Welcome to PredictiveWorks. Python branch. PythonWorks. has a strong focus on data science and illustrates recent project results. This repository was made to be helpful for others and to provide technical hints in case of poorly documented open source libraries.
- Climate Change
- Earth Observation
- Geo Marketing
- Smart Agriculture
- Smart Building
- Smart City
- Smart Energy
- Smart Infrastructure
- Sustainability Reporting
The June to August 2022 temperature distribution in Austria in action:
heatwave-2022.mp4
This section introduces (visualization) results from projects related to open EO datasets.
Copernicus Land Monitoring Service for Italy's field detection and monitoring.
Selected list of 4 European NUTS 3 regions (Bern, Torino, Munich, Stuttgart) enriched with EU-DEM dataset.
This section introduces (visualization) results from recent smart energy projects.
The image below illustrates the capacity in MW of active coal fueled power plants in Europe.
The image below illustrates the potential net power of private solar units, aggregated at German county level (left side). The net power distribution is compared to the spatial distribution of annual solar radiation (right side). As a result, there is no spatial correlation of areas with high net power & radiation.
This section leverages the NEWA Mesoscale Atlas. The mesoscale part of the New European Wind Atlas (NEWA) was created from WRF model simulations for all of Europe at a grid spacing of 3 km x 3 km, initially covering the 30 years from 1989 to 2018.
The WRF model simulations (using WRF V3.8.1) were done in 10 partly overlapping domains using ERA5 reanalysis and OSTIA sea surface temperatures. The model configuration, production and evaluation of the results against observations are described in Hahmann et al. (2020) and Dörenkämper et al. (2020).
The image below visualizes wind speeds in 100 m (above ground) in Germany.
This section introduces (visualization) results from recent smart agriculture projects.
The image below visualizes the number of gateways per NUTS-3 regions in Germany.
The image shows the individual gateways for Vienna, Austria as an overlay for the Vienna elevation model (Copernicus DEM), and the Vienna vegetation index (Sentinel. This map is part of a project that evaluates the usability of LoRaWAN technology for urban-near agriculture.
The image below visualizes drought index in mm/°C (de Martonne), Germany 2018-08.
The image below visualizes soil moisture in % nFK, Germany 2018-08.
The image below shows multiple vegetation indexes for a summer day in Vienna, including the Sentinel-2 true color image.
This section introduces (visualization) results from recent smart building projects.
This section introduces (visualization) results from recent smart city projects.
The image illustrates the vegetation index (NDVI) of the city of Bern. The data were extracted from Sentinel-2 (relative orbit, 108).
The image visualizes the LTE cell towers in Austria, Germany, Italy and Poland. It is based on OpenCelliD, the world's largest open database of cell towers, which so far, is one of the most precise publicly available data sources for telecom-related projects.
This section introduces (visualization) results from recent geo marketing projects. Geo-referenced socio-demographic, energy, climate, behavior and regional trends data form an important basis for hyper-local customer segmentation.
The image below illustrates the age distribution of German counties, elder persons (>= 60) on the left side, and children (<= 10) on the right side.
This section introduces (visualization) results from recent sustainability projects.
The image below visualizes the protected areas in Italy.
The social dimension of sustainability reporting (e.g., to disclose global supplier relations) needs a world's eye on conflicts, human rights violation and more. The image below illustrates 15 minutes of the world's sentiment.
The image shows the annual water risk in 4 European countries for the agricultural sector. The risk is normalized according to the following categories: Low (0, 1), Low-Medium (1, 2), Medium-High (2, 3), High (3, 4), Extremely High (4, 5).
