@article{rachunok_verma_fletcher_2024, title={Predicting and understanding residential water use with interpretable machine learning}, volume={19}, ISSN={["1748-9326"]}, url={https://doi.org/10.1088/1748-9326/ad1434}, DOI={10.1088/1748-9326/ad1434}, abstractNote={Abstract}, number={1}, journal={ENVIRONMENTAL RESEARCH LETTERS}, author={Rachunok, Benjamin and Verma, Aniket and Fletcher, Sarah}, year={2024}, month={Jan} }
 @article{rachunok_fletcher_2023, title={Socio-hydrological drought impacts on urban water affordability}, url={https://doi.org/10.1038/s44221-022-00009-w}, DOI={10.1038/s44221-022-00009-w}, abstractNote={In water-stressed regions, droughts pose a critical challenge to urban water security for low-income households. Droughts reduce water availability, forcing water providers to invest in additional supplies or enact expensive, short-term emergency measures. These costs are frequently passed on to households through increased rates and surcharges, driving up water bills for low-income households and altering patterns of water consumption. Here we have developed a socio-hydrological modelling approach that integrates hydrology, water infrastructure, utility decision-making and household behaviour to understand the impacts of droughts on household water affordability. We present here an application based on Santa Cruz, California and show that many drought resilience strategies raise water bills for low-income households and lower them for high-income households. We also found that low-income households are most vulnerable to both changing drought characteristics and infrastructure lock-in. Unaffordable water prices pose a threat to human health and well-being. A socio-hydrological modelling approach that integrates hydrology, water infrastructure, utility decision-making and household behaviour can be used to understand the impacts of droughts on household water affordability}, journal={Nature Water}, author={Rachunok, Benjamin and Fletcher, Sarah}, year={2023}, month={Jan} }
 @article{nayak_rachunok_thompson_fletcher_2023, title={Socio-hydrological impacts of rate design on water affordability during drought}, volume={18}, ISSN={["1748-9326"]}, url={https://doi.org/10.1088/1748-9326/ad0994}, DOI={10.1088/1748-9326/ad0994}, abstractNote={Abstract}, number={12}, journal={ENVIRONMENTAL RESEARCH LETTERS}, author={Nayak, Adam and Rachunok, Benjamin and Thompson, Barton and Fletcher, Sarah}, year={2023}, month={Dec} }
 @article{bennett_rachunok_flage_nateghi_2021, title={Mapping climate discourse to climate opinion: An approach for augmenting surveys with social media to enhance understandings of climate opinion in the United States}, url={https://doi.org/10.1371/journal.pone.0245319}, DOI={10.1371/journal.pone.0245319}, abstractNote={Surveys are commonly used to quantify public opinions of climate change and to inform sustainability policies. However, conducting large-scale population-based surveys is often a difficult task due to time and resource constraints. This paper outlines a machine learning framework—grounded in statistical learning theory and natural language processing—to augment climate change opinion surveys with social media data. The proposed framework maps social media discourse to climate opinion surveys, allowing for discerning the regionally distinct topics and themes that contribute to climate opinions. The analysis reveals significant regional variation in the emergent social media topics associated with climate opinions. Furthermore, significant correlation is identified between social media discourse and climate attitude. However, the dependencies between topic discussion and climate opinion are not always intuitive and often require augmenting the analysis with a topic’s most frequent n-grams and most representative tweets to effectively interpret the relationship. Finally, the paper concludes with a discussion of how these results can be used in the policy framing process to quickly and effectively understand constituents’ opinions on critical issues.}, journal={PLOS ONE}, author={Bennett, Jackson and Rachunok, Benjamin and Flage, Roger and Nateghi, Roshanak}, editor={Grabar, NataliaEditor}, year={2021}, month={Jan} }
 @article{rachunok_nateghi_2021, title={Overemphasis on recovery inhibits community transformation and creates resilience traps}, url={https://doi.org/10.1038/s41467-021-27359-5}, DOI={10.1038/s41467-021-27359-5}, abstractNote={Abstract}, journal={Nature Communications}, author={Rachunok, Benjamin and Nateghi, Roshanak}, year={2021}, month={Dec} }
 @article{choi_rachunok_nateghi_2021, title={Short-term solar irradiance forecasting using convolutional neural networks and cloud imagery}, volume={16}, url={https://doi.org/10.1088/1748-9326/abe06d}, DOI={10.1088/1748-9326/abe06d}, abstractNote={Abstract}, number={4}, journal={Environmental Research Letters}, publisher={IOP Publishing}, author={Choi, Minsoo and Rachunok, Benjamin and Nateghi, Roshanak}, year={2021}, month={Apr}, pages={044045} }
 @article{obringer_rachunok_maia-silva_arbabzadeh_nateghi_madani_2021, title={The overlooked environmental footprint of increasing Internet use}, volume={167}, url={https://doi.org/10.1016/j.resconrec.2020.105389}, DOI={10.1016/j.resconrec.2020.105389}, journal={Resources, Conservation and Recycling}, publisher={Elsevier BV}, author={Obringer, Renee and Rachunok, Benjamin and Maia-Silva, Debora and Arbabzadeh, Maryam and Nateghi, Roshanak and Madani, Kaveh}, year={2021}, month={Apr}, pages={105389} }
