GeoPython 2021 Schedule

Day 1: April 22, 2021

Room 1 Room 2
Your Time
Session Type
Registration Opens

Streaming links can be found in chat rooms ("Track 1" and "Track 2") (Check your email for your login to chat)
Special Session
Opening Session Day 1

Conference Opening Day 1
Special Session
Geopythonic processing of massive high resolution Copernicus Sentinel data streams on cloud infrastructure
ANASTASAKIS Konstantinos, Guido Lemoine

We demonstrate the use of geopython solutions to address Big Data Analytics requirements in cloud-based processing of massive high resolution Copernicus Sentinel data streams in a European agricultural use context.
Interpolating Elevation Data inside Tunnel and Bridge Networks
Alexander Held
geOps GmbH

We present a method to interpolate elevation data inside complex tunnel or bridge networks. Our work is based on Python libraries such as NumPy, NetworkX and Flask.
How to Use Spatial Data to Identify CPG Demand Hotspots
Argyrios Kyrgiazos

Spatial models can provide a rich set of tools to analyze multivariate geolocated data, enabling data-driven decisions to understand consumer behavior in the CPG industry.
Mapquadlib - A Python library that supports multi-level tiled representations of the map of the earth.
Christian Stade-Schuldt

Mapquadlib is a zero-dependency OSS Python library that contains implementations for various tile schemas used at HERE.
30 Maps in 30 days with Python
Alexander Kmoch, Topi Tjukanov
University of Tartu

The *#30DayMapChallenge* is an increasingly popular phenomenon, started on Twitter just 2 years ago by Topi Tjukanov, where he encourages fellow geo folks to make a map to different themes each day during the month of November. In this talk we introduce the MapChallenge and describe how to solve all the challenges within the available Python/PyViz geospatial library ecosystem, including packages, themes, challenges, gotchas and revelations during making 30 maps in 30 days.
Python in QGIS
Zoltan Siki
Budapest University of Technology and Economics

Python can be used in many ways in QGIS. The presentation shortly introduces how and where Python can be used from the QGIS Python console to the standalone QGIS Python applications.
Predicting Traffic Accident Hotspots with Spatial Data Science
Miguel Alvarez

Road traffic accidents are a major health and economic problem worldwide. Spatial Data combined with Data Science tools and models can help anticipate high-risk locations dynamically based on factors such as traffic, weather, and road signaling.
Building custom web administrators for geographic data driven websites with Django
Marc Compte
University of Girona

In this talk I will show some of the Django admin core functionalities (routing, ORM, templating, i18n & l10n,...) that will allow us to set up a backend for our web map in just a few steps. I’ll show some of the customizations that we can do out-of-the-box, as well as some of the third-party modules that we can use to include additional functionalities to our backend, such as tabbed forms, REST API, menus, dashboards, adding field types and widgets (geom, rich text editor, color field, …).
QGIS Bridge, Metadata & Geostyler
Paul van Genuchten, Sander Schaminee
GeoCat BV, Netherlands

Annual report from the GeoCat python team. A next release of GeoCat Bridge for QGIS is upcoming. We've seen some adoption of the underlying modules outside the QGIS domain.
Interactive mapping and analysis of geospatial big data using geemap and Google Earth Engine
Qiusheng Wu, Kel Markert

This workshop introduces the [geemap]( Python package and how it can be used for interactive mapping and analysis of large-scale geospatial datasets with Earth Engine in a Jupyter-based environment. We will also demonstrate how to produce publication-quality maps and build interactive web apps.
How I Used Python and Big Data to Measure Seismic Silences during the COVID19 Lockdown?
Artash Nath

"Lockdown' was a key tool used by governments around the world to stem the movement of people to check the spread of COVID19. I analyzed the impact of lockdown on human movements by writing Python algorithms to measure the reduction in seismic vibrations using data from seismic stations across Canada.
SaferPLACES platform: a GeoPython-based climate service addressing urban flooding hazard and risk.
stefano bagli
GECOsistema srl

GeoPython libraries for mapping flood hazard and risk in urban areas
ML-Enabler: Enabling Rapid Machine Learning Inference of School Mapping in Asia, Africa and South America
Martha Morrissey
Development Seed

ML-Enabler is an open source model inferencing tool with a UI that acts as a github for models, allows users to run inference at scale, validate model predictions, integrate with common OSM mapping tools like Map Roulette. We will discuss how Development Seed used ML-Enabler to facilitate model inference to detect previously unmapped schools over 71 million zoom 18 tiles over multiple countries in Africa, Asia, and South America as part of UNICEF’s Project Connect initiative.
Estimating the economic impact of COVID-19 using real-time images from space
Nataraj Dasgupta

