Detailed Program (22nd Oct, 2023, Teaching and Learning - LG03)(All times in BST)
Here is the link to attend the workshop virtually:Zoom
9:00-9:10 AM
Opening remarks by InfoWild'23 Workshop Organizers
9:10-10:30 AM
President, BrightWorld Labs
Topic: What do scientists researching wildlife conservation have in common with realtors?
Abstract: We cannot emphasize enough the value of location in wildlife conservation. Location can be
explicit when you use GPS and other location tagging to track wildlife. And location can be implicit
when the public, media, and policymakers talk about places and other things we can tie to
location.
The scientific community has produced valuable insights by analyzing the movement of people,
wildlife, goods, and more, where the data is precise movement trajectories. However, research
should focus more on geographic movement from text descriptions. Descriptions of things moving
include rich contextual information that describes what is moving, when, why, and how it moves.
There are many challenges to utilizing this source, like location ambiguities and fusion with other
data sources. But, combining Natural Language Processing (NLP), Information Retrieval (IR), and
Machine Learning with visual analytics will help us better utilize this source to monitor and analyze
wildlife for conservation.
Finally, my most important messages from this talk will be 1) geospatial analysis is vital to all key
topics in knowledge extraction and management for wildlife conservation and 2) the geospatial
industry unnecessarily complicates geospatial analysis, and many scientists outside the field
would benefit from knowing it is simply not that unique.
10:30-11:00 AM
Break
11:00-11:20 AM
Paper Presentation: 20min, QA: 10min
Title: A Flexible and Scalable Approach for Collecting Wildlife Advertisements on the Web
Authors: Juliana Barbosa, Juliana Freire and Sunandan Chakraborty
Abstract: Wildlife traffickers are increasingly carrying out their activities in
cyberspace. As they advertise and sell wildlife products in online
marketplaces, they leave digital traces of their activity. This creates
a new opportunity: by analyzing these traces, we can obtain insights
into how trafficking networks work as well as how they can be
disrupted. However, collecting such information is difficult. Online
marketplaces sell a very large number of products and identifying
ads that actually involve wildlife is a complex task that is hard to
automate. Furthermore, given that the volume of data is staggering,
we need scalable mechanisms to acquire, filter, and store the ads,
as well as to make them available for analysis. In this paper, we
present a new approach to collect wildlife trafficking data at scale.
We propose a data collection pipeline that combines scoped crawlers
for data discovery and acquisition with foundational models and
machine learning classifiers to identify relevant ads. We describe
a dataset we created using this pipeline which is, to the best of
our knowledge, the largest of its kind: it contains almost a million
ads obtained from 41 marketplaces, covering 235 species and 20
languages.
Camera Ready Version of the paper
11:30 AM-12:30 PM
Talk and Discussion on the topic
Analysis of Elephant Movement in Sub-Saharan Africa: Ecological, Climatic, and Conservation Perspectives
Authors: Matthew Hines, Gregory Glatzer,Shreya Ghosh and Prasenjit Mitra. ACM SIGCAS/SIGCHI Conference on Computing and Sustainable Societies (COMPASS '23)
Abstract: The interaction between elephants and their environment has profound implications for both ecology and conservation strategies.
This study presents an analytical approach to decipher the intricate
patterns of elephant movement in Sub-Saharan Africa, concentrating on key ecological drivers such as seasonal variations and rainfall
patterns. Despite the complexities surrounding these influential
factors, our analysis provides a holistic view of elephant migratory behavior in the context of the dynamic African landscape.
Our comprehensive approach enables us to predict the potential
impact of these ecological determinants on elephant migration, a
critical step in establishing informed conservation strategies. This
projection is particularly crucial given the impacts of global climate
change on seasonal and rainfall patterns, which could substantially
influence elephant movements in the future. The findings of our
work aim to not only advance the understanding of movement
ecology but also foster a sustainable coexistence of humans and
elephants in Sub-Saharan Africa. By predicting potential elephant
routes, our work can inform strategies to minimize human-elephant
conflict, effectively manage land use, and enhance anti-poaching
efforts. This research underscores the importance of integrating
movement ecology and climatic variables for effective wildlife
management and conservation planning.
