Using VIIRS Day/Night Band to Measure Electricity Supply Reliability: Preliminary Results from Maharashtra, India

Abstract

Unreliable electricity supplies are common in developing countries and impose large socio-economic costs, yet precise information on electricity reliability is typically unavailable. This paper presents preliminary results from a machine-learning approach for using satellite imagery of nighttime lights to develop estimates of electricity reliability for western India at a finer spatial scale. We use data from the Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar Partnership (SNPP) satellite together with newly-available data from networked household voltage meters. Our results point to the possibilities of this approach as well as areas for refinement. With currently available training data, we find a limited ability to detect individual outages identified by household-level measurements of electricity voltage. This is likely due to the relatively small number of individual outages observed in our preliminary data. However, we find that the approach can estimate electricity reliability rates for individual locations fairly well, with the predicted versus actual regression yielding an R 2 > 0.5. We also find that, despite the after midnight overpass time of the SNPP satellite, the reliability estimates derived are representative of daytime reliability.

Synergistic Use of Nighttime Satellite Data, Electric Utility Infrastructure, and Ambient Population to Improve Power Outage Detections in Urban Areas

“…Our results with a post-processed DNB product are improved compared to Mann et al who used the random forest algorithm combined with raw, unprocessed DNB imagery to classify whether or not an outage occurred in a grid cell using household-level outage data [42]. Although the overall error rate from the Mann et al study was 2.69%, their model was much better at classifying grid cells without household outages (3.63% error) than grid cells with household outages (62% error), which the authors attribute to small sample size (<3% of all observations were actual outages).…”

Variation of Individual Location Radiance in VIIRS DNB Monthly Composite Images

“…• Differences in imaging angle [14,15] • Time of night (because lights turn off as night progresses) [16,17] • Seasonal variations in vegetation and snow cover [18] • Atmospheric parameters such as aerosol content [19] • Shift in the ground footprint of pixels, and/or differing pixels used in building monthly or annual composites [20] • Changes in the sensitivity or errors in calibration of the imaging sensor [21] • Presence or absence of moonlight [21,22] • Presence or absence of temporary (e.g. seasonal) lighting [23] • Electrical blackouts or brownouts, disasters [24][25][26] • Actual changes in permanently installed lighting [9,10,27,28] For example, consider how different imaging angles affect the visibility of facade lighting (Fig 1, see also [29]). The two aerial photographs of the area near Berlin's "Zoologischen Garten" train station appear similar at first glance.…”

An Object Similarity-Based Thresholding Method for Urban Area Mapping from Visible Infrared Imaging Radiometer Suite Day/Night Band (VIIRS DNB) Data

“…Because of the improved performance, VIIRS DNB data have been used in various applications, such as extracting urban areas [23][24][25][26][27], reflecting demographic and socioeconomic conditions [25,[28][29][30][31][32][33], monitoring nocturnal surface air quality [34][35][36], and so on [26,[37][38][39][40][41].…”