 @article{kanmani_obringer_rachunok_nateghi_2020, title={Assessing Global Environmental Sustainability Via an Unsupervised Clustering Framework}, volume={12}, url={https://doi.org/10.3390/su12020563}, DOI={10.3390/su12020563}, abstractNote={The importance of sustainable development has risen in recent years due to the significant number of people affected by lack of access to essential resources as well as the need to prepare for and adapt to intensifying climate change and rapid urbanization. Modeling frameworks capable of effectively assessing and tracking sustainability lie at the heart of creating effective policies to address these issues. Conventional frameworks, such as the Environmental Performance Index (EPI), that support such policies often involve ranking countries based on a weighted sum of a number of relevant environmental metrics. However, the selection and weighing processes are often biased. Moreover, the ranking process fails to provide policymakers with possible avenues to improve their country’s environmental sustainability. This study aimed to address these gaps by proposing a novel data-driven framework to assess the environmental sustainability of countries objectively by leveraging unsupervised learning theory. Specifically, this framework harnesses a clustering technique known as Self-Organized Maps to group countries based on their characteristic environmental performance metrics and track progression in terms of shifts within clusters over time. The results support the hypothesis that the inconsistencies in the EPI calculation can lead to misrepresentations of the relative sustainability of countries over time. The proposed framework, which does not rely on ranking or data transformations, enables countries to make more informed decisions by identifying effective and specific pathways towards improving their environmental sustainability.}, number={2}, journal={Sustainability}, publisher={MDPI AG}, author={Kanmani, Aiyshwariya Paulvannan and Obringer, Renee and Rachunok, Benjamin and Nateghi, Roshanak}, year={2020}, month={Jan}, pages={563} }
 @article{assessment of wind power scenario creation methods for stochastic power systems operations_2020, url={http://dx.doi.org/10.1016/j.apenergy.2020.114986}, DOI={10.1016/j.apenergy.2020.114986}, abstractNote={Probabilistic scenarios of renewable energy production, such as wind, have been gaining popularity for use in stochastic variants of power systems operations scheduling problems, allowing for optimal decision-making under uncertainty. The quality of the scenarios has a direct impact on the value of the resulting decisions, but until now, methods for creating scenarios have not been compared under realistic operational conditions. Here, we compare the quality of scenario sets created using three different methods, based on a simulated re-enactment of stochastic day-ahead unit commitment and subsequent dispatch for a realistic test system. We create scenarios using a dataset of forecasted and actual wind power values, scaled to evaluate the effects of increasing wind penetration levels. We show that the choice of scenario set can significantly impact system operating cost, renewable energy use, and the ability of the system to meet demand. This result has implications for the ability of system operators to efficiently integrate renewable production into their day-ahead planning, highlighting the need for the use of performance-based assessments for scenario evaluation.}, journal={Applied Energy}, year={2020}, month={Jun} }
 @article{kumar_rachunok_maia-silva_nateghi_2020, title={Asymmetrical response of California electricity demand to summer-time temperature variation}, url={https://doi.org/10.1038/s41598-020-67695-y}, DOI={10.1038/s41598-020-67695-y}, abstractNote={Abstract}, journal={Scientific Reports}, author={Kumar, Rohini and Rachunok, Benjamin and Maia-Silva, Debora and Nateghi, Roshanak}, year={2020}, month={Jul} }
 @article{alemazkoor_rachunok_chavas_staid_louhghalam_nateghi_tootkaboni_2020, title={Hurricane-induced power outage risk under climate change is primarily driven by the uncertainty in projections of future hurricane frequency}, url={http://dx.doi.org/10.1038/s41598-020-72207-z}, DOI={10.1038/s41598-020-72207-z}, abstractNote={Abstract Nine in ten major outages in the US have been caused by hurricanes. Long-term outage risk is a function of climate change-triggered shifts in hurricane frequency and intensity; yet projections of both remain highly uncertain. However, outage risk models do not account for the epistemic uncertainties in physics-based hurricane projections under climate change, largely due to the extreme computational complexity. Instead they use simple probabilistic assumptions to model such uncertainties. Here, we propose a transparent and efficient framework to, for the first time, bridge the physics-based hurricane projections and intricate outage risk models. We find that uncertainty in projections of the frequency of weaker storms explains over 95% of the uncertainty in outage projections; thus, reducing this uncertainty will greatly improve outage risk management. We also show that the expected annual fraction of affected customers exhibits large variances, warranting the adoption of robust resilience investment strategies and climate-informed regulatory frameworks.}, journal={Scientific Reports}, author={Alemazkoor, Negin and Rachunok, Benjamin and Chavas, Daniel R and Staid, Andrea and Louhghalam, Arghavan and Nateghi, Roshanak and Tootkaboni, Mazdak}, year={2020}, month={Sep} }
