Predicting socioeconomic indicators using transfer learning on imagery data: an application in Brazil

Castro, Diego A; López, Mariano Jiménez

doi:10.1007/s10708-022-10618-3

Cited by 10 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the lack of traditional data collection methods, it has been proposed to use alternative data sources, such as satellite images. The use of satellite images has proven to be a cost-effective means of obtaining real-time data access in countries where data is inaccessible due to social, environmental, or economic problems [2][3][4] . Satellite images have been used in applications across various domains, including environmental science and conservation for deforestation monitoring 5 , as well as in public health for measuring food security indices 6 , detecting poverty 7,8 and predicting climate-sensitive diseases like dengue 9,10 , or malaria 11 These applications are especially valuable in LMIC with limited resources, benefiting up to 128 economies and public health in the process [12][13][14] .…”

Section: Introductionmentioning

confidence: 99%

A multimodal framework for extraction and fusion of satellite images and public health data

Moukheiber,

Restrepo,

Cajas

et al. 2024

Sci Data

View full text Add to dashboard Cite

In low- and middle-income countries, the substantial costs associated with traditional data collection pose an obstacle to facilitating decision-making in the field of public health. Satellite imagery offers a potential solution, but the image extraction and analysis can be costly and requires specialized expertise. We introduce SatelliteBench, a scalable framework for satellite image extraction and vector embeddings generation. We also propose a novel multimodal fusion pipeline that utilizes a series of satellite imagery and metadata. The framework was evaluated generating a dataset with a collection of 12,636 images and embeddings accompanied by comprehensive metadata, from 81 municipalities in Colombia between 2016 and 2018. The dataset was then evaluated in 3 tasks: including dengue case prediction, poverty assessment, and access to education. The performance showcases the versatility and practicality of SatelliteBench, offering a reproducible, accessible and open tool to enhance decision-making in public health.

show abstract

Section: Introductionmentioning

confidence: 99%

A multimodal framework for extraction and fusion of satellite images and public health data

Moukheiber,

Restrepo,

Cajas

et al. 2024

Sci Data

View full text Add to dashboard Cite

show abstract

“…In a seminal study, Jean et al [2] [3] extended this work and showed how to fine-tune a deep Convolutional Neural Network (CNN), pre-trained on the ImageNet data, to predict poverty levels from high-resolution daytime satellite images in sub-Saharan Africa. This paper has been followed by many studies, see [4] for a review. However, despite the successes of this approach, the results have yet to be employed for policy decisions.…”

Section: Introductionmentioning

confidence: 99%

Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks

Sarmadi,

Rögnvaldsson,

Carlsson

et al. 2023

2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

Deep convolutional neural networks (CNNs) have been shown to predict poverty and development indicators from satellite images with surprising accuracy. This paper presents a first attempt at analyzing the CNNs responses in detail and explaining the basis for the predictions. The CNN model, while trained on relatively low resolution day-and night-time satellite images, is able to outperform human subjects who look at high-resolution images in ranking the Wealth Index categories. Multiple explainability experiments performed on the model indicate the importance of the sizes of the objects, pixel colors in the image, and provide a visualization of the importance of different structures in input images. A visualization is also provided of type images that maximize the network prediction of Wealth Index, which provides clues on what the CNN prediction is based on.

show abstract

“… Castro et al. 59 2022 First, VGG16 CNN (transfer learning). Second, linear regression (combination of ridge and lasso).…”

Section: Introductionmentioning

confidence: 99%

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

Hall

Ohlsson²,

Rögnvaldsson³

2022

Patterns

View full text Add to dashboard Cite

Predicting socioeconomic indicators using transfer learning on imagery data: an application in Brazil

Abstract: considerably different, results are consistent with the literature and encouraging as it is a first analysis of its kind for Brazil.

Cited by 10 publications

References 39 publications

A multimodal framework for extraction and fusion of satellite images and public health data

A multimodal framework for extraction and fusion of satellite images and public health data

Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks

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

Contact Info

Product

Resources

About