EconBase
← All papers

Nowcasting Italian Municipal Income with Nightlights: A Deep Learning Approach

Massimo Giannini

arXiv 9 May 2026 · Econometrics

arXiv:2605.08782 · PDF · DOI · OpenAlex · Extracted main text

Abstract

This paper assesses whether NASA Black Marble nightlight intensity can serve as an early indicator of annual taxable income at the Italian municipal level, where official data are released with a 12--18 month lag. Using a panel of 7{,}631 municipalities over 2012--2021, we compare four recurrent neural network architectures (LSTM, BiLSTM, GRU, Transformer) against six benchmarks: simple persistence, panel fixed effects, autoregressive distributed lag, and two spatial econometric specifications (SAR, Spatial Durbin) on a queen-contiguity matrix. Models are trained on 2012--2019 and evaluated out-of-sample on 2020--2021 with a cross-sectional Diebold--Mariano test. A single-layer GRU achieves a median forecast error of 1.07 million euros across the cross-section of municipalities -- approximately $4%$ of the median municipal IRPEF income of 29 million euros -- statistically dominating every benchmark (DM $>4$ against persistence, $>40$ against spatial linear models, all $p<0.001$). Spatial models recover statistically significant spatial autocorrelation ($ρ\approx 0.71$) and a meaningful nightlight spillover ($θ\approx 0.05$), but their forecasting gap with the GRU is virtually identical to that of spatially-naive linear specifications. We conclude that nightlights contain genuine predictive content for municipal income, but extracting it requires a model class flexible enough to capture cross-sectional heterogeneity and non-linearities that linear specifications, spatial or otherwise, cannot recover.

Citation extraction

20
references
47
in-text mentions
20
distinct cited
0
self-citations
9,644
main-text words

appendix boundary found by appendix_command · 79% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Goulet Coulombe, Philippe and Leroux, Maxime and Stevanovic, Dalibor… (2022) How Is Machine Learning Useful for Macroeconomic Forecasting?0.9285580%
2Medeiros, Marcelo C. and Vasconcelos, Gabriel F. R. and Veiga, Álvar… (2021) Forecasting Inflation in a Data-Rich Environment: The Benefits of Machine Learning Methods0.9285580%
3Pesaran, M. Hashem (2007) A Simple Panel Unit Root Test in the Presence of Cross-Section Dependence0.84333100%
4Zeng, Ailing and Chen, Muxi and Zhang, Lei and Xu, Qiang (2023) Are Transformers Effective for Time Series Forecasting?0.7373367%
5Henderson, J. Vernon and Storeygard, Adam and Weil, David N (2012) Measuring Economic Growth from Outer Space0.73732100%
6LeSage, James and Pace, R. Kelley (2009) Introduction to Spatial Econometrics0.73732100%
7Chen, Xi and Nordhaus, William D (2011) Using Luminosity Data as a Proxy for Economic Statistics0.64422100%
8Chow, Gregory C. and Lin, An-loh (1971) Best Linear Unbiased Interpolation, Distribution, and Extrapolation of Time Series by Related Series0.64422100%
9Donaldson, Dave and Storeygard, Adam (2016) The View from Above: Applications of Satellite Data in Economics0.64422100%
10Román, Miguel O. and Wang, Zhuosen and Sun, Qingsong and Kalb, Virgi… (2018) NASA's Black Marble Nighttime Lights Product Suite0.64422100%

Showing the top 10 of 20 scored citations.