An official website of the United States government
This study investigates the application of explainable AI (XAI) techniques to understand the deep learning models used for predicting urban conflict from satellite imagery. First, a ResNet18 convolutional neural network achieved 89% accuracy in distinguishing riot and non-riot urban areas. Using the Score-CAM technique, regions critical to the model’s predictions were identified, and masking these areas caused a 20.9% drop in the classification accuracy, highlighting their importance. However, Score-CAM’s ability to consistently localize key features was found to be limited, particularly in complex, multi-object urban environments. Analysis revealed minimal alignment between the model-identified features and traditional land use metrics, suggesting that deep learning captures unique patterns not represented in existing GIS datasets. These findings underscore the potential of deep learning to uncover previously unrecognized socio-spatial dynamics while revealing the need for improved interpretability methods. This work sets the stage for future research to enhance explainable AI techniques, bridging the gap between model performance and interpretability and advancing our understanding of urban conflict drivers.
more »
« less
Predicting Protests and Riots in Urban Environments With Satellite Imagery and Deep Learning
Conflict, manifesting as riots and protests, is a common occurrence in urban environments worldwide. Understanding their likely locations is crucial to policymakers, who may (for example) seek to provide overseas travelers with guidance on safe areas, or local policymakers with the ability to pre-position medical aid or police presences to mediate negative impacts associated with riot events. Past efforts to forecast these events have focused on the use of news and social media, restricting applicability to areas with available data. This study utilizes a ResNet convolutional neural network and high-resolution satellite imagery to estimate the spatial distribution of riots or protests within urban environments. At a global scale (N = 18,631 conflict events), by training our model to understand relationships between urban form and riot events, we are able to predict the likelihood that a given urban area will experience a riot or protest with accuracy as high as 97%. This research has the potential to improve our ability to forecast and understand the relationship between urban form and conflict events, even in data-sparse regions.
more »
« less
- Award ID(s):
- 2317591
- PAR ID:
- 10537813
- Publisher / Repository:
- Wiley
- Date Published:
- Journal Name:
- Transactions in GIS
- ISSN:
- 1361-1682
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Water insecurity may precipitate interpersonal conflict, although no studies to date have rigorously examined these relationships. We examined relationships between household demographics, water insecurity, regional conflict, and interpersonal conflict over water. Using survey data from eight sub-Saharan African countries, we found that interpersonal conflict within and outside the home is associated with multiple domains of water insecurity, particularly accessibility. Furthermore, we found that higher levels of remote violence and protests are associated with greater within household conflict, whereas riots and violent armed conflict are associated with greater conflict between neighbors. Our findings expand upon the current literature by examining factors affecting interpersonal conflict over water, which may become increasingly important as precipitation patterns and land temperatures change in this region.more » « less
-
We call for a relational approach to constructing protest event data from news sources to provide tools for detecting and correcting errors and for capturing the relations among events and between events and the texts describing them. We address two problems with most protest event datasets: (1) inconsistencies and errors in identifying events and (2) disconnect between data structures and what is known about how protests and media accounts of protests are produced. Relational data structures can capture the theoretically important structuring of events into campaigns and episodes and media attention cascades and cycles. Relational data structures support richer theorizing about the interplay of protests and their representations in news media discourses. We present preliminary illustrative data about Black protests from these new procedures to demonstrate the value of this approach.more » « less
-
Governmental and nongovernmental organizations have increasingly relied on early-warning systems of conflict to support their decisionmaking. Predictions of war intensity as probability distributions prove closer to what policymakers need than point estimates, as they encompass useful representations of both the most likely outcome and the lower-probability risk that conflicts escalate catastrophically. Point-estimate predictions, by contrast, fail to represent the inherent uncertainty in the distribution of conflict fatalities. Yet, current early warning systems are preponderantly focused on providing point estimates, while efforts to forecast conflict fatalities as a probability distribution remain sparse. Building on the predecessor VIEWS competition, we organize a prediction challenge to encourage endeavours in this direction. We invite researchers across multiple disciplinary fields, from conflict studies to computer science, to forecast the number of fatalities in state-based armed conflicts, in the form of the UCDP ‘best’ estimates aggregated to two units of analysis (country-months and PRIO-GRID-months), with estimates of uncertainty. This article introduces the goal and motivation behind the prediction challenge, presents a set of evaluation metrics to assess the performance of the forecasting models, describes the benchmark models which the contributions are evaluated against, and summarizes the salient features of the submitted contributions.more » « less
-
Protest event analysis is an important method for the study of collective action and social movements and typically draws on traditional media reports as the data source. We introduce collective action from social media (CASM)—a system that uses convolutional neural networks on image data and recurrent neural networks with long short-term memory on text data in a two-stage classifier to identify social media posts about offline collective action. We implement CASM on Chinese social media data and identify more than 100,000 collective action events from 2010 to 2017 (CASM-China). We evaluate the performance of CASM through cross-validation, out-of-sample validation, and comparisons with other protest data sets. We assess the effect of online censorship and find it does not substantially limit our identification of events. Compared to other protest data sets, CASM-China identifies relatively more rural, land-related protests and relatively few collective action events related to ethnic and religious conflict.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
