Multi-task deep learning for predicting poverty from satellite images

S Pandey, T Agarwal, NC Krishnan - … of the AAAI Conference on Artificial …, 2018 - ojs.aaai.org
… 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

Semi-supervised multitask learning on multispectral satellite images using wasserstein generative adversarial networks (gans) for predicting poverty

A Perez, S Ganguli, S Ermon, G Azzari, M Burke… - arXiv preprint arXiv …, 2019 - arxiv.org
… evidence that multi-task learning improves generalization of machine learning models “by …
Combining satellite imagery and machine learning to predict poverty. Science, 2016. [22] …

Multi-source satellite imagery and point of interest data for poverty mapping in East Java, Indonesia: Machine learning and deep learning approaches

SR Putri, AW Wijayanto, S Pramana - Remote Sensing Applications …, 2023 - Elsevier
poverty estimation model development scenarios using machine learning and deep learning
… First, the model is constructed using multisource satellite imagery and geospatial point of …

Predicting food security outcomes using convolutional neural networks (cnns) for satellite tasking

S Ganguli, J Dunnmon, D Hau - arXiv preprint arXiv:1902.05433, 2019 - arxiv.org
satellite imagery and machine learning to predict poverty. … multitask learning on
multispectral satellite images using … networks (gans) for predicting poverty. arXiv preprint arXiv:…

Predicting city poverty using satellite imagery

S Piaggesi, L Gauvin, M Tizzoni… - Proceedings of the …, 2019 - openaccess.thecvf.com
… In this work we apply a machine learning approach similar to the one developed by Jean et
al. [16] for predicting economic outcomes in 5 African countries from satellite imagery, to the …

Predict Socio-Economic Status of an Area from Satellite Image Using Deep Learning

A Shetty, A Thorat, R Singru… - … on electronics and …, 2020 - ieeexplore.ieee.org
… for predicting poverty in rural regions of India from satellite … Initially, they train a multi-task
fully convolution model to predict … source of drinking water – from satellite imagery. Using only …

A review of explainable AI in the satellite data, deep machine learning, and human poverty domain

O Hall, M Ohlsson, T Rögnvaldsson - Patterns, 2022 - cell.com
… how they relate to the poverty, machine learning, and satellite imagery nexus. Our inclusion
… cover poverty/wealth prediction, using survey data as the basis for the ground truth poverty/…

Satellite image and machine learning based knowledge extraction in the poverty and welfare domain

O Hall, M Ohlsson, T Rögnvaldsson - arXiv preprint arXiv:2203.01068, 2022 - arxiv.org
… to the poverty, machine learning and satellite imagery nexus. Our … elements of explainable
machine learning (transparency, … Multi-task deep learning for predicting poverty from satellite

Using Convolutional Neural Networks on Satellite Images to Predict Poverty

A Okaidat, S Melhem, H Alenezi… - 2021 12th International …, 2021 - ieeexplore.ieee.org
… This work aims to use deep learning and transfer learning (ResNet50 and VGG16) to train
the model on satellite imagesMulti-task deep learning for predicting poverty from satellite

Geospatial Deep Learning for Estimating Socioeconomic Well-Being in Developing Regions: An Analysis of Burundi's Poverty Projection

D Durgamahanty, S Sriram, V Nivethitha… - … on Innovations in …, 2024 - Springer
… a two-step approach for predicting poverty using multispectral satellite imagery. Initially, they
… Krishnan NC (2018) Multi-task deep learning for predicting poverty from satellite images. In: …