Search

Abstract: Social data from census and household surveys provide key information for monitoring the status of populations, but the data utility can be limited by temporal gaps between surveys. Recent studies have pointed to the potential for remotely sensed satellite sensor data to be used as proxies for social data. Such an approach could provide valuable information for the monitoring of populations between enumeration periods. Field observations in Assam, north-east India suggested that socioeconomic conditions could be related to patterns in the type and abundance of local land cover dynamics prompting the development of a more formal approach. This research tested if environmental data derived from remotely sensed satellite sensor data could be used to predict a socioeconomic outcome using a generalised autoregressive error (GARerr) model. The proportion of female literacy from the 2001 Indian National Census was used as an indicator of socioeconomic conditions. A significant positive correlation was found with woodland and a significant negative correlation with winter cropland (i.e., additional cropping beyond the normal cropping season). The dependence of female literacy on distance to nearest road was very small. The GARerr model reduced residual spatial autocorrelation and revealed that the logistic regression model over-estimated the significance of the explanatory covariates. The results are promising, while also revealing the complexities of population–environment interactions in rural, developing world contexts. Further research should explore the prediction of socioeconomic conditions using fine spatial resolution satellite sensor data and methods that can account for such complexities. [Copyright &y& Elsevier]

Summary This article presents results from an investigation of the relationships between welfare and geographic metrics from over 14,000 villages in Assam, India. Geographic metrics accounted for 61% of the variation in the lowest welfare quintile and 57% in the highest welfare quintile. Travel time to market towns, percentage of a village covered with woodland, and percentage of a village covered with winter crop were significantly related to welfare. These results support findings in the literature across a range of different developing countries. Model accuracy is unprecedented considering that the majority of geographic metrics were derived from remotely sensed data. [ABSTRACT FROM AUTHOR]

There is increasing interest in leveraging Earth Observation (EO) and geospatial data to predict and map aspects of socioeconomic conditions to support survey and census activities. This is particularly relevant for the frequent monitoring required to assess progress towards the UNs' Sustainable Development Goals (SDGs). The Sundarban Biosphere Reserve (SBR) is a region of international ecological importance, containing the Indian portion of the world's largest mangrove forest. The region is densely populated and home to over 4.4 million people, many living in chronic poverty with a strong dependence on nature-based rural livelihoods. Such livelihoods are vulnerable to frequent natural hazards including cyclone landfall and storm surges. In this study we examine associations between environmental variables derived from EO and geospatial data with a village level multidimensional poverty metric using random forest machine learning, to provide evidence in support of policy formulation in the field of poverty reduction. We find that environmental variables can predict up to 78% of the relative distribution of the poorest villages within the SBR. Exposure to cyclone hazard was the most important variable for prediction of poverty. The poorest villages were associated with relatively small areas of rural settlement (<∼30%), large areas of agricultural land (>∼50%) and moderate to high cyclone hazard. The poorest villages were also associated with less productive agricultural land than the wealthiest. Analysis suggests villages with access to more diverse livelihood options, and a smaller dependence on agriculture may be more resilient to cyclone hazard. This study contributes to the understanding of poverty-environment dynamics within Low-and middle-income countries and the associations found can inform policy linked to socio-environmental scenarios within the SBR and potentially support monitoring of work towards SDG1 (No Poverty) across the region. • Earth Observation and geospatial data could support monitoring of development. • We examine association between poverty and the environment with machine learning. • Cyclone hazard was the most important variable for prediction of poverty in the SBR. • The poorest villages were predicted with up to 78% accuracy. • Results can inform policy linked to socio-environmental scenarios in the SBR. [ABSTRACT FROM AUTHOR]