 @article{the sensitivity of electric power infrastructure resilience to the spatial distribution of disaster impacts_2020, url={http://dx.doi.org/10.1016/j.ress.2019.106658}, DOI={10.1016/j.ress.2019.106658}, abstractNote={Credibly assessing the resilience of energy infrastructure in the face of natural disasters is a salient concern facing researchers, government officials, and community members. Here, we explore the influence of the spatial distribution of disruptions due to hurricanes and other natural hazards on the resilience of power distribution systems. We find that incorporating information about the spatial distribution of disaster impacts has significant implications for estimating infrastructure resilience. Specifically, the uncertainty associated with estimated infrastructure resilience metrics to spatially distributed disaster-induced disruptions is much higher than determined by previous methods. We present a case study of an electric power distribution grid impacted by a major landfalling hurricane. We show that improved characterizations of disaster disruption drastically change the way in which the grid recovers, including changes in emergent system properties such as antifragility. Our work demonstrates that previous methods for estimating critical infrastructure resilience may be overstating the confidence associated with estimated network recoveries due to the lack of consideration of the spatial structure of disruptions.}, journal={Reliability Engineering & System Safety}, year={2020}, month={Jan} }
 @article{rachunok_bennett_nateghi_2019, title={Twitter and Disasters: A Social Resilience Fingerprint}, volume={7}, url={https://doi.org/10.1109/ACCESS.2019.2914797}, DOI={10.1109/ACCESS.2019.2914797}, abstractNote={Understanding the resilience of a community facing a crisis event is critical to improving its adaptive capacity. Community resilience has been conceptualized as a function of the resilience of components of a community such as ecological, infrastructure, economic, and social systems, etc. In this paper, we introduce the concept of a “resilience fingerprint” and propose a multi-dimensional method for analyzing components of community resilience by leveraging existing definitions of community resilience with data from the social network Twitter. Twitter data from 14 events are analyzed and their resulting resilience fingerprints computed. We compare the fingerprints between events and show that major disasters such as hurricanes and earthquakes have a unique resilience fingerprint which is consistent between different events of the same type. Specifically, hurricanes have a distinct fingerprint which differentiates them from other major events. We analyze the components underlying the similarity among hurricanes and find that ecological, infrastructure and economic components of community resilience are the primary drivers of the difference between the community resilience of hurricanes and other major events.}, journal={IEEE Access}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Rachunok, Benjamin A. and Bennett, Jackson B. and Nateghi, Roshanak}, year={2019}, pages={58495–58506} }
 @inproceedings{stochastic unit commitment performance considering monte carlo wind power scenarios_2018, url={http://dx.doi.org/10.1109/pmaps.2018.8440563}, DOI={10.1109/pmaps.2018.8440563}, abstractNote={Stochastic versions of the unit commitment problem have been advocated for addressing the uncertainty presented by high levels of wind power penetration. However, little work has been done to study trade-offs between computational complexity and the quality of solutions obtained as the number of probabilistic scenarios is varied. Here, we describe extensive experiments using real publicly available wind power data from the Bonneville Power Administration. Solution quality is measured by re-enacting day-ahead reliability unit commitment (which selects the thermal units that will be used each hour of the next day) and real-time economic dispatch (which determines generation levels) for an enhanced WECC-240 test system in the context of a production cost model simulator; outputs from the simulation, including cost, reliability, and computational performance metrics, are then analyzed. Unsurprisingly, we find that both solution quality and computational difficulty increase with the number of probabilistic scenarios considered. However, we find unexpected transitions in computational difficulty at a specific threshold in the number of scenarios, and report on key trends in solution performance characteristics. Our findings are novel in that we examine these tradeoffs using real-world wind power data in the context of an out-of-sample production cost model simulation, and are relevant for both practitioners interested in deploying and researchers interested in developing scalable solvers for stochastic unit commitment.}, booktitle={2018 IEEE International Conference on Probabilistic Methods Applied to Power Systems (PMAPS)}, year={2018}, month={Jun} }