Tackling Climate Change with Machine Learning

Rolnick, David; Donti, Priya L.; Kaack, Lynn H.; Kochanski, Kelly; Lacoste, Alexandre; Sankaran, Kris; Ross, Andrew Slavin; Milojevic-Dupont, Nikola; Jaques, Natasha; Waldman‐Brown, Anna; Luccioni, Alexandra; Maharaj, Tegan; Sherwin, Evan D.; Mukkavilli, S. Karthik; Kording, Konrad P.; Gomes, Carla P.; Ng, Andrew Y.; Hassabis, Demis; Platt, John; Creutzig, Felix; Chayes, Jennifer; Bengio, Yoshua

doi:10.48550/arxiv.1906.05433

Cited by 95 publications

(105 citation statements)

References 410 publications

(482 reference statements)

Supporting

Mentioning

103

Contrasting

Unclassified

Order By: Relevance

“…Our work is a tool for the NAS community, which facilitates NAS research that may be used for positive impacts on society (for example, algorithms that reduce CO 2 emissions (Rolnick et al, 2019)) or negative impacts on society (for example, models that discriminate or exclude groups of people). Due to the increase in conversations about ethics and societal impacts in the AI community (Hecht et al, 2018), we are hopeful that the applications of our work will have a net positive impact on society.…”

Section: Ethics Statementmentioning

confidence: 99%

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Mehta¹,

White²,

Zela³

et al. 2022

Preprint

View full text Add to dashboard Cite

The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has significantly lowered the computational overhead for conducting scientific research in neural architecture search (NAS). Although they have been widely adopted and used to tune real-world NAS algorithms, these benchmarks are limited to small search spaces and focus solely on image classification. Recently, several new NAS benchmarks have been introduced that cover significantly larger search spaces over a wide range of tasks, including object detection, speech recognition, and natural language processing. However, substantial differences among these NAS benchmarks have so far prevented their widespread adoption, limiting researchers to using just a few benchmarks. In this work, we present an in-depth analysis of popular NAS algorithms and performance prediction methods across 25 different combinations of search spaces and datasets, finding that many conclusions drawn from a few NAS benchmarks do not generalize to other benchmarks. To help remedy this problem, we introduce NAS-Bench-Suite, a comprehensive and extensible collection of NAS benchmarks, accessible through a unified interface, created with the aim to facilitate reproducible, generalizable, and rapid NAS research. Our code is available at https://github.com/automl/naslib.

show abstract

Section: Ethics Statementmentioning

confidence: 99%

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Mehta¹,

White²,

Zela³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To address climate and sustainability goals, many power grids are starting to integrate larger amounts of time-varying renewable energy, such as solar and wind. As described in [52], this means power systems optimization problems must generally be solved both more quickly and at larger scales. In addition, weather extremes driven by climate change [37] yield a significant need for resilient power system optimization.…”

Section: Broader Impactsmentioning

confidence: 99%

Adversarially Robust Learning for Security-Constrained Optimal Power Flow

Donti¹,

Agarwal²,

Bedmutha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been explored. In this work, we combine innovations from these areas to tackle the problem of N-k security-constrained optimal power flow (SCOPF). N-k SCOPF is a core problem for the operation of electrical grids, and aims to schedule power generation in a manner that is robust to potentially k simultaneous equipment outages. Inspired by methods in adversarially robust training, we frame N-k SCOPF as a minimax optimization problem -viewing power generation settings as adjustable parameters and equipment outages as (adversarial) attacks -and solve this problem via gradient-based techniques. The loss function of this minimax problem involves resolving implicit equations representing grid physics and operational decisions, which we differentiate through via the implicit function theorem. We demonstrate the efficacy of our framework in solving N-3 SCOPF, which has traditionally been considered as prohibitively expensive to solve given that the problem size depends combinatorially on the number of potential outages.

show abstract

“…In the same time, AI is often presented as a solution to environmental problems, often under the larger scope of IT for Green [26,32]. The negative environmental impacts are briefly evoked -and in particular rebound effects [26] where unitary efficiency gains can lead to global GHG increase -but no quantification of all AI's environmental costs are proposed to close the loop between AI for Green and Green AI.…”

Section: Introductionmentioning

confidence: 99%

Unraveling the Hidden Environmental Impacts of AI Solutions for Environment

Ligozat¹,

Longhi²,

Bugeau³

et al. 2021

Preprint

View full text Add to dashboard Cite

In the past ten years artificial intelligence has encountered such dramatic progress that it is seen now as a tool of choice to solve environmental issues and in the first place greenhouse gas emissions (GHG). At the same time the deep learning community began to realize that training models with more and more parameters required a lot of energy and as a consequence GHG emissions. To our knowledge, questioning the complete environmental impacts of AI methods for environment ("AI for green"), and not only GHG, has never been addressed directly. In this article we propose to study the possible negative impact of "AI for green" 1) by reviewing first the different types of AI impacts 2) by presenting the different methodologies used to assess those impacts, in particular life cycle assessment and 3) by discussing how to assess the environmental usefulness of a general AI service.

show abstract

Tackling Climate Change with Machine Learning

Cited by 95 publications

References 410 publications

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Adversarially Robust Learning for Security-Constrained Optimal Power Flow

Unraveling the Hidden Environmental Impacts of AI Solutions for Environment

Contact Info

Product

Resources

About