Dataset Information

A human-machine collaborative approach measures economic development using satellite imagery.

ABSTRACT: Machine learning approaches using satellite imagery are providing accessible ways to infer socioeconomic measures without visiting a region. However, many algorithms require integration of ground-truth data, while regional data are scarce or even absent in many countries. Here we present our human-machine collaborative model which predicts grid-level economic development using publicly available satellite imagery and lightweight subjective ranking annotation without any ground data. We applied the model to North Korea and produced fine-grained predictions of economic development for the nation where data is not readily available. Our model suggests substantial development in the country's capital and areas with state-led development projects in recent years. We showed the broad applicability of our model by examining five of the least developed countries in Asia, covering 400,000 grids. Our method can both yield highly granular economic information on hard-to-visit and low-resource regions and can potentially guide sustainable development programs.

SUBMITTER: Ahn D

PROVIDER: S-EPMC10603027 | biostudies-literature | 2023 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A human-machine collaborative approach measures economic development using satellite imagery.

Ahn Donghyun D Yang Jeasurk J Cha Meeyoung M Yang Hyunjoo H Kim Jihee J Park Sangyoon S Han Sungwon S Lee Eunji E Lee Susang S Park Sungwon S

Nature communications 20231026 1

Machine learning approaches using satellite imagery are providing accessible ways to infer socioeconomic measures without visiting a region. However, many algorithms require integration of ground-truth data, while regional data are scarce or even absent in many countries. Here we present our human-machine collaborative model which predicts grid-level economic development using publicly available satellite imagery and lightweight subjective ranking annotation without any ground data. We applied t ...[more]

PMID: 37884499

Similar Datasets

Project description:IntroductionNoncommunicable diseases (NCDs) are the leading cause of morbidity and mortality worldwide, accounting for 74% of deaths annually. Satellite imagery provides previously unattainable data about factors related to NCDs that overcome limitations of traditional, non-satellite-derived environmental data, such as subjectivity and requirements of a smaller geographic area of focus. This systematic literature review determined how satellite imagery has been used to address the top NCDs in the world, including cardiovascular diseases, cancers, chronic respiratory diseases, and diabetes.MethodsA literature search was performed using PubMed (including MEDLINE), CINAHL, Web of Science, Science Direct, Green FILE, and Engineering Village for articles published through June 6, 2023. Quantitative, qualitative, and mixed-methods peer-reviewed studies about satellite imagery in the context of the top NCDs (cancer, cardiovascular disease, chronic respiratory disease, and diabetes) were included. Articles were assessed for quality using the criteria from the Oxford Centre for Evidence-Based Medicine.ResultsA total of 43 studies were included, including 5 prospective comparative cohort trials, 22 retrospective cohort studies, and 16 cross-sectional studies. Country economies of the included studies were 72% high-income, 16% upper-middle-income, 9% lower-middle-income, and 0% low-income. One study was global. 93% of the studies found an association between the satellite data and NCD outcome(s). A variety of methods were used to extract satellite data, with the main methods being using publicly available algorithms (79.1%), preprocessing techniques (34.9%), external resource tools (30.2%) and publicly available models (13.9%). All four NCD types examined appeared in at least 20% of the studies.ConclusionResearchers have demonstrated they can successfully use satellite imagery data to investigate the world's top NCDs. However, given the rapid increase in satellite technology and artificial intelligence, much of satellite imagery used to address NCDs remains largely untapped. In particular, with most existing studies focusing on high-income countries, future research should use satellite data, to overcome limitations of traditional data, from lower-income countries which have a greater burden of morbidity and mortality from NCDs. Furthermore, creating and refining effective methods to extract and process satellite data may facilitate satellite data's use among scientists studying NCDs worldwide.

Project description:This study aims to develop a software framework for predicting aridity using vegetation indices (VI) from LANDSAT 8 OLI images. VI data are predicted using machine learning (ml): Random Forest (RF) and Correlation and Regression Trees (CART). Comparison of prediction using Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest neighbors (k-nn) and Multivariate Adaptive Regression Spline (MARS). Prediction results are interpolated using Inverse Distance Weight (IDW). This study was conducted in stages: (1) Image preprocessing; (2) calculating numerical data extracted from the LANDSAT band imagery using vegetation indices; (3) analyzing correlation coefficients between VI; (4) prediction using RF and CART; (5) comparing performances between RF and CART using ANN, SVM, k-nn, and MARS; (6) testing the accuracy of prediction using Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE); (7) interpolating with IDW. Correlation coefficient of VI data shows a positive correlation, the lowest r (0.07) and the highest r (0.98). The experiments show that the RF and CART algorithms have efficiency and effectivity in determining the aridity areas better than the ANN, SVM, k-nn, and MARS algorithm. RF has a difference between the predicted results and 1.04% survey data MAPE and the smallest value close to zero is 0.05 MSE. CART has a difference between the predicted results and 1.05% survey data MAPE and the smallest value approaching to zero which is 0.05 MSE. The prediction results of VI show that in 2020 most of the study areas were low vegetation areas with the Normalized Difference Vegetation Index (NDVI) < 0.21, had an indication of drought with the Vegetation Health Index (VHI) < 31.10, had a Vegetation Condition Index (VCI) in some areas between 35%-50% (moderate drought) and < 35% (high drought). The Burn Area Index (dBAI) values are between -3, 971 and -2,376 that show the areas have a low fire risk, and index values are between -0, 208 and -0,412 that show the areas are starting vegetation growth. The result of this study shows that the machine learning algorithms is an accurate and stable algorithm in predicting the risks of drought and land fire based on the VI data extracted from the LANDSAT 8 OLL imagery. The VI data contain the record of vegetation condition and its environment, including humidity, temperatures, and the environmental vegetation health.

Dataset Information

A human-machine collaborative approach measures economic development using satellite imagery.

Publications

A human-machine collaborative approach measures economic development using satellite imagery.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets