The multi-step method here applied in studying the genetic structure of a low dispersal and philopatric species, like the Fire Salamander Salamandra salamandra, was proved to be effective in identifying the hierarchical structure of population living in broadleaved forest ecosystems in Northern Italy. In this study 477 salamander larvae, collected in 28 sampling populations (SPs) in the Prealpine and in the foothill areas of Northern Italy, were genotyped at 16 specie-specific microsatellites. SPs showed a significant overall genetic variation (Global FST=0.032, p<0.001). The genetic population structure was assessed by using STRUCTURE 2.3.4. We found two main genetic groups, one represented by populations inhabiting the Prealpine belt, which maintain connections with those of the Eastern foothill lowland (PEF), and a second group with the populations of the Western foothill lowland (WF). The two groups were significantly distinct with a Global FST of 0.010 (p<0.001). While the first group showed a moderate structure, with only one divergent sampling population (Global FST =0.006, p<0.001), the second group proved more structured being divided in four clusters (Global FST=0.017, p=0.058). This genetic population structure should be due to the large conurbations and main roads that separate the WF group from the Prealpine belt and the Eastern foothill lowland. The adopted methods allowed the analysis of the genetic population structure of Fire Salamander from wide to local scale, identifying different degrees of genetic divergence of their populations derived from forest fragmentation induced by urban and infrastructure sprawl.

The dataset

The Pest Sticky Traps (PST) dataset is a collection of yellow chromotropic sticky trap pictures specifically designed for training/testing deep learning models to automatically count insects and estimate pest populations.

Images were manually annotated by some experts of the Department of Agriculture, Food and Environment of the University of Pisa (Italy) by putting a dot over the centroids of each identified insect. Specifically, we labeled insects as belonging to the category “whitefly” considering two different species, i.e., the sweet potato whitefly (Bemisia tabaci) (Gennadius) and the greenhouse whitefly (Trialeurodes vaporariorum) (Westwood).

The dataset comprises two subsets:
- a subset we suggest using for the training/validation phases (contained in the `train/` folder)
- a subset we suggest using for the test phase (contained in the `test/` folder)

Annotations of the two subsets are contained in `train/annotations.csv` and `test/annotations.csv`, respectively. They have the following columns:
- *imageName* - filename of the image containing the whiteflies,
- *X,Y* - 2D coordinates of the whitefly in the image space,
- *class* - class index of the insect (always 0 in this dataset).

Citing our work

If you found this dataset useful, please cite the following paper

@inproceedings{CIAMPI2023102384,
  title = {A deep learning-based pipeline for whitefly pest abundance estimation on chromotropic sticky traps},
  journal = {Ecological Informatics},
  volume = {78},
  pages = {102384},
  year = {2023},
  issn = {1574-9541},
  doi = {10.1016/j.ecoinf.2023.102384},
  url = {https://www.sciencedirect.com/science/article/pii/S1574954123004132},
  year = 2023,
  author = {Luca Ciampi and Valeria Zeni and Luca Incrocci and Angelo Canale and Giovanni Benelli and Fabrizio Falchi and Giuseppe Amato and Stefano Chessa},
}

and this Zenodo Dataset

@dataset{ciampi_2023_7801239,
  author = {Luca Ciampi and Valeria Zeni and Luca Incrocci and Angelo Canale and Giovanni Benelli and Fabrizio Falchi and Giuseppe Amato and Stefano Chessa},
  title = {Pest Sticky Traps: a dataset for Whitefly Pest Population Density Estimation in Chromotropic Sticky Traps}},
  month = apr,
  year = 2023,
  publisher = {Zenodo},
  version = {1.0.0},
  doi = {10.5281/zenodo.7801239},
  url = {https://doi.org/10.5281/zenodo.6560823}
}

Contact Information

If you would like further information about the dataset or if you experience any issues downloading files, please contact us at luca.ciampi@isti.cnr.it