This Year's
Challenges
Finals
Biodiversity
A Science global study revealed a strong effect of humans on daily patterns of wildlife activity. Animals are seeking nocturnal refuge increasing their nocturnality by an average factor of 1.36 due to human presence. That sums to an already substantial proportion of nocturnal global biodiversity, with 30% of all vertebrates and more than 60% of all invertebrates, according to LUCIA.

However, even during the night, there are big challenges to the species. By changing the night behavior of organisms, Artificial Light at Night (ALAN) is a major threat to global biodiversity. One of the most affected species is bats, but they are not the only ones. According to LUCIA, ALAN kills 6.8 million nocturnal insects every night.

How can we make public lighting more accommodating to natural wildlife without disregarding pedestrians and road users?
Semi-Finals
Biodiversity
Ocean pollution is a major threat to marine life, with almost 1000 species of marine animals impacted by it, from sea turtles and sharks to small fish and plankton. Additionally, the risk of extinction for marine mammals is high, with around 37% of all marine mammal species at risk.

It is crucial to understand the influence of environmental variables on the biodiversity and abundance of species.

The intended outcome of this challenge is a scalable predictive model that provides insights into the future developments of endangered and invasive species in the Avencas Marine Protected Area. The solutions should consider the developments in species during the observation period and, ideally, be easily scalable to be used in other marine ecosystems with similar data.
Semi-Finals Challenge:
Avencas Marine Protected Area: Predict the Future of the Local Ecosystem and its Species
|
Predicting a safety score for women in Costa Rica by Urbanalytica
|
Avencas Marine Protected Area: Predict the Future of the Local Ecosystem and its Species
by
Cascais Municipality
|
To be announced
STAGE 2
Transportation & Mobility
According to TomTom Traffic Index, in 2019, the top-10 most congested cities had an average 61,6% congestion level. That is a lot of time spent in traffic. Despite that, a global transition to public transportation or soft mobility - getting around under your own steam (cycling, walking, roller-skating, etc.) - is still slower than the planet wishes. A Eurostat study shows that In the European Union, in 2018, public transportation represented only 19% of inland passenger transport.

Public transportation and soft mobility are two solutions for increasingly crowded roads and a greener future. How can we make these systems more efficient and attractive? Could soft mobility get better results?

There are now 600 fleets of shared e-scooters in Europe across more than 300 urban areas in 26 countries, according to the ZAG Daily.
STAGE 2 CHALLENGES:
Optimization of public transport routes during road interruptions by Cascais Municipality
|
Winning solution
by Moons of Jupyter
Predicting the flow of people for public transportation improvements by Porto Digital and Porto Municipality
|
Winning solution
by Green@Ces
Optimization of soft-mobility drop-off points by Porto Digital and Porto Municipality
|
1st PHASE
Mobility
Over the last 40 years, 300,000 individuals have moved from the City of Lisbon to its outskirts in the metropolitan area. As a result, public transport journeys within the city dropped from 46% to 22% in 2017.

With public transport usage decreasing and car usage increasing, it's crucial to analyze mobile device data to determine the main mobility flows and understand commuting patterns.

The intended outcome of this challenge is a better understanding and visualization of how people move between grids during rush hours. Teams are expected to present a model that can predict those movements and identify potential interventions to improve the commuting experience of people in Lisbon and favor sustainable modes of mobility.
STAGE 1 CHALLENGES:
Determining The Main Mobility Flows in the City of Lisbon Based on Mobile Device Data
by
LxDataLab Lisbon
|
Winning solution
by The Bayes Bunch
World Data League - a competition for data scientists
World Data League
©Copyright 2023
World Data League on IRCAI's Top 100