Using Neural Networks to Predict Microspatial Economic Growth

Khachiyan, Arman; Thomas, Anthony; Zhou, Huye; Hanson, Gordon H.; Cloninger, Alex; Rosing, Tajana; Khandelwal, Ankur

doi:10.1257/aeri.20210422

Cited by 7 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, the proliferation in data availability and computational power can give rise to data-driven approaches that are not constrained by theoretical frameworks. An example is in modeling highresolution income and population changes in the U.S. using deep learning approaches applied to daytime satellite imagery to achieve predictive power well beyond previous models (Khachiyan et al 2022). Heterogeneous spatial interactions may be incorporated in a variety of ways into these models (Alexander et al 2017, Prestele et al 2017, Plantinga 2021.…”

Section: Heterogeneity At Individual (Field Agent) Scalesmentioning

confidence: 99%

Accounting for spatial economic interactions at local and meso scales in integrated assessment model (IAM) frameworks: challenges and recent progress

Cultice

Irwin

Jones

2023

Environ. Res. Lett.

View full text Add to dashboard Cite

The scientific and policy needs to assess and manage climate change impacts have spawned new coupled, multi-scale integrated assessment model (IAM) frameworks that link global climate and economic processes with high-resolution data and models of human-environmental systems at local and meso scales (Fisher-Vanden and Weyant 2020). A central challenge is in accounting for the fundamental interdependence of people, firms, and economic activities across space at multiple scales. This requires modeling approaches that can incorporate the relevant spatial details at each scale while also ensure consistency with spatially varying feedbacks and interactions across scales—a condition economists refer to as spatial equilibrium. In this paper, we provide an overview of how economists think about and model spatial interactions, particularly those at the local level. We describe challenges and recent progress in accounting for greater spatial heterogeneity at individual (field, agent) scales and incorporating heterogeneous spatial interactions and dynamics into consistent IAM frameworks. We conclude that the most notable progress is in advancing global IAMs with spatial heterogeneity and dynamics embedded in spatial equilibrium frameworks and that less progress has been made in incorporating features of spatial equilibrium into highly detailed multi-scale IAMs.

show abstract

Section: Heterogeneity At Individual (Field Agent) Scalesmentioning

confidence: 99%

Accounting for spatial economic interactions at local and meso scales in integrated assessment model (IAM) frameworks: challenges and recent progress

Cultice

Irwin

Jones

2023

Environ. Res. Lett.

View full text Add to dashboard Cite

show abstract

“…However, self-reported changes are subject to recall error and may only capture major changes in assets. Meanwhile, Khachiyan et al [36] look at variation across census blocks in the USA and find that a CNN trained on daytime imagery predicted half of the change in population density between 2000 and 2020, and 42% of the variation in income change between 2000 and 2017. Both Khachiyan et al [36] and Yeh et al (2020) use CNNs for prediction.…”

Section: Predictions Across Time Are Much Less Accurate Than Predicti...mentioning

confidence: 99%

Small Area Estimation of Poverty and Wealth Using Geospatial Data: What have We Learned So Far?

Newhouse

2023

Calcutta Statistical Association Bulletin

View full text Add to dashboard Cite

This article offers a non-technical review of selected applications that combine survey and geospatial data to generate small area estimates of wealth or poverty. Publicly available data from satellites and phones predict poverty and wealth accurately across space, when evaluated against census data, and their use in model-based estimates improves the accuracy and efficiency of direct survey estimates. Models based on interpretable features appear to predict more accurately than estimates derived from convolutional neural networks. Estimates for sampled areas are significantly more accurate than those for non-sampled areas due to informative sampling. In general, estimates benefit from using geospatial data at the most disaggregated level possible. Tree-based machine learning methods appear to generate more accurate estimates than linear mixed models in common settings. Small area estimates using geospatial data can improve the design of social assistance programmes, particularly when the existing targeting system is poorly designed. AMS subject classification: 62P20

show abstract

“…First, what is apparent from studies that apply the remote sensing of cities or regions in the economic domain is that the spatial distribution of economic factors tends to be inferred only indirectly. Rather than defining conceptually what type of land cover features provide a relevant economic signal, in order to then map these features, the involved studies instead lean towards black-box type of approaches that predict local economic circumstances from conceptually limitedly defined patterns in land cover [17][18][19][20][21][22]. Although these approaches are remarkably useful for highlighting otherwise hard to observe variation in local economic development across administrative areas [23], whether any of the observed land is used for business or for other purposes remains inherently implicit as this is not conceptually defined nor measured directly.…”

Section: Introductionmentioning

confidence: 99%

Estimating the allocation of land to business

Daams

2023

PLoS ONE

View full text Add to dashboard Cite

This paper is uniquely focused on mapping business land in satellite imagery, with the aim to introduce a standardized approach to estimating how much land in an observed area is allocated to business. Business land and control categories of land are defined and operationalized in a straightforward setting of pixel-based classification. The resultant map as well as information from a sample-based quantification of the map’s accuracy are used jointly to estimate business land’s total area more precisely. In particular, areas where so-called errors of omission are possibly concentrated are accounted for by post-stratifying the map in an extension of recent advances in remote sensing. In specific, a post-stratum is designed to enclose areas where business activity is co-located. This then enhances the area estimation in a spatially explicit way that is informed by urban and regional economic thought and observation. In demonstrating the methodology, a map for the San Francisco Bay Area metropolitan area is obtained at a producer’s accuracy of 0.89 (F1-score = 0.84) or 0.82 to 0.94 when sub-selecting reference sample pixels by confidence in class assignment. Overall, the methodological approach is able to infer the allocation of land to business (in km2 ± 95% C.I.) on a timely and accurate basis. This inter-disciplinary study may offer some fundamental ground for a potentially more refined assessment and understanding of the spatial distribution of production factors as well as the related structure and implications of land use.

show abstract

Using Neural Networks to Predict Microspatial Economic Growth

Cited by 7 publications

References 32 publications

Accounting for spatial economic interactions at local and meso scales in integrated assessment model (IAM) frameworks: challenges and recent progress

Accounting for spatial economic interactions at local and meso scales in integrated assessment model (IAM) frameworks: challenges and recent progress

Small Area Estimation of Poverty and Wealth Using Geospatial Data: What have We Learned So Far?

Estimating the allocation of land to business

Contact Info

Product

Resources

About