Recent publications
-
IRPS 20232023Investigation of li-ion battery state of health (SOH) degradation and its modeling facilitates determination of device warranty and can provide information about the device battery health. For such studies, batteries undergo life-cycling test with fixed cycling depths and charging currents (C-rates) across cycles, and the gathered degradation data is used for model development. However, in the real world
-
Products contribute to carbon emissions in each phase of their life cycle, from manufacturing to disposal. Estimating the embodied carbon in products is a key step towards understanding their impact, and undertaking mitigation actions. Precise carbon attribution is challenging at scale, requiring both domain expertise and granular supply chain data. As a first-order approximation, standard reports use Economic
-
2022Conventionally, Earth system (e.g., weather and climate) forecasting relies on numerical simulation with complex physical models and hence is both expensive in computation and demanding on domain expertise. With the explosive growth of spatiotemporal Earth observation data in the past decade, data-driven models that apply Deep Learning (DL) are demonstrating impressive potential for various Earth system
-
AI-ML Systems 20222022We showcase a novel solution to a recommendation system problem where we face a perpetual soft item cold start issue. Our system aims to recommend demanded products to prospective sellers for listing in Amazon stores. These products always have only few interactions thereby giving rise to a perpetual soft item cold start situation. Modern collaborative filtering methods solve cold start using content attributes
-
2022We address performance fairness for speaker verification using the adversarial reweighting (ARW) method. ARW is reformulated for speaker verification with metric learning, and shown to improve results across different subgroups of gender and nationality, without requiring annotation of subgroups in the training data. An adversarial network learns a weight for each training sample in the batch so that the
Related content
-
Amazon is committed to building a sustainable business for our customers and the planet. Learn more about the company's goals, strategies and policies in our sustainability report.
-
February 24, 2023Session focused on tips and tools that can help customers reduce the carbon footprint of artificial intelligence and machine learning workloads.
-
January 09, 2023Mehrdad Mahdjoubi, founder and CEO of Alexa Fund portfolio company, explains ‘no compromise’ approach to saving resources without sacrificing user experience.
-
December 13, 2022Amazon advocates for updating carbon accounting to measure where renewable-energy projects will have the greatest impact.
-
October 18, 2022Examining the opportunities for reducing energy consumption in robotics and automation across Amazon's fulfillment center network.
-
September 30, 2022NeurIPS competition involves reinforcement learning, with the objective of minimizing both cost and CO2 emissions.
-
September 30, 2022How data-driven methods can help to identify fault detection and drive energy efficiencies for facilities of all sizes.
-
August 01, 2022Confronting climate change requires the participation of governments, companies, academics, civil-society organizations, and the public.
-
July 25, 2022Pioneering web-based PackOpt tool has resulted in an annual reduction in cardboard waste of 7% to 10% in North America, saving roughly 60,000 tons of cardboard annually.
-
March 09, 2022Amazon joins the US DOE’s Bio-Optimized Technologies to keep Thermoplastics out of Landfills and the Environment (BOTTLE™) Consortium, focusing on materials and recycling innovation.
-
January 04, 2022A combination of deep learning, natural language processing, and computer vision enables Amazon to hone in on the right amount of packaging for each product.
-
November 22, 2021Lise St. Denis, a research scientist at the University of Colorado, says social media can be useful for responders. Now she's helping them separate truly useful info from the noise.
-
November 12, 2021Paper by Netessine and co-authors focuses on encouraging adoption of sustainable, off-grid lighting solutions in poorer areas of the world.
-
November 09, 2021How the Amazon Logistics Research Science team guides important decisions related to last-mile delivery.
-
October 05, 2021The Oxford professor says merging AI, ML, and climate science can help us understand the impact of aerosol-cloud interactions on climate.
-
September 22, 2021As office buildings become smarter, it is easier to configure them with sustainability management in mind.
-
August 23, 2021Coordinated automation could improve traffic flow, boost efficiency, and slash emissions. A combination of machine learning, big data, and Amazon Web Services is making this future possible.
-
July 14, 2021With the help of new machine learning techniques, a team at Caltech is upgrading their system to help scientists identify more earthquakes — and understand why they happen.
-
July 07, 2021James Hensman joins an effort to expand machine learning talent for UN sustainability goals.
-
June 30, 2021How Amazon is aligning its decarbonization goals with the best available science.
-
April 22, 2021Cloud access to the CMIP6 dataset will enable climate scientists and researchers to study future climate conditions more easily.