A convolutional neural network approach to predict non‐permissive environments from moderate‐resolution imagery

Abstract

Convolutional neural networks (CNNs) trained with satellite imagery have been successfully used to generate measures of development indicators, such as poverty, in developing nations. This article explores a CNN‐based approach leveraging Landsat 8 imagery to predict locations of conflict‐related deaths. Using Nigeria as a case study, we use the Armed Conflict Location & Event Data (ACLED) dataset to identify locations of conflict events that did or did not result in a death. Imagery for each location is used as an input to train a CNN to distinguish fatal from non‐fatal events. Using 2014 imagery, we are able to predict the result of conflict events in the following year (2015) with 80% accuracy. While our approach does not replace the need for causal studies into the drivers of conflict death, it provides a low‐cost solution to prediction that requires only publicly available imagery to implement. Findings suggest that the information contained in moderate‐resolution imagery can be used to predict the likelihood of a death due to conflict at a given location in Nigeria the following year, and that CNN‐based methods of estimating development‐related indicators may be effective in applications beyond those explored in the literature.

Deep learning fusion of satellite and social information to estimate human migratory flows

“…In the cases where ancillary data are used alongside imagery in a prediction (i.e., metadata providing the location of a cellphone), the ancillary information is generally integrated only in the final affine layer [in the context of satellite imagery, see e.g., Babenko et al (2017), Burke et al (2021), Cadamuro et al (2018), Goodman et al (2020), Hu et al (2019), Jean et al (2016), Perez et al (2017), andTingzon et al (2019)]. In the broader literature, recent work has explored the integration of tabular data into the convolutional network itself, rather than only the final predictive layer(s).…”

“…With the growth of convolutional neural network‐based approaches to satellite imagery analysis, studies are now beginning to emerge which seek to quantify explicit attributes about geographic locations—that is, the income of a household (Babenko et al, 2017; Jean et al, 2016; Perez et al, 2017; Tingzon et al, 2019), likelihood of a conflict event (Goodman et al, 2020), population density (Hu et al, 2019; Tiecke et al, 2017), school education outcomes (Runfola et al, 2021), and continuous grades of road quality (Brewer et al, 2021; Cadamuro et al, 2018). Many of these studies have been in response to the critical lack of data on human well‐being in data‐scarce environments (Burke et al, 2021), specifically seeking to improve our ability to capture relationships in impoverished areas (Jean et al, 2016).…”

“…Many of these studies have been in response to the critical lack of data on human well‐being in data‐scarce environments (Burke et al, 2021), specifically seeking to improve our ability to capture relationships in impoverished areas (Jean et al, 2016). Among other contributions, this literature has established the value of transfer learning in overcoming the relatively small‐N of many socioeconomic datasets (Brewer et al, 2021; Goodman et al, 2020; Jean et al, 2016; Runfola et al, 2021).…”

Economic downturns and the Greek referendum of 2015: Evidence using night-time light data

“…In principle, the measurements are taken every 24 h. Subsequently, the measurements are processed and aggregated to generate a yearly average. For the analysis, we obtained the processed data from Goodman et al. (2016) that were aggregated to the average NTL at the municipality level ( N = 322).…”

Tracking the industrial growth of modern China with high-resolution panchromatic imagery: A sequential convolutional approach

“…Satellite imagery analysis using deep learning methods, specifically convolutional neural networks (CNNs), has grown in popularity since 2012, with uses extending into the estimation of population [1], wealth [2], poverty [3], conflict [4], migration [5], education [6], and infrastructure [7], among other applications [8,9,10,11]. These techniques have broadly illustrated that harnessing satellites to remotely track development over time in otherwise data sparse regions is a potentially effective strategy [12].…”