In this talk, we will first discuss the process of analysing GeoTIFF images of surface lights on Earth from space using multicore processing tools on AWS. Second, we will discuss how the data can then be used to predict GDP and other economic metrics, especially during supply-demand shocks like COVID-19.
Your Time
Session Type
Crop yield prognosis using ML and EO data
Peter Fogh

SEGES, a Danish agricultural knowledge and innovation centre, developed and productionized in 2020 a crop yield prognosis model. We present the utilized ML methods, EO data, de-facto Python GIS packages, experiment results, and DevOps solutions.
Mapping, Monitoring and Forecasting Groundwater Floods in Ireland
Joan Campanyà i Llovet
IT Carlow / Geological Survey Ireland

An automated approach for characterizing groundwater floods in Ireland based on remote sensing data, GIS information and hydrological models to improve the reliability of adaptation planning and predictions in the groundwater sector.
The power of "Where" - Location data in Moovit
Yehuda Horn

behind the scene of geo-data challenges in Moovit. Location data is everywhere, in multiple formats and different environments. We use python as cross-platform programming to work with our location data in many ways. Python allows us to read, edit, and analyze location data on one hand and visualize the data, on the other hand. the data process and the visualization process can be in GIS software, Jupyter notebooks, or by standalone Python script.
Universal geospatial data storage with TileDB: No more file formats
Norman Barker
TileDB Inc

This talk will describe the open-source TileDB Embedded library and its integrations in the geospatial domain. We will give examples of its use for point clouds, SAR and weather with partners such as Capella Space and exactEarth, and emphasize on the need to depart from file formats and focus on universal, end-to-end solutions instead.
3D Geological Modelling using GemPy
Kristiaan Joseph

Several 3D modelling and visualization Python scripts have been combined into a seamless workflow and subsequently applied to a sparse dataset in a geologically complex area. Preliminary 3D-model results are encouraging and align with known and inferred regional geology.
The Open Data Cube (ODC): a very intuitive tool to store, manage and analyse satellite images data
Aurelio Vivas
Universidad de los Andes

In the era of Big Data, mechanisms to easily store, retrieve and analyze large amounts of earth observation data are needed. The Open Data Cube (ODC) proposes to minimize these complexities, with the use of open source tools (xarray, gdal, rasterio, dask, netcdf, geotiff, postgresql) composed in a single Python interface.
eemont: A Python Package that extends Google Earth Engine

eemont is a new python package that extends Earth Engine classes with methods to pre-process (and process) the most used satellite imagery.
Deep learning-based remote sensing for disaster relief with Python
Thomas Chen

Attend this talk to learn about ongoing and future work using deep learning techniques to remotely sense and assess building damage post-natural disaster, using Python.

Day 2: April 23, 2021

Room 1 Room 2
Your Time
Session Type
Opening Session Day 2

Special Session
Geospatial analysis using python 101
krishna lodha

This workshop is ideal for someone who has recently started using python and exploring the possibilities of it in the GIS industry. This is the beginning of complex spatial scripting
Predicting dissolved oxygen in a lagoon using interpretable machine learning
Dimitris Politikos

The goal of the study is to predict dissolved oxygen concentration in a lagoon with XGBoost algorithm, based on a series of explanatory variables (e.g., water temperature, pH value, oxidation-reduction potential, air temperature, salinity). Special focus is given on interpreting the outcomes using Additive exPlanations (SHAP) methodology, aiming to elucidate the environmental windows that cause low levels of dissolved oxygen (anoxic conditions), which may have severe impact on the survival rate of aquatic organisms.
The Mission Support System
Reimar Bauer

A research aircraft mission involve measuring atmospheric situations of interest along a flight path. These missions typically involve a wide range of unique instruments developed and operated by different scientific institutions, with different requirements and operating conditions. The Mission Support System is a software to solve these conditions.
Curie Point Depth Mapping using PyCurious from Aeromagnetic Data
Horizon Perdana

Curie Point Depth is the depth where the earth crust are losing the magnetic ability and the temperature is above 580 °C. The anomalous CPD (shallower depth than usual, approximately at 15km) could be the initial information of the heat source of a geothermal reservoir. The CPD of an area could be estimated by processing the a set of magnetic anomaly data.
Understanding Qiskit: Quantum by Quantum
Anmol Krishan Sachdeva

Although there have been some significant advancements in software technologies, there are still many problems which classical computing cannot solve. Quantum Computing has the potential to solve such problems and provide high-performance computing capabilities. This talk focuses on introducing the basic concepts of Quantum Computing using Qiskit.
Improved Crop Yield Prediction through Spatio-Temporal Analysis of Agricultural Data
Arjumand Younus

Precision agriculture has seen a remarkable progress over the last decade or so with its primary goal being accurate prediction of crop yield. This talk provides an overview of efforts in SFI's funded project CONSUS whereby agricultural data obtained from a commercial agronomy service company is used to derive significant insights for crop yield prediction.
The Bavarian Open Data Cube
Sebastian Foertsch, Steven Hill