Link of the paper
12:30-1:30 PM
Lunch Break
1:30-2:30 PM
Keynote talk by Dr. Thomas Muller
Goethe University and Senckenberg Biodiversity and Climate Research Centre, Frankfurt (Germany)
Topic: Animal Movement and Conservation
2:30-2:50 PM
Paper Presentation: 20min, QA: 10min
Title: WildGEN: Long-horizon Trajectory Generation for Wildlife
Authors: Ali Al-Lawati, Elsayed Eshra and Prasenjit Mitra
Abstract: Trajectory generation is an important concern in pedestrian, vehicle, and wildlife movement studies. Generated trajectories help
enrich the training corpus in relation to deep learning applications,
and may be used to facilitate simulation tasks. This is especially
significant in the wildlife domain, where the cost of obtaining addi-
tional real data can be prohibitively expensive, time-consuming, and
bear ethical considerations. In this paper, we introduce WildGEN: a
conceptual framework that addresses this challenge by employing a
Variational Auto-encoders (VAEs) based method for the acquisition
of movement characteristics exhibited by wild geese over a long
horizon using a sparse set of truth samples. A subsequent post-
processing step of the generated trajectories is performed based on
smoothing filters to reduce excessive wandering. Our evaluation is
conducted through visual inspection and the computation of the
Hausdorff distance between the generated and real trajectories. In
addition, we utilize the Pearson Correlation Coefficient as a way to
measure how realistic the trajectories are based on the similarity of
clusters evaluated on the generated and real trajectories.
Camera Ready Version of the paper
3:00-3:30 PM
Break
3:30-4:15 PM
Keynote talk by Dr. Bistra Dilkina
Dr. Allen and Charlotte Ginsburg Early Career Chair in Computer Science and Associate Professor of Computer Science, University of Southern California.
Topic: AI for Wildlife Conservation
4:15-5:00 PM
Keynote talk by Christopher Yeh
Computing and Mathematical Sciences, California Institute of Technology, USA
Topic: Shared Challenges across Machine Learning for Sustainability
Abstract: Machine learning techniques have demonstrated significant advancements across a wide range of sustainability issues, ranging from poverty mapping to energy systems and wildlife conservation. While the domains are distinct, the underlying machine learning problems have a number of shared challenges modeling challenges. In this talk, I will describe how the problems of datasets curation, uncertainty quantification, decision-focused learning, and active learning are both shared and intertwined. By understanding and addressing these shared challenges, we can maximize the potential of machine learning in tackling pressing global sustainability issues.
5:00-5:30 PM
Panel Discussion and Concluding Remarks
Discussion Topic: "What is the next step?"
Concluding Remarks by Dr. Prasenjit Mitra
Future directions in the field of AI-driven wildlife conservation: (1)
Can we discern and interpret spatio-temporal patterns in largescale human activity data related to the frequency and intensity of
human-wildlife interactions and conflicts? (2) How can we quantify and predict the impact of various sound and light pollution
types on wildlife behavior and visitor experiences in protected areas? (3) To what extent do human-induced habitat modifications,
such as land-use changes and settlements, impact the signature
mobility or activity patterns of wildlife? Can we develop an AI model to quantify these effects? (4) How can we leverage AI-driven
spatio-temporal data analysis to enhance protection strategies for
endangered species? (5) Can we utilize spatio-temporal data analysis to predict wildlife-human conflicts and devise risk mitigation
strategies? (6) What are the potential obstacles and limitations
when employing AI for spatio-temporal data analysis in wildlife
conservation? (7) How can we apply AI-driven spatio-temporal
analysis to understand the effects of climate change on wildlife migration patterns? (8) Can AI-driven spatio-temporal data analysis
aid in disease surveillance within wildlife populations? (9) How
do we ensure ethical use of AI and uphold animal privacy rights
in wildlife conservation?