Spatiotemporal Prediction of Conflict Fatality Risk Using Convolutional Neural Networks and Satellite Imagery
Open Access
- 13 September 2024
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 16 (18) , 3411
Abstract
As both satellite imagery and image-based machine learning methods continue to improve and become more accessible, they are being utilized in an increasing number of sectors and applications. Recent applications using convolutional neural networks (CNNs) and satellite imagery include estimating socioeconomic and development indicators such as poverty, road quality, and conflict. This article builds on existing work leveraging satellite imagery and machine learning for estimation or prediction, to explore the potential to extend these methods temporally. Using Landsat 8 imagery and data from the Armed Conflict Location & Event Data Project (ACLED) we produce subnational predictions of the risk of conflict fatalities in Nigeria during 2015, 2017, and 2019 using distinct models trained on both yearly and six-month windows of data from the preceding year. We find that predictions at conflict sites leveraging imagery from the preceding year for training can predict conflict fatalities in the following year with an area under the receiver operating characteristic curve (AUC) of over 75% on average. While models consistently outperform a baseline comparison, and performance in individual periods can be strong (AUC > 80%), changes based on ground conditions such as the geographic scope of conflict can degrade performance in subsequent periods. In addition, we find that training models using an entire year of data slightly outperform models using only six months of data. Overall, the findings suggest CNN-based methods are moderately effective at detecting features in Landsat satellite imagery associated with the risk of fatalities from conflict events across time periods.Keywords
Funding Information
- USAID Global Development Lab (AID-OAA-A-12-00096)
This publication has 69 references indexed in Scilit:
- Conflict forecasting using remote sensing data: An application to the Syrian civil warInternational Journal of Forecasting, 2023
- pyShore: A deep learning toolkit for shoreline structure mapping with high-resolution orthographic imagery and convolutional neural networksComputers & Geosciences, 2023
- Changes in agricultural and grazing land, and insights for mitigating farmer-herder conflict in West AfricaLandscape and Urban Planning, 2022
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019
- Assessing the causal impact of Chinese aid on vegetative land cover in Burundi and Rwanda under conditions of spatial imprecisionDevelopment Engineering, 2019
- GeoQuery: Integrating HPC systems and public web-based geospatial data toolsComputers & Geosciences, 2019
- A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classificationISPRS Journal of Photogrammetry and Remote Sensing, 2018
- A new image classification method using CNN transfer learning and web data augmentationExpert Systems with Applications, 2018
- Titling community land to prevent deforestation: An evaluation of a best-case program in Morona-Santiago, EcuadorGlobal Environmental Change, 2015
- Pattern recognition by affine moment invariantsPattern Recognition, 1993