our knowledge, is the first such tool available to biologists that uses CNNs for marsh vegetation estimations. In order to select effective CNN models for our MarshCover server, we conduct extensive empirical analyses of three distinct CNNs, i.e., LeNet-5, AlexNet and VGG-16, to compare their performances on a public marsh image dataset. To this end, we address two classification problems for this paper: a binary classification problem classifying points as vegetated and unvegetated, and a multiclass classification problem that classifies points into either an unvegetated class or one of five different species classes. Our experiments identify the VGG16 model as the best classifier to embed in MarshCover for both the binary classification problem and the full classification problem with a two model classifier (called two-shot). These two classifiers had accuracies on test data of 90.76% and 84% respectively. MarshCover is publicly available online.

Vegetation monitoring is one of the major cornerstones of environmental protection today, giving scientists a look into changing ecosystems. One important task in vegetation monitoring is to estimate the coverage of vegetation in an area of marsh. This task often calls for extensive human labor carefully examining pixels in photos of marsh sites, a very time-consuming process. In this paper, aiming to automate this process, we propose a novel framework for such automation using deep neural networks. Then, we focus on the utmost component to build convolutional neural networks (CNNs) to identify the presence or absence of vegetation. To this end, we collect a new dataset with the help of Guana Tolomato Matanzas National Estuarine Research Reserve (GTMNERR) to be used to train and test the effectiveness of our selected CNN models, including LeNet-5 and two variants of AlexNet. Our experiments show that the AlexNet variants achieves higher accuracy scores on the test set than LeNet-5, with 92.41\% for a AlexNet variant ondistinguishing between vegetation and the lack thereof. These promising results suggest us to confidently move forward with not only expanding our dataset, but also developing models to determine multiple species in addition to the presence of live vegetation.

To protect the world’s marshlands, it is of utmost importance to be able to monitor their vegetation composition and coverage. This currently is accomplished by large teams of researchers and volunteers manually looking at the marsh images and labeling randomly selected pixels by what species (or lack thereof) is present at the pixel. This task, however, is extremely labor intensive, limiting the amount of quality environmental monitoring that can be done in the field. If the task was automated, teams would be able to monitor larger swaths of land. In this paper, we propose a novel framework for such automation using deep neural networks. Then, we focus on the key component of this framework: a binary classifier to decide whether a pixel is vegetated or not. To this end, we create a dataset of labeled snippet images out of publicly available photoquadrats of the marshlands in Florida. Finally, we construct LeNet-5 and AlexNet, adjusted to our input snippets, faster training time, networks and experiment to learn them on our dataset for the binary classification task. Our results show that the AlexNet model achieves higher accuracy on the test set than the LeNet-5 model, with 92.41% for AlexNet and 91.34% for LeNet-5.