Predicting energy poverty with combinations of remote-sensing and socioeconomic survey data in India: Evidence from machine learning
Introduction
Lack of access to modern energy has been recognized as a major hindrance to decent living standards, good health, education, and economic development. This paper aims to improve the identification of districts with a high prevalence of energy poverty to support policy efforts and better target interventions. Indeed, many governments worldwide have put programs in place to alleviate energy poverty. In India, where over 200 million people did not have access to electricity in 2016, a succession of programs, including the Deen Dayal Upadhyaya Gram Jyoti Yojana (DDUGJY) and the Saubhagya scheme, achieved great improvement in the number of households with access to electricity and put India on track to reach full electrification before 2030 (IEA, 2017). However, supply reliability and affordability issues mean that access to electricity is still a challenge for many and the gap to full electrification varies geographically, especially within states (Jain et al., 2018). In 2017, about 60% of the population still relied on biomass for cooking and averaged over one hour per day collecting fuel (IEA, 2017). The 2016 government program, Pradhan Mantri Ujjwala Yojana (PMUY), achieved notable success in shifting household consumption away from biomass toward increasing use of liquefied petroleum gas (LPG). However, here again, LPG adoption varies from state to state and within states (Jain et al., 2018).
One of the reasons it is difficult to tackle energy poverty lies in its multiple causes and repercussions. In developing countries, energy poverty describes insufficient access to modern energy services: lighting and powering appliances via electric power, and clean cooking via LPG (Li et al., 2014). Specifically, the reliance on traditional biomass (dung cake, agro residues, firewood), and to a lesser extent on kerosene, is problematic due to the unfair burden it places on energy-poor households with respect to fuel collection, fuel inefficiency, health consequences, or financial implications (Heltberg, 2003; Malla and Timilsina, 2014; Poblete-Cazenave and Pachauri, 2018). Day et al.'s (2016) definition, based on Sen's capability approach, is particularly suitable for capturing the multidimensional nature of energy poverty:
An inability to realize essential capabilities as a direct or indirect result of insufficient access to affordable, reliable and safe energy services, and taking into account available reasonable alternative means of realizing these capabilities (Day et al., 2016).
This approach is also consistent with recent findings from high-income countries that energy poverty is associated with decreased subjective wellbeing (Churchill et al., 2020; Welsch and Biermann, 2017). Estimations of energy poverty have moved from simple, economic-based measures to a range of multidimensional energy poverty indexes (MEPI) that focus on physical access to electricity, affordability, and access to equipment, cost, and efficiency.
The many factors involved in measuring energy poverty with a MEPI require information on socioeconomic indicators and energy-specific information such as equipment, connection, price, and availability of electricity and fuel. Accordingly, an important obstacle to measuring energy poverty is data availability. This is especially true in rural areas of developing countries where practical access to the areas to conduct field surveys and the financial means to conduct the surveys are often challenging. The difficultyto collect data on a wide scale is such that institutional measures and reports are often restricted to the concept of electricity connection and omit the other aspects of energy poverty (e.g., affordability, reliability, safety, availability).
In this regard, data collected via satellite remote sensing (RS) techniques offer promising possibilities to support data collection efforts. Thanks to their wider availability and improvement in quality and coverage, RS data have found applications in many fields and have already proven to be useful to predict income poverty, alone or in combination with field data. They offer inexpensive information, comprehensive area coverage, and frequent updates. Although they cannot replace detailed individual surveys conducted on the field, they can be employed to identify areas where risk is higher. This paper observed how an energy poverty index, built with field survey data from the Council on Energy, Environment and Water (CEEW) in India, can be predicted using RS data and standard socioeconomic information. Using a random forest algorithm, it shows that RS data are good predictors of energy poverty prevalence. Thus, it can produce cost-effective information for large geographic areas to better outline risk areas and target policy attention to aid energy poverty alleviation.
In the process, we questioned the relationship between energy poverty and the physical environment surrounding households and communities. Socioeconomic causes and consequences of energy poverty have been largely studied, with income and affordability recognized as the main determinants of energy poverty. However, there has been little examination of the impact of natural elements, except for outdoor temperatures, on energy vulnerability. Thus, the first contribution of this paper is to look at whether geographical and environmental factors can be used to predict energy poverty. The use of RS data to highlight the geographical and environmental aspects of energy poverty has received limited attention, despite some studies showing that geographic information system (GIS) analysis is particularly well-suited for energy poverty prediction. The second contribution is the use of a machine learning approach to predict the districts with a high prevalence of energy poverty. Although the existing literature has substantiated the outperformance of machine learning in terms of energy prices forecasting (Herrera et al., 2019; An et al., 2019), to the best of our knowledge, very little attention has been paid to the prediction of energy poverty. To fill this research gap, we used the random forest model, a prevalent machine learning algorithm, to predict energy poverty. This paper focused on India because a large percentage of the world's energy poverty comes from India (Bhide and Monroy, 2011).
