Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Heatwave increases nighttime light intensity in hyperdense cities of the Global South: A double machine learning study

Ramit Debnath, Taran Chandel, Fengyuan Han, Ronita Bardhan

TL;DR

This paper investigates whether heatwaves increase nighttime urban activity in four hyperdense Global South cities by linking heatwave episodes to nighttime light via a causal, double/debiased machine learning framework. The authors construct city-specific heatwave definitions, apply a two-stage DML estimator to isolate the direct effect on $Y[c,t] = log(NTL[c,t])$, and confirm robust, temporally lagged increases in nighttime activity with clear cross-city heterogeneity. Key findings show significant NTL increases on Day 3 for Cairo, Delhi, and Guangzhou, and on Day 4 for São Paulo, with longer heatwaves producing larger effects. These results inform heat-resilience and urban planning by highlighting how behavioral shifts to nighttime activity can alter energy demand and infrastructure needs, especially in resource-constrained urban environments.

Abstract

Heatwaves, intensified by climate change and rapid urbanisation, pose significant threats to urban systems, particularly in the Global South, where adaptive capacity is constrained. This study investigates the relationship between heatwaves and nighttime light (NTL) radiance, a proxy of nighttime economic activity, in four hyperdense cities: Delhi, Guangzhou, Cairo, and Sao Paulo. We hypothesised that heatwaves increase nighttime activity. Using a double machine learning (DML) framework, we analysed data from 2013 to 2019 to quantify the impact of heatwaves on NTL while controlling for local climatic confounders. Results revealed a statistically significant increase in NTL intensity during heatwaves, with Cairo, Delhi, and Guangzhou showing elevated NTL on the third day, while São Paulo exhibits a delayed response on the fourth day. Sensitivity analyses confirmed the robustness of these findings, indicating that prolonged heat stress prompts urban populations to shift activities to night. Heterogeneous responses across cities highlight the possible influence of urban morphology and adaptive capacity to heatwave impacts. Our findings provide a foundation for policymakers to develop data-driven heat adaptation strategies, ensuring that cities remain liveable and economically resilient in an increasingly warming world.

Heatwave increases nighttime light intensity in hyperdense cities of the Global South: A double machine learning study

TL;DR

This paper investigates whether heatwaves increase nighttime urban activity in four hyperdense Global South cities by linking heatwave episodes to nighttime light via a causal, double/debiased machine learning framework. The authors construct city-specific heatwave definitions, apply a two-stage DML estimator to isolate the direct effect on , and confirm robust, temporally lagged increases in nighttime activity with clear cross-city heterogeneity. Key findings show significant NTL increases on Day 3 for Cairo, Delhi, and Guangzhou, and on Day 4 for São Paulo, with longer heatwaves producing larger effects. These results inform heat-resilience and urban planning by highlighting how behavioral shifts to nighttime activity can alter energy demand and infrastructure needs, especially in resource-constrained urban environments.

Abstract

Heatwaves, intensified by climate change and rapid urbanisation, pose significant threats to urban systems, particularly in the Global South, where adaptive capacity is constrained. This study investigates the relationship between heatwaves and nighttime light (NTL) radiance, a proxy of nighttime economic activity, in four hyperdense cities: Delhi, Guangzhou, Cairo, and Sao Paulo. We hypothesised that heatwaves increase nighttime activity. Using a double machine learning (DML) framework, we analysed data from 2013 to 2019 to quantify the impact of heatwaves on NTL while controlling for local climatic confounders. Results revealed a statistically significant increase in NTL intensity during heatwaves, with Cairo, Delhi, and Guangzhou showing elevated NTL on the third day, while São Paulo exhibits a delayed response on the fourth day. Sensitivity analyses confirmed the robustness of these findings, indicating that prolonged heat stress prompts urban populations to shift activities to night. Heterogeneous responses across cities highlight the possible influence of urban morphology and adaptive capacity to heatwave impacts. Our findings provide a foundation for policymakers to develop data-driven heat adaptation strategies, ensuring that cities remain liveable and economically resilient in an increasingly warming world.

Paper Structure

This paper contains 23 sections, 4 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Nighttime light (NTL) and urban productivity
  4. Heatwave-induced productivity shifts and its measurement
  5. Critique of nighttime light data
  6. Data and Methods
  7. Data & Preprocessing
  8. Conceptualization
  9. Methodology
  10. Modeling approach
  11. Hot Day Identification
  12. Heatwave Period
  13. Nuisance function estimation
  14. Orthogonalization and cross-fitting
  15. Estimation approach by Lasso and Random Forest
  16. ...and 8 more sections

Figures (4)

  • Figure 1: Visual representation of the annual mean nightime light (NTL) intensity ((in nW/cm²/sr)) for the study areas for 2013 and 2019
  • Figure 2: A directed acyclic graph (DAG) representing the causal relationship between urban heatwaves and nightlight radiance as a proxy for urban activities.
  • Figure 3: Average treatment effect (ATE) results demonstrating the effect of heatwave events on urban nightime activities in four study areas, denoted by nighttime light (NTL) radiance values. The x-axis denotes the heatwave episode on the day 2, day 3 and day 4, respectively and y-axis shows the estimated ATE (in %). Error bars shown at 95% CI.
  • Figure 4: Sensitivity analysis illustrating before and after impact impacts of heatwave events (in days) on nighttime light (NTL) radiance across the four cities. Error bars shown at 95% CI.