ITS Berkeley

Aging Diagnostics for a Commercial Sodium-ion Cell: Experimental and Simulation-based Transfer from Lithium-ion Systems

Quade, Katharina Lilith
Sauer, Dirk Uwe
Scott Moura
2025

Sodium-ion batteries are gaining attention as a cost-effective and sustainable complementary technology to their lithium counterpart. However, fully realizing their drop-in potential and integrating them into applications requires a deeper understanding of their aging behavior, as well as the implications for the overall system. A high-power, cost-sensitive application is selected, where lithium-ion cells could potentially be replaced by a cheaper complementary technology with similar power characteristics and energy density. An extensive field dataset from this application is then...

Ambient Temperature and Homicide Mortality in 307 Latin American Cities: A Case Time Series Design

Moraes, Sara Lopes de
Daniel Rodriguez
Schinasi, Leah H.
Kephart, Josiah L.
Dronova, Iryna
Bakhtsiyarava, Maryia
Caiaffa, Waleska Teixeira
Rangel-Moreno, Karla
Rodriguez-Villamizar, Laura A.
O’Neill, Marie
de Lima Friche, Amélia Augusta
Herrera López, Astrid Berena
Alazraqui, Marcio
Magalhães, Amanda Silva
Sarmiento, Olga L.
Sanchez, Brisa N.
Gouveia, Nelson
2026

Homicide is a leading cause of death in many countries, and growing evidence suggests that short-term variations in ambient temperature, especially high temperatures, might be associated with higher risk of homicide. Latin America is the most violent region in the world, yet knowledge about the linkages between ambient temperature and homicide mortality in the region remains limited. We conducted a case time series design using conditional quasi-Poisson and distributed lag non-linear models to estimate short-term associations (0-7 lag days) between daily mean temperature and homicide...

Reducing Annotation Cost in Vision Language Pedestrian Re Identification via Uncertainty Driven Sampling

Anderson, Michael
Daniel Rodriguez
Chen, Yi
2026

Scaling pedestrian re-identification for autonomous driving is limited by the cost of identity labeling across large camera networks. Inspired by CLIP-based uncertainty modal modeling, this paper proposes an active learning approach that selects labeling candidates using uncertainty in the joint vision–language embedding space. The method combines (i) uncertainty sampling for ambiguous matches, (ii) diversity sampling based on embedding coverage, and (iii) batch acquisition with redundancy control. Experiments are conducted on a large-scale dataset with 400,000 images and 50,000 identities...

DeepTimeGeo: Trajectory Reconstruction From Sparse Data With Transformer

Cao, Shangqing
Wu, Jiaman
Kasliwal, Aparimit
Chen, Baoqi
Perona, Giuseppe
Marta Gonzalez
2026

The completion of sparse Location-Based Service (LBS) data for modeling urban-scale origin-destination (OD) flow is of great importance to transportation planning applications. Sparse trajectories lack realistic human mobility patterns. Only with completed trajectories one can derive urban-scale OD flow that resembles complete travel diaries as those gathered by surveys or actively collecting phone applications. We present DeepTimeGeo (DTG), a transformer encoder-only model that reconstructs complete trajectories from sparse LBS inputs. We adopt a rank-based representation of locations to...

Learning to Recommend in Unknown Games

Alanqary, Arwa
Baba, Zakaria
Wu, Manxi
Alexandre Bayen
2026

We study preference learning through recommendations in multi-agent game settings, where a moderator repeatedly interacts with agents whose utility functions are unknown. In each round, the moderator issues action recommendations and observes whether agents follow or deviate from them. We consider two canonical behavioral feedback models-best response and quantal response-and study how the information revealed by each model affects the learnability of agents' utilities. We show that under quantal-response feedback the game is learnable, up to a positive affine equivalence class, with...

An Adaptive Estimation Approach based on Fisher Information to Overcome the Flat Voltage Plateau Challenges of SOC Estimation in LFP Batteries

Shi, Junzhe
Jiang, Shida
Tao, Shengyu
Lee, Jaewong
Borah, Manashita
Scott Moura
2026

Accurate and robust state-of-charge (SOC) estimation remains a critical challenge for lithium iron phosphate (LFP) batteries due to their flat SOC–open-circuit-voltage (OCV) characteristics, pronounced hysteresis, and non-ideal operating conditions such as current sensor bias, voltage quantization, temperature variation, and insufficient excitation. This paper proposes an adaptive SOC estimation framework that addresses these challenges through an information-aware fusion strategy. The method adaptively fuses Coulomb counting and voltage-based SOC estimation using Fisher information,...

Employment Diversification and Urban Mobility Disparities: A Multi-scale Analysis of U.S. Core-Based Statistical Areas

Wu, Zeyu
Marta Gonzalez
2026

The Economic Complexity Index (ECI), a metric traditionally utilized in international trade to correlate high complexity with lower income inequality, is evaluated here at the subnational level to determine if this relationship persists across diverse urban scales. By adapting the ECI to employment distributions across 121 Core-Based Statistical Areas (CBSAs) in five U.S. states—California, New York, New Mexico, Louisiana, and Mississippi—this study integrates Replica mobility data with American Community Survey socioeconomic indicators. The analysis reveals a significant reversal of...

Electrifying Long-haul Freight Trucks Reduces Societal Costs in the United States

Porzio, Jason
McNeil, Wilson
Tong, Fan
Scott Moura
Auffhammer, Maximilian
Scown, Corinne D.
2026

Abstract Electrifying long-haul heavy-duty vehicles (HDVs) entails high private costs but offers substantial reductions in external costs by substituting diesel combustion with electricity generation. We combine technoeconomic analysis and life-cycle assessment of lithium-ion battery electric (BE) and diesel HDVs to estimate total private costs and monetized climate and health damages in the United States. In 2025, BE-HDVs are estimated to have 46% higher private costs ($0.71 mile⁻¹) than diesel trucks, decreasing to 33% ($0.52 mile⁻¹) by 2035. However, their external costs are 64–69%...

Macroscopic Modeling and Hierarchical Control of Battery Swapping Stations

Wang, Ruiting
Čičić, Mladen
Scott Moura
Maria Laura Delle Monache
2025

Battery swapping offers a compelling alternative to fast charging for large EV fleets. By decoupling charging from vehicle dwell time, battery swapping stations (BSS) can charge batteries slower, reducing grid strain and extending battery life, while enabling quick vehicle turnaround. In this work, we present a hierarchical control architecture for large-scale BSS that addresses the computational limits of conventional integer programming approaches. By adopting a macroscopic model that represents battery states as a continuous distribution, our method captures nonlinear battery dynamics...

Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs

Baba, Zakaria
Alexandre Bayen
Canesse, Alexi
Maria Laura Delle Monache
Drieux, Martin
Fu, Zhe
Matin, Hossein Nick Zinat
Piccoli, Benedetto
2026

We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative structure of the scheme. The model can be trained both in a supervised setting with efficiently generated synthetic data or in an unsupervised manner, leveraging the weak formulation of the partial differential equation. We provide theoretical results that our model can perform arbitrarily well, and provide associated upper bounds on neural network size....