Predicting Household Water Consumption Using Satellite and Street View Images in Two Indian Cities

TL;DR

This study explores using publicly available satellite and street view images, combined with minimal geospatial data, to predict household water consumption in Indian cities, offering a cost-effective alternative to traditional surveys.

Contribution

It demonstrates that open-access imagery and simple covariates can effectively estimate household water use, nearing the accuracy of survey-based methods.

Findings

GSV segmentation with covariates achieves 0.55 accuracy

High precision at water use extremes, confusion in middle classes

Open-access imagery is a promising survey alternative

Abstract

Monitoring household water use in rapidly urbanizing regions is hampered by costly, time-intensive enumeration methods and surveys. We investigate whether publicly available imagery-satellite tiles, Google Street View (GSV) segmentation-and simple geospatial covariates (nightlight intensity, population density) can be utilized to predict household water consumption in Hubballi-Dharwad, India. We compare four approaches: survey features (benchmark), CNN embeddings (satellite, GSV, combined), and GSV semantic maps with auxiliary data. Under an ordinal classification framework, GSV segmentation plus remote-sensing covariates achieves 0.55 accuracy for water use, approaching survey-based models (0.59 accuracy). Error analysis shows high precision at extremes of the household water consumption distribution, but confusion among middle classes is due to overlapping visual proxies. We also compare and contrast our estimates for household water consumption to that of household subjective income. Our findings demonstrate that open-access imagery, coupled with minimal geospatial data, offers a promising alternative to obtaining reliable household water consumption estimates using surveys in urban analytics.