Section snippets
Defining and measuring energy poverty: a multidimensional approach
Addressing energy poverty requires first identifying what energy poverty is. However, various measuring approaches have been used over the years. Income-based and expenditure-based poverty lines propose relatively simple and easy to implement ways to measure energy poverty (Foster, 2000). Nevertheless, these approaches do not account for factors such as the effect of equipment efficiency, type of fuels, or household size, which all affect energy expenditure (Pachauri et al., 2004) and may not
Severe energy poverty index
First, the study evaluated the energy poverty levels in the study area. Churchill and Smyth (2020) and Churchill et al. (2020) highlight how energy poverty can be assessed by objective expenditure-based approaches, by the subjective appraisal of the deprivation (Thomson et al., 2017), or by a composite of several indicators. Given the various channels through which households in developing countries can experience energy poverty, we adopted a multidimensional approach to measuring energy
Energy poverty prediction
Table 5 presents the predictions for the ‘access to electricity’ component of energy poverty in India for 2015. We used three groups of predictors—socioeconomic, geographical and environmental, and mixed predictors—to evaluate prediction performances. The results show that the random forest model using the traditional socioeconomic predictors gives an out-of-bag5
Conclusions and policy implications
This paper showed that energy poverty is strongly correlated with geographical and environmental features. While the existing literature proposes various approaches to measuring energy poverty using socioeconomic predictors, few have attempted to overcome the data availability problem with predicting energy poverty. This paper differs from them by including, for the first time, variables related to the natural environment of the household. We employed a popular machine learning algorithm, the
Acknowledgements
This research is supported by the National Social Science Foundation of China (20CSH048, 20AZD024, 21ZDA062), the National Natural Science Foundation of China (71773099), the Rural Finance Survey of the Ministry of Agriculture and Rural Affairs (05190084), and the Fundamental Research Funds for the Central Universities (SWU2009105).
References (87)
- et al.
Multi-dimensional energy poverty patterns around industrial crop projects in Ghana: enhancing the energy poverty alleviation potential of rural development strategies
Energy Policy
(2020) - et al.
Solar PV power plant site selection using a GIS-AHP based approach with application in Saudi Arabia
Appl. Energy
(2017) - et al.
Energy poverty reduction by fuel switching. Impact evaluation of the LPG conversion program in Indonesia
Energy Policy
(2014) - et al.
On the competitiveness of grid-tied residential photovoltaic generation systems in Pakistan: panacea or paradox?
Energy Policy
(2018) - et al.
Evaluation of renewable energy sources in peripheral areas and renewable energy-based rural development
Renew. Sust. Energ. Rev.
(2018) Energy access problem of the poor in India: is rural electrification a remedy?
Energy Policy
(2006)- et al.
Energy poverty: a special focus on energy poverty in India and renewable energy technologies
Renew. Sust. Energ. Rev.
(2011) - et al.
Spatializing energy justice
Energy Policy
(2017) - et al.
Toward renewable energy geo-information infrastructures: applications of GIScience and remote sensing that build institutional capacity
Renew. Sust. Energ. Rev.
(2013) - et al.
Assessing the determinants and drivers of multi-dimensional energy poverty in Ghana
Energy Policy
(2019)
Conceptualising energy use and energy poverty using a capabilities framework
Energy Policy
Estimating rural populations without access to electricity in developing countries through nighttime light satellite imagery
Energy Policy
From targeting to implementation: the role of identification
Energy Policy
Determinants of household energy consumption in India
Energy Policy
A global poverty map derived from satellite data
Comput. Geosci.
Predicting fuel poverty at a small-area level in England
Energy Policy
Spatial targeting, synergies and scale: exploring the criteria of smart practices for siting renewable energy projects
Energy Policy
Energy poverty: An overview
Renew. Sust. Energ. Rev.
Energy poverty vulnerability index: a multi-dimensional tool to identify hotspots for local action
Energy Rep.
Big data and energy poverty alleviation
Big Data Cogn. Comput.
Long-term forecast of energy commodities price using machine learning
Energy
Investigating rural poverty and marginality in Burkina Faso using remote sensing-based products
Int. J. Appl. Earth Obs. Geoinf.
Energy indicators for tracking sustainability in developing countries
Energy Policy
Are the energy poor also income poor? Evidence from India
Energy Policy
Comprehensive energy poverty index: measuring energy poverty and identifying micro-level solutions in south and Southeast Asia
Energy Policy
Non-universal nature of energy poverty: energy services, assessment of needs and consumption evidences from rural Himachal Pradesh
Energy Policy
Energy poor or fuel poor: what are the differences?
Energy Policy
Estimating energy savings for the residential building stock of an entire city: a GIS-based statistical downscaling approach applied to Rotterdam
Energy Build.
Fuel poverty in Scotland: refining spatial resolution in the Scottish fuel poverty indicator using a GIS-based multiple risk index
Health Place
Household fuel use in developing countries: review of theory and evidence
Energy Econ.
Estimation of technical and economic potential of offshore wind along the coast of India
Energy
Measuring energy poverty: focusing on what matters
Renew. Sust. Energ. Rev.
On measuring energy poverty in Indian households
World Dev.
Urban energy consumption mapping for energy management
Energy Policy
Artificial neural networks and linear regression prediction models for social housing allocation: fuel poverty potential risk index
Energy
A structural model of cooking fuel choices in developing countries
Energy Econ.
PM2.5 in household kitchens of Bhaktapur, Nepal, using four different cooking fuels
Atmos. Environ.
Targeting energy justice: Exploring spatial, racial/ethnic and socioeconomic disparities in urban residential heating energy efficiency
Energy Policy
Controlling air pollution in a context of high energy poverty levels in southern Chile: clean air but colder houses?
Energy Policy
Socioeconomic determinants of energy poverty amongst Indian households: a case study of Mumbai
Energy Policy
The political economy of energy poverty: a review of key challenges
Energy Sustain. Develop.
Area-based targeting of fuel poverty in Northern Ireland: An evidenced-based approach
Appl. Geogr.
Evaluating fuel poverty policy in Northern Ireland using a geographic approach
Energy Policy
Cited by (20)
Energy poverty assessment: Indicators and implications for developing and developed countries
2024, Energy Conversion and ManagementEnergy poverty prediction in the United Kingdom: A machine learning approach
2024, Energy PolicyEnergy poverty and beyond: The state, contexts, and trajectories of energy poverty studies in Asia
2023, Energy Research and Social Science
- 1
These authors equally share the first authorship.