Frugal innovations are often associated with sustainable development. These connections, however, are based on anecdotal assumptions rather than empirical evidence. This article evaluates the sustainability of four frugal innovations from water and energy sectors. For the purposes of the evaluation, a set of indicators was developed. Indicators are drawn from sustainable development goals by the United Nations and they encompass central dimensions of sustainability: ecological, social and economic. In this article, frugal innovations are compared to solutions that are currently used in similar low-income contexts. Studied frugal innovations were found more sustainable in terms of energy production and water purification capacity than the existing solutions. In terms of social sustainability, larger differences between innovations were found. For example, business models of frugal energy solutions focus on capacity building and the inclusion of marginalized low-income people, whereas business models of water purification solutions focus on more traditional corporate social responsibility activities, such as marketing awareness campaigns and cooperation with non-governmental organizations. Three major sustainability challenges for frugal innovators were identified: (1) the proper integration of material efficiency into product or service systems; (2) the patient promotion of inclusive employment; and (3) the promotion of inclusive and sustainable local industrialization. The article concludes that despite indisputable similarities between frugality and sustainability, it is problematic to equate the two conceptually.

Water is perhaps the most intertwined, and basic, resource on our planet. Nevertheless, billions face water-related challenges, varying from lack of water and sanitation services to hindrances on livelihoods and socio-economic activities. The Sustainable Development Goals (SDGs) recognize the broad role that water has for development, and also call for the private sector to participate in solving these numerous development challenges. This study looks into the potential of frugal innovations as a means for the private sector to engage in water-related development challenges. Our findings, based on a case study and literature review, indicate that frugal innovations have potential in this front due to their focus on affordable, no-frills solutions. However, we also recognize pitfalls related to frugal innovations in the water sector. Although the innovations would, in principle, be sustainable, deficiencies related to scale and institutional structures may emerge. These deficiencies are linked to the importance of water in a variety of processes, both natural and manmade, as well as to the complexity of global production-consumption value chains. Increasing the innovations’ sustainability impact requires broader acknowledgement of the underlying value chains and their diverse links with water. A holistic view on water can mitigate water-related business risks while increasing wellbeing on an individual level.

Ensuring sufficient free residual chlorine (FRC) up to the time and place water is consumed in refugee settlements is essential for preventing the spread of waterborne illnesses. Water system operators need accurate forecasts of FRC during the household storage period. However, factors that drive FRC decay after water leaves the piped distribution system vary substantially, introducing significant uncertainty when modelling point-of-consumption FRC. Artificial neural network (ANN) ensemble forecasting systems (EFS) can account for this uncertainty by generating probabilistic forecasts of point-of-consumption FRC. ANNs are typically trained using symmetrical error metrics like mean squared error (MSE), but this leads to forecast underdispersion forecasts (the spread of the forecast is smaller than the spread of the observations). This study proposes to solve forecast underdispersion by training an ANN-EFS using cost functions that combine alternative metrics (Nash-Sutcliffe efficiency, Kling Gupta Efficiency, Index of Agreement) with cost-sensitive learning (inverse FRC weighting, class-based FRC weighting, inverse frequency weighting). The ANN-EFS trained with each cost function was evaluated using water quality data from refugee settlements in Bangladesh and Tanzania by comparing the percent capture, confidence interval reliability diagrams, rank histograms, and the continuous ranked probability. Training the ANN-EFS using the cost functions developed in this study produced up to a 70% improvement in forecast reliability and dispersion compared to the baseline cost function (MSE), with the best performance typically obtained by training the model using Kling-Gupta Efficiency and inverse frequency weighting. Our findings demonstrate that training the ANN-EFS using alternative metrics and cost-sensitive learning can improve the quality of forecasts of point-of-consumption FRC and better account for uncertainty in post-distribution chlorine decay. These techniques can enable humanitarian responders to ensure sufficient FRC more reliably at the point-of-consumption, thereby preventing the spread of waterborne illnesses.