Earth Observation Data are an important source of information to tackle the Global Change. Datacubes in cloud environments can be helpful to organize the growing amount of data and makes it easier for many experts to get started.
The Participatory Terrain model (ParTerra) in Python
Arjen Haag

The Participatory Terrain model (ParTerra) deploys an algorithm to fuse together data from OpenStreetMap (OSM) and any base elevation dataset to create a high-resolution digital terrain model for any area in the world.
Over-Simplified Modeling - The case of the Global Warming Potential
Mike Müller
hydrocomputing GmbH & Co. KG

This talk introduces a Python-based model for an improved calculation of the Global Warming Potential. The new model is only slightly more complex, but greatly improves the model outcomes.
Trackintel: An open-source python library for human mobility modeling and analysis
Ye Hong

Focusing on human mobility data, the trackintel framework ( provides functionalities for mobility data modeling, quality enhancement, data integration, performing quantitative analysis and mining tasks, and visualizing the data and/or analyzing results.
On the role of packaging in GIS, or: How to drive computer clusters and GPUs from within desktop GUI applications for non-technical users
Sebastian M. Ernst - Independent Scientific Services

There is a growing discrepancy between what FOSS GIS GUI applications are capable of and what the contemporary (geo-) Python stack can do. While the latter is clearly much more powerful, it requires extensive and constantly growing software development skills. This talk looks at ways of how to (re-) connect the two worlds, especially for non-technical users through the means and recent advances in software packaging.
Pyinterpolate - Python package for spatial interpolation and deconvolution of areal data
Szymon Moliński

**PyInterpolate** is designed as the Python library for geostatistics. It's role is to provide access to spatial statistics tools used in a wide range of studies. The main advantage of a package is ability to transform areal aggregates into smaller blocks with Area-to-Point Poisson Kriging technique.
Bins! An easy path to make them using Fast API, PostGIS and JavaScript
Vinícius Cruvinel Rêgo

In order to manage and analyze geospatial data, more frequently are being used the Binning Process to achieve consistent results. In a more generic way, Binning is the process to group (cluster) points data into defined geometric features like squares or hexagons. For example, the process that uses hexagon polygons is defined as "Hexagon Binning". Nowadays, this process became more used as provides a quick and efficient way to summarize (clustering) points data, giving a better overview principal when the amount of points are high.
Spatial SQL? ...can you say that in Python, please?
César Ariel Pérez Mercado

In this talk, we'll review and solve some spatial analysis exercises in both of two ways: using Spatial SQL in PostGIS, and using GeoPandas in Python
Audio Signal Processing for Feature Building and Machine Learning
Jyotika Singh

This talk will highlight audio signals, audio processing techniques, feature building and end to end Machine Learning examples along with the open source tools that can be leveraged in python.
Cal ToxTrack: A Web GIS for Pollution Mapping in California
Megan Luisa White

This project focused on the public’s right-to-know about toxic chemical releases in their community by developing a geospatial web application called Cal ToxTrack. Built from scratch using PostgreSQL as a database, GeoDjango as a Python development framework, and Leaflet as a JavaScript framework, it effectively visualizes chemical releases and provides interactive tools to help explore pollution data.
Closing Session

Special Session
Your Time
Session Type
Travel Time Prediction for Urban Travel using Uber Movement and OpenStreetMap
Vishnu Prasad J S, Ujaval Gandhi

In this talk, we will demonstrate how two large open datasets - Uber Movement and OpenStreetMap (OSM) - can be used to develop a pretty robust travel time predictor for urban travel. We use open-source routing libraries to build a machine learning model that can accurately predict travel time across many cities of the world.
Spatial analysis of Covid-19 relation with weather parameters
Abouzar Ramezani

Finding relation between weather parameters and covid-19 spread using netcdf data.
Maps with Django
Paolo Melchiorre

Keeping in mind the Pythonic principle that “simple is better than complex” we'll see how to create a web map with the Python based web framework Django using its GeoDjango module, storing geographic data in your local database on which to run geospatial queries.
Creating 3D Terrain Models of Switzerland using Open Data
Martin Christen

Since March 1, 2021, the Federal Office of Topography swisstopo made its official digital data and services available online free of charge as Open Government Data (OGD).
Exploratory Movement Data Analysis
Anita Graser

Recent developments in Python data visualization libraries enable data analysts and scientists to quickly and intuitively create interactive data visualizations. In this talk, we dive into examples of visualizing movement (GPS tracking) datasets using MovingPandas, GeoViews, and HoloViz in Jupyter notebooks.
Should We Return to Python 2?
Miroslav Šedivý

Did you migrate all your projects to Python 3 or kept a backdoor open just in case?