Learning to Score Economic Development from Satellite Imagery

Han, Sungwon; Ahn, Dongchan; Park, Sung Won; Yang, Jeasurk; Susang, Lee,; Kim, Jihee; Yang, Hyunjoo; Park, Sangyoon; Cha, Meeyoung

doi:10.1145/3394486.3403347

Cited by 23 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Han, et al [25] in their work present a three step approach for judging the economic status of a region without having access to ground truth figures by using high resolution satellite images: (i) the man-made and natural objects in a satellite image are classified (segregated) into different collections by using a clustering framework, (ii) partial order graph of the collections identified in the previous step are developed, and, finally, (iii) a Convolutional Neural Network (CNN) based framework is used to sort each of the satellite images (grids) on the basis of the relative positioning of the collections. Eventually a score is assigned to each of the locations (satellite images), this score is indicative of the near real-time economic development of that corresponding location.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

ReGNL: Rapid Prediction of GDP during Disruptive Events using Nightlights

Musthyala¹,

Rudrajit²,

Hritish³

et al. 2022

Preprint

View full text Add to dashboard Cite

Policy makers often make decisions based on parameters such as GDP, unemployment rate, industrial output, etc. The primary methods to obtain or even estimate such information are resource intensive and time consuming. In order to make timely and well-informed decisions, it is imperative to be able to come up with proxies for these parameters which can be sampled quickly and efficiently, especially during disruptive events, like the COVID-19 pandemic. Recently, there has been a lot of focus on using remote sensing data for this purpose. The data has become cheaper to collect compared to surveys, and can be available in real time. In this work, we present Regional GDP NightLight (ReGNL), a neural network based model which is trained on a custom dataset of historical nightlights and GDP data along with the geographical coordinates of a place, and estimates the GDP of the place, given the other parameters. Taking the case of 50 US states, we find that ReGNL is disruption-agnostic and is able to predict the GDP for both normal years (2019) and for years with a disruptive event (2020). ReGNL outperforms timeseries ARIMA methods for prediction, even during the pandemic. Following from our findings, we make a case for building infrastructures to collect and make available granular data, especially in resource-poor geographies, so that these can be leveraged for policy making during disruptive events. CCS Concepts: • Computing methodologies → Neural networks; Supervised learning by regression; • Applied computing → Economics.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Off-late, nightlight has emerged as a convenient proxy used to ascertain economic activity of a region [17,25].…”

Section: Introductionmentioning

confidence: 99%

ReGNL: Rapid Prediction of GDP during Disruptive Events using Nightlights

Musthyala¹,

Rudrajit²,

Hritish³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Abitbol and Karsai [32] applied a CNN model to predict inhabited tiles' socioeconomic status and projected the class discriminative activation maps onto the original images, interpreting the estimation of wealth in terms of urban topology. To date, daytime imagery and deep neural networks have been widely applied to predict various socioeconomic indicators such as population [33][34][35], poverty distribution [15,18,36], and urbanization [6,37]. Despite the convenience and scalability, these studies depend largely on data-intensive CNNs and require large volumes of ground-truth labels to supervise the training process.…”

Section: Detection Of Economic-related Visual Patterns From Daytime Satellite Imagery Via Deep Learningmentioning

confidence: 99%

Nightlight as a Proxy of Economic Indicators: Fine-Grained GDP Inference around Chinese Mainland via Attention-Augmented CNN from Daytime Satellite Imagery

Liu

Bai

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

The official method of collecting county-level GDP values in the Chinese Mainland relies mainly on administrative reporting data and suffers from high costs of time, money, and human labor. To date, a series of studies have been conducted to generate fine-grained maps of socioeconomic indicators from the easily accessed remote sensing data and achieved satisfactory results. This paper proposes a transfer learning framework that regards nightlight intensities as a proxy of economic activity degrees to estimate county-level GDP around the Chinese Mainland. In the framework, paired daytime satellite images and nightlight intensity levels were applied to train a VGG-16 architecture, and the output features at a specific layer, after dimensional reduction and statistics calculation, were fed into a simple regressor to estimate county-level GDP. We trained the model with data of 2017 and utilized it to predict county-level GDP of 2018, achieving an R-squared of 0.71. Furthermore, the results of gradient visualization confirmed the validity of the proposed framework qualitatively. To the best of our knowledge, this is the first time that county-level GDP values around the Chinese Mainland have been estimated from both daytime and nighttime remote sensing data relying on attention-augmented CNN. We believe that our work will shed light on both the evolution of fine-grained socioeconomic surveys and the application of remote sensing data in economic research.

show abstract

“…Most recent methods proposed to extract urban land cover or buildings from remote sensing images [12,13,22] use deep learning techniques trained on large datasets to obtain per-pixel labels building or no building. While one could, in principle, obtain population estimates [14], or even socioeconomic indicators [34], directly in that raster format, it is usually transformed into a vector data to simplify its further use in Geographic Information Systems. Some works obtain vector outlines in post-processing, by polygonizing raster predictions [31], whereas others learn to produce vector outputs end-to-end [6,16], sometimes supported by specific shape priors for, e.g., rural buildings [36].…”

Section: Related Workmentioning

confidence: 99%

Mapping Vulnerable Populations with AI

Kellenberger,

Vargas-Muñoz,

Tuia

et al. 2021

Preprint

View full text Add to dashboard Cite

Humanitarian actions require accurate information to efficiently delegate support operations. Such information can be maps of building footprints, building functions, and population densities. While the access to this information is comparably easy in industrialized countries thanks to reliable census data and national geo-data infrastructures, this is not the case for developing countries, where that data is often incomplete or outdated. Building maps derived from remote sensing images may partially remedy this challenge in such countries, but are not always accurate due to different landscape configurations and lack of validation data. Even when they exist, building footprint layers usually do not reveal more fine-grained building properties, such as the number of stories or the building's function (e.g., office, residential, school, etc.). In this project we aim to automate building footprint and function mapping using heterogeneous data sources. In a first step, we intend to delineate buildings from satellite data, using deep learning models for semantic image segmentation. Building functions shall be retrieved by parsing social media data like for instance tweets, as well as ground-based imagery, to automatically identify different buildings functions and retrieve further information such as the number of building stories. Building maps augmented with those additional attributes make it possible to derive more accurate population density maps, needed to support the targeted provision of humanitarian aid.

show abstract

Learning to Score Economic Development from Satellite Imagery

Cited by 23 publications

References 23 publications

ReGNL: Rapid Prediction of GDP during Disruptive Events using Nightlights

ReGNL: Rapid Prediction of GDP during Disruptive Events using Nightlights

Nightlight as a Proxy of Economic Indicators: Fine-Grained GDP Inference around Chinese Mainland via Attention-Augmented CNN from Daytime Satellite Imagery

Mapping Vulnerable Populations with AI

Contact Info

Product

Resources

About