INSTITUTIONAL DIGITAL REPOSITORY

Multi-task deep learning for predicting poverty from satellite images

Show simple item record

dc.contributor.author Pandey, S.M.
dc.contributor.author Agarwal, T.
dc.contributor.author Krishnan, N.C.
dc.date.accessioned 2019-05-20T15:31:11Z
dc.date.available 2019-05-20T15:31:11Z
dc.date.issued 2019-05-20
dc.identifier.uri http://localhost:8080/xmlui/handle/123456789/1266
dc.description.abstract Estimating economic and developmental parameters such as poverty levels of a region from satellite imagery is a challenging problem that has many applications. We propose a two step approach to predict poverty in a rural region from satellite imagery. First, we engineer a multi-task fully convolutional deep network for simultaneously predicting the material of roof, source of lighting and source of drinking water from satellite images. Second, we use the predicted developmental statistics to estimate poverty. Using full-size satellite imagery as input, and without pre-trained weights, our models are able to learn meaningful features including roads, water bodies and farm lands, and achieve a performance that is close to the optimum. In addition to speeding up the training process, the multi-task fully convolutional model is able to discern task specific and independent feature representations en_US
dc.language.iso en_US en_US
dc.title Multi-task deep learning for predicting poverty from satellite images en_US
dc.type Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account