Plant leaf classification

There are important potential applications for a machine learning system than can classify plants. For example, current research on crop protection is using machine learning for precision weed and plant disease detection. The importance of moving away from traditional pesticide-based crop protection methods cannot be overstated, as demonstrated by the alarming rate at which flowering plants are evolving away from insect pollination.

I obtained a dataset of plant leaf images (Hussain, 2023) and compared three machine learning algorithms for classification: multilayer perceptron, random forest and support vector machine. The classifiers’ accuracy vary between 74% and 84% .

The Jupyter notebook with the full Python code can be accessed on Kaggle.

Computing α-diversity

Diversity indices are a common descriptive statistic used in biodiversity informatics. Diversity indices typically express the species richness of a given habitat or area. The α-diversity index is suitable when studying a single habitat and is expressed by a single number. There are several commonly used equations used to compute α-diversity. In this example, I will be using the Simpson’s diversity index, which is computed by the formula:

    \[D = 1 - \sum_{i=1}^{S}p_i^2\]

Where S is the number of species in the sample and p is the proportion of a particular species. The Simpson’s diversity index is thus more influenced by common species rather than by rare species and is often considered to be an index reflecting the actual species diversity in a sample.

To illustrate this, I will use will use data obtained from GBIF. Remember, α-diversity is suitable for expressing the diversity within a single habitat, so I will obtain data accordingly. Here I chose the Tiergarten, a large (210 hectare) park in central Berlin.

Continue reading “Computing α-diversity”

Using neural networks to classify 3D scans

For my capstone project in machine learning at EPFL, I wrote a classifier capable of sorting 3D scans of archaeological objects by culture.

Digitization of museum collections is currently a major challenge faced by cultural heritage and natural history museums. Museums are expected to digitize the collections to improve not only the documentation of artifacts, but also their availability for research, reconstruction and outreach activities, and to make these digital representations available online.

Machine learning setup

Continue reading “Using neural networks to classify 3D scans”

Comparing the distribution of Corvus corone and Corvus cornix

In this post, I will use a divergent color scale to plot two distributions on the same map. As an example, I chose to plot the European distribution of two species of corvids: the carrion crow (Corvus corone) and the hooded crow (Corvus cornix). There has been some adjustments to the taxonomical status of the hooded crow (see Parkin et al., 2003 for details), hoewever, currently, they are regarded as different species.

In this map, I will use a divergent color scale to show areas in Europe where each species is dominant, and also show areas where both species are present.

Distribution of Corvus corone and C. cornix in Europe
Continue reading “Comparing the distribution of Corvus corone and Corvus cornix

Simple distribution maps using ggplot

In a previous post, I discussed how to plot GBIF occurrence data using OpenStreetMaps. Here, I will plot a distribution map. Distribution maps differ from occurrence maps in that occurrences are aggregated and plotted as a heat map. Additionally, the map has to be projected using an equal area projection.
I will illustrate these two features by plotting the distribution of the tawny owl (Strix aluco) in Europe.

Distribution of the tawny owl in Europe
Continue reading “Simple distribution maps using ggplot”

Spectrograms

Spectrograms are a common visualization of sound data. Visualizing sound data can be useful when doing a presentation or for publication. Additionally, machine learning algorithms for classifying sound data generally use spectrograms as their starting point, instead of the sound data itself, as many advanced algorithnms for classifying images are readily available. The example uses the R packages warbleR (Araya-Salas & Smith-Vidaurre, 2017), seewave (Sueur, Aubin, Simonis, 2008) and tuneR (Ligges et al., 2018).

This example draws the spectrogram of the call of a tawny owl (Strix aluco).

Tawny owl (Strix aluco). Alvaro Ortiz Troncoso, XC494801. Accessible at www.xeno-canto.org/494801.
Continue reading “Spectrograms”

Ecological data sets in R-core

If you are using R, then you are probably familiar with the mtcars data set, that is used in many R tutorials. The “car analogy” is so common in text books, that this so-called technique has its own Wikipedia page. For the rest of us, who don’t understand anything about motor cars, R-core comes with a wide selection of example data sets, some of which relate to ecology or biodiversity.

Continue reading “Ecological data sets in R-core”