Welcome to Vattenfall Open data
Explore Vattenfall datasets and innovation projects where the data has been used. Through this portal Vattenfall seeks to boost innovation in the field of data science and we encourage you to use the data in your own projects to create new solutions.
This portal is a pilot where different data and projects will be shared. Over time the data and projects displayed might change. The data is shared under different licenses that permits use of the data in different applications. You can find more information connected to each dataset.
Fish-AI is a project to use image recognition to count and analyze fish travelling in fish-ladders past hydropower dams. The data in this project is shared under the license CC BY 4.0.
The data contains images (.png) and labels (.txt) containing information about class and bounding box.
To ensure that the Open Data initiative proceeds in the right direction, please take our survey.
To the survey
Assessing biodiversity in rivers is important to understand the environmental impact of electricity generation from hydropower. Hydropower dams are often designed with a fish-ladder that bypasses the dam and allows river travelling fish to jump to the upper part of the river. This is one of many different actions taken to prevent negative impact on the local biodiversity.
Part of understanding the efficiency of the fish-ladder and the biological state of the river is to count the fish that passes in the fish-ladder. This can be done manually or through some kind of camera equipment. Historically infrared cameras have been used, but with modern development in AI together with camera technology biologist can instead use digital cameras to capture additional information more accurately. This information can then be processed and automatically analyzed using image recognition.
Besides improving the time it takes to count fish travelling in the fish ladder, the combined technology also has the benefit of opening up more information about the animals. Through our biology experts we have been able to assess the amount of wild vs farmed fish that pass the hydropower dam, and also understand the different levels of diseases such as fungi that those fish have.
There has also been other research projects in the area, for example one to understand the effects of imbalances in the dataset on the accuracy of the image recognition. The curious reader can read more here: Convolutional neural network based object detection in a fish ladder: Positional and class imbalance problems using YOLOv3
Project information and data coming soon.