# Creating a Project In ecology, plot or quadrat-based sampling is a [classic](https://www.webpages.uidaho.edu/veg_measure/Modules/Lessons/Module%205\(Density\)/5_2_Plot-based_Techniques.htm) technique for capturing information such as density, frequency, biomass and cover of organisms. Quadrats (also known as plots) are typically a square frame placed over the seafloor. In ReefCloud, digital downward-facing photographs can be used as quadrats from which we can pull information on benthic composition, using a point-count approach. In ReefCloud, points are overlain across images and the organism (or group) under each point is annotated, with the proportion of points falling on an organism/group being used to quantify percentage cover. Comparing cover estimates from photo quadrats between reefs and through time can help us monitor changes in community composition. **How many points per image should I choose?** Point count methodology, whereby the proportion of randomly overlain points intersecting an organism or substratum is used to estimate coverage, is a common method for [estimating the abundance of benthic organisms on coral reefs](https://www.semanticscholar.org/paper/Development-of-Benthic-Sampling-Methods-for-the-and-Brown-Cox/bec318eac011766c8c8d5d95d07948362b4ea0f7). Studies have shown that percent cover estimates derived from overlaying points onto each photo can act as a proxy for both abundance and biomass, with similar trends detected for both individual species and community metrics ([Perkins et al 2022](https://www.sciencedirect.com/science/article/pii/S1470160X22005003)). "Points" here refers to the number of human annotatable points overlaid on each photograph, and this is defined during project creation. Users can define whether the points are to be randomly dispersed across an image, or organised a fixed or grid format. Although the user can choose the number of human annotatable points per image used to train the AI model, the model will always annotate 50 points per image. The optimum number of human annotatable points is dependent on the number of images that will be annotated, as well as the spread of the images across the habitat you want to sample, and the size, abundance and spatial distribution of the target organisms (see [Perkins et al](https://www.sciencedirect.com/science/article/pii/S0272771416301068) 2016). It is also important to consider the scientific question and what kind of information you're interested in capturing from your imagery. Generally precision is improved with a larger number of images than more points per image. For broad scale monitoring, 5 to 10 points per image is generally considered adequate, especially where there are plenty of photos. Some research suggests where coral cover is lower a greater number of points are needed (for example 5 points for >60% coral cover and 30 points for <30%). If your goal is to adequately capture all recognisable features within each image, >60 points has been recommended ([Perkins](https://www.sciencedirect.com/science/article/pii/S0272771416301068) et al 2016). The complexity of your label set will also influence the number of recommended points. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.reefcloud.ai/frequently-asked-questions/creating-a